Utilizing Human Data Validation For KPI Analysis And Machine Learning
1 like1,170 views
This document discusses utilizing human data validation for key performance indicator (KPI) analysis and machine learning. It describes Radius Intelligence's use of human validation of business data to establish ground truths for training machine learning models and evaluating data sources. While human validation provides benefits, it also incurs costs in money, time, and potential issues between validation teams and data science teams. The document outlines strategies for minimizing validation costs while meeting downstream needs through experimentation and multiple-consumer sampling techniques.
1 of 20
Downloaded 68 times
Ad
Recommended
Big Data in Production: Lessons from Running in the Cloud
Big Data in Production: Lessons from Running in the CloudJen Aman This document discusses best practices for running big data workloads in production on the cloud. It emphasizes that production systems require scalability, high availability, maintainability, and evolvability. The document also discusses challenges such as security, automation, and efficiency. It recommends leveraging cloud services like AWS to handle tasks like provisioning, monitoring, billing and cost optimization in order to focus on the core data and analytics workloads.
H2O World - Machine Learning at Comcast - Andrew Leamon & Chushi Ren
H2O World - Machine Learning at Comcast - Andrew Leamon & Chushi RenSri Ambati 1) Comcast uses machine learning for personalized recommendations on their X1 platform and to predict trending shows.
2) They apply machine learning to identify customer service issues that could potentially be avoided by a truck roll through predictive modeling.
3) Comcast also uses machine learning to develop a customer experience metric to help prioritize network deployments and understand customer needs.
Operationalizing analytics to scale
Operationalizing analytics to scaleLooker Many companies have invested time and money into building sophisticated data pipelines that can move massive amounts of data, often in real time. However, for the analyst or data scientist who builds offline models, integrating their analyses into these pipelines for operational purposes can pose a challenge.
In this slide deck, we will discuss some key technologies and workflows companies can leverage to build end-to-end solutions for automating statistical and machine learning solutions: from collection and storage to analysis and real-time predictions.
Machines and the Magic of Fast Learning
Machines and the Magic of Fast LearningSingleStore Human-machine interaction is no longer the exclusive province of science fiction. The advance of the internet and connected devices has inspired data scientists to create machine-learning applications to extract value from these new forms of data.
So what's the next frontier?
Join MemSQL Engineer Michael Andrews and Sr. Director Mike Boyarski to learn how to use real-time data as a vehicle for operationalizing machine-learning models. Michael and Mike will explore advanced tools, including TensorFlow, Apache Spark, and Apache Kafka, and compelling use cases demonstrating the power of machine learning to effect positive change.
You will learn:
Top technologies for building the ideal machine-learning stack
How to power machine-learning applications with real-time data
A use case and demo of machine learning for social good
Dataiku productive application to production - pap is may 2015 
Dataiku productive application to production - pap is may 2015 Dataiku This document discusses the development of predictive applications and outlines a vision for a platform called "Blue Box" that could help address many of the challenges in building and deploying these applications at scale. It notes that building predictive applications currently requires integrating multiple separate components. The document then describes desired features for the Blue Box platform, such as data cleansing, external data integration, model updating, decision logic, auditing, and serving predictions in real-time. It poses questions about how such a platform could be created, whether through open source or a commercial offering.
Better Customer Experience with Data Science - Bernard Burg, Comcast
Better Customer Experience with Data Science - Bernard Burg, ComcastSri Ambati This document discusses using data science and machine learning to improve the customer experience at Comcast. It describes using error data from set-top boxes and customer behavior data to predict when customers will call and the reasons for their calls. H2O machine learning algorithms were able to more accurately predict calls and reasons compared to Spark ML, improving the customer service experience. Overall, adopting H2O's algorithms provided superior results, faster performance, and better use of memory compared to alternative tools.
Beyond Data Discovery: The Value Unlocked by Modern Data Modeling
Beyond Data Discovery: The Value Unlocked by Modern Data ModelingLooker In this webinar we will discuss Looker’s novel approach to data modeling and how it powers a data exploration environment with unprecedented depth and agility.
Some topics we will cover:
-A new architecture beyond direct connect
-Language-based, git-integrated data modeling
-Abstractions that make SQL more powerful and more efficient
How to Build a Data-Driven Company: From Infrastructure to Insights
How to Build a Data-Driven Company: From Infrastructure to InsightsJanessa Lantz Companies like Buffer, SeatGeek, and Asana aren’t just talking about the value of data, they’re building data infrastructure that can actually deliver it. Join this 45-minute webinar to learn why these companies are investing in data and what you need to know to keep up.
Industrial Data Science
Industrial Data ScienceNiko Vuokko A three hour lecture I gave at the Jyväskylä Summer School. The talk goes through important details about the use of data science in real businesses. These include data deployment, data processing, practical issues with data solutions and arising trends in data science.
See also Part 1 of the lecture: Introduction Data Science. You can find it in my profile (click the face)
Understanding DataOps and Its Impact on Application Quality
Understanding DataOps and Its Impact on Application QualityDevOps.com Modern day applications are data driven and data rich. The infrastructure your backends run on are a critical aspect of your environment, and require unique monitoring tools and techniques. In this webinar learn about what DataOps is, and how critical good data ops is to the integrity of your application. Intelligent APM for your data is critical to the success of modern applications. In this webinar you will learn:
The power of APM tailored for Data Operations
The importance of visibility into your data infrastructure
How AIOps makes data ops actionable
Effective Cost Management for Amazon EMR
Effective Cost Management for Amazon EMRDevOps.com Amazon EMR has become very popular as a cloud native platform for big data. However, customers are finding unexpected costs eating into their cloud budget. Furthermore, lack of visibility to root cause and general inefficiency is costing organizations thousands, if not millions in operating their Amazon EMR environment.
Join AWS and Unravel to discover best practices to effectively manage costs on Amazon EMR. We will discuss:
Advantages of running Spark and Hadoop on Amazon EMR;
Top 5 contributors to cost overruns in Amazon EMR;
Best practices to manage Amazon EMR costs with Unravel.
Measuring Data Quality with DataOps
Measuring Data Quality with DataOpsSteven Ensslen Most organisations think that they have poor data quality, but don’t know how to measure it or what to do about it. Teams of data scientists, analysts, and ETL developers are either blindly taking a “garbage in -> garbage out” approach, or worse still, “cleansing” data to fit their limited perspectives. DataOps is a systematic approach to measuring data and for planning mitigations for bad data.
Real time analytics @ netflix
Real time analytics @ netflixCody Rioux A brief overview of Real-Time Analytics at Netflix and the challenges we've faced in designing and deploying production ready products based on real-time data.
H2O World - Self Guiding Applications with Venkatesh Yadav
H2O World - Self Guiding Applications with Venkatesh YadavSri Ambati This document discusses self-guiding mobile applications that can provide engaging user experiences through predictive features. It presents a proof of concept for a photo editing app that uses crowdsourced usage data and machine learning algorithms to predict users' next actions and display relevant tools prominently. Performance results are promising. The document recommends exposing predictive models through REST APIs for loose coupling and continuous development, demonstrating how models trained on a platform can receive API requests and send predictions to applications.
Real time machine learning
Real time machine learningVinoth Kannan The document discusses real-time machine learning using the Lambda architecture. It describes the need for models that can learn incrementally from streaming data and remain accurate over time. The Lambda architecture is introduced as having a speed layer for real-time processing, a serving layer to query current and batch views, and a batch layer for immutable datasets. Mahout is described as an Apache library for scalable machine learning like recommendation, clustering, and classification using Hadoop. Basic recommendation algorithms are covered along with use cases like e-commerce personalization, fraud detection, and media metadata generation.
Dataiku - Big data paris 2015 - A Hybrid Platform, a Hybrid Team 
Dataiku - Big data paris 2015 - A Hybrid Platform, a Hybrid Team Dataiku Between traditional Business Intelligence and "Big Data" approaches, many companies need to innovate and work in a hybrid manner. How and with what tools can business and technical profiles collaborate productively together? lorian Douetteau, Dataiku's CEO, answers these questions.
An Architecture for Agile Machine Learning in Real-Time Applications
An Architecture for Agile Machine Learning in Real-Time ApplicationsJohann Schleier-Smith Presented at KDD, August 11, 2015.
Abstract of the paper:
Machine learning techniques have proved effective in recommender systems and other applications, yet teams working to deploy them lack many of the advantages that those in more established software disciplines today take for granted. The well-known Agile methodology advances projects in a chain of rapid development cycles, with subsequent steps often informed by production experiments. Support for such workflow in machine learning applications remains primitive.
The platform developed at if(we) embodies a specific machine learning approach and a rigorous data architecture constraint, so allowing teams to work in rapid iterative cycles. We require models to consume data from a time-ordered event history, and we focus on facilitating creative feature engineering. We make it practical for data scientists to use the same model code in development and in production deployment, and make it practical for them to collaborate on complex models.
We deliver real-time recommendations at scale, returning top results from among 10,000,000 candidates with sub-second response times and incorporating new updates in just a few seconds. Using the approach and architecture described here, our team can routinely go from ideas for new models to production-validated results within two weeks.
Data kitchen 7 agile steps - big data fest 9-18-2015
Data kitchen 7 agile steps - big data fest 9-18-2015DataKitchen This document discusses applying agile principles and practices to data and analytics teams to address the complexity they face. It outlines seven steps to doing agile data work: 1) adding tests, 2) modularizing and containerizing work, 3) using branching and merging, 4) employing multiple environments, 5) giving analysts tools to experiment, 6) using simple storage, and 7) supporting small team, feature branch, and data governance workflows. The goal is to enable rapid experimentation and integration of new data sources through these agile practices adapted for analytics teams and their unique needs.
RightScale Webinar: Enterprise-Grade Cloud Cost Planning and Management
RightScale Webinar: Enterprise-Grade Cloud Cost Planning and ManagementRightScale This document summarizes a presentation about enterprise-grade cloud cost planning and management using RightScale. It discusses the need for a "mind shift" to understand cloud costs, which can involve over 12,000 pricing points and frequent changes. It then outlines RightScale's approach to cost management in three phases: investigation and planning, deploying and monitoring, and optimization. Key tips include choosing regions wisely, tagging all resources, understanding high availability and disaster recovery costs, monitoring costs across accounts, identifying idle resources, and using purchase options to reduce costs.
Embedding Data & Analytics With Looker
Embedding Data & Analytics With LookerLooker Delivering data and analytics to your customers should be straightforward. The Looker Data Platform allows for easy access to data through a robust API and embeddable charts, tables and dashboards.
Learn how Looker can help you:
- Embed charts, tables and dashboards into applications
- Use the Looker API to deliver data to applications, including Slack
- Build a customer portal to deliver more value to your customers
- Design the above with version control through Git, along with clustering and multi-server setup as needed
Real Time Business Platform by Ivan Novick from Pivotal
Real Time Business Platform by Ivan Novick from PivotalVMware Tanzu Korea This document discusses Pivotal's real time business platform for maximizing the value of data investments. It recommends identifying business problems with high ROI potential, then focusing data solutions on high-speed ingestion, consolidation, real-time queries, and analytics to drive real-time insights. The platform combines Gemfire for fast transactions with Greenplum for analytics. Use cases discussed include predictive maintenance, fraud detection, and recommendation engines. The platform provides a complete solution from data capture and analytics to application integration.
The paradox of big data - dataiku / oxalide APEROTECH
The paradox of big data - dataiku / oxalide APEROTECHDataiku The document discusses the paradoxes of big data. It notes that while data volumes are large, useful data can still be refined to fit in memory. It also discusses how the ecosystem around big data technologies like Hadoop and Spark has grown rapidly with many startups receiving funding. Practical uses of big data involve using tools like Dataiku's Data Science Studio to clean, model, and extract insights from multiple data sources to optimize processes like deliveries or improve search relevance. The document provides steps to get started with big data including learning Python/R and practicing on platforms like Kaggle to enter the field.
Big Data Day LA 2016/ Big Data Track - Rapid Analytics @ Netflix LA (Updated ...
Big Data Day LA 2016/ Big Data Track - Rapid Analytics @ Netflix LA (Updated ...Data Con LA This talk explores how Netflix equips its engineers with the freedom to find and introduce the right software for the job - even if it isn't used anywhere else in-house. Examples include how Netflix has enabled analysts to fluidly switch between MPP RDBMS and an auto-scaling Presto cluster, how Spark + NoSQL stores are used when deploying data sets to internal web apps, and how data scientists are enabled to work in the ML framework of their choosing and deploy models as a service.
Zero Downtime App Deployment using Hadoop
Zero Downtime App Deployment using HadoopDataWorks Summit/Hadoop Summit Hadoop can enable zero downtime app deployments by using microservices, continuous delivery, and real-time analytics. The presenters describe how Expedia saves $5M annually through zero downtime deployments. Their architecture uses microservices, continuous integration, deployment monitoring with Storm/Kafka/HDFS, and analytics in Solr/Hive to enable canary testing, fast feedback, and automated problem resolution. A live demo shows log processing, analytics, and using results to ensure smooth, high-quality deployments.
Spark and the Enterprise by Tony Baer
Spark and the Enterprise by Tony BaerSpark Summit This document discusses the growing popularity and capabilities of the Apache Spark platform for large-scale data analytics. It notes that Spark has over 40 committers, 1000 contributors, and is being used in 179 projects. The document highlights key features of Spark like its ease of use, performance (10-100x faster than MapReduce), flexibility, and ability to handle both batch and real-time processing. It also provides examples of how Spark can help businesses by enabling more complex analytics like predictive modeling, enabling smarter predictions, and allowing insights from real-time data. The document emphasizes that Spark advocates should focus on illustrating tangible business benefits over technical features when discussing Spark with higher-level business stakeholders.
Eric Andersen Keynote
Eric Andersen KeynoteData Con LA Google provides a suite of data and analytics services and tools for businesses to manage large datasets and gain insights from data. These include BigQuery for analytics, Cloud Dataproc for batch processing, Cloud Dataflow for streaming data, Cloud Pub/Sub for event delivery, and Cloud Bigtable for large-scale NoSQL databases. Google has been developing these services based on its own experiences managing big data over 15 years.
Big data prototyping in AWS cloud
Big data prototyping in AWS cloudSamuel Yee This document discusses using AWS cloud for rapid prototyping of big data minimum viable products (MVPs). Key benefits of cloud computing include no upfront costs, ability to scale quickly, and pay only for resources used. Typical big data use cases involve retrospective analysis, real-time processing, and machine learning. The document demonstrates building a basic Hadoop cluster on AWS in 15 minutes for word count analysis. It recommends measuring MVP outcomes and considering ongoing cloud use based on needs for 24/7 access, internal resources, and security requirements.
Smart App@Pivotal by Dat Tran
Smart App@Pivotal by Dat TranVMware Tanzu Korea This document discusses smart apps and how Pivotal uses data science to build them. It describes three key components of smart apps: data, a smart system that uses data science to understand user behavior, and a user interface. It then provides examples of smart apps Pivotal has developed for logistics and automotive customers, describing how machine learning models were used to predict delivery locations and road conditions. The document emphasizes an API-first approach and using cloud platforms like Cloud Foundry to operationalize models and deliver insights through predictive APIs.
Predicting Retail KPIs using Magento & Machine Learning
Predicting Retail KPIs using Magento & Machine LearningRud Boruah The document discusses using machine learning to predict customer behavior for a Magento e-commerce site. It outlines collecting data from Magento like product views and quotes to build models that can predict checkout intent and prevent cart abandonment. A demo is then presented on how a scalable infrastructure with a Magento extension, slave database, and NoSQL database can be used to train models on historical data and predict customer behavior in real-time.
A Spark Framework For < $100, < 1 Hour, Accurate Personalized DNA Analy...
A Spark Framework For < $100, < 1 Hour, Accurate Personalized DNA Analy...Spark Summit This document presents a Spark framework for personalized DNA analysis at large scale for under $100 and less than 1 hour. The framework segments input DNA data and runs it through three stages on a Spark cluster: 1) mapping and static load balancing, 2) sorting and dynamic load balancing, and 3) Picard deduplication and GATK variant calling. It achieves high CPU utilization, scales linearly from 1 to 20 nodes, analyzes 400GB of data in under an hour on a 35-node cluster for under $100, and has a 99.1% concordance with serial GATK. Future work involves accelerating it using FPGAs.
Ad
More Related Content
What's hot (20)
Industrial Data Science
Industrial Data ScienceNiko Vuokko A three hour lecture I gave at the Jyväskylä Summer School. The talk goes through important details about the use of data science in real businesses. These include data deployment, data processing, practical issues with data solutions and arising trends in data science.
See also Part 1 of the lecture: Introduction Data Science. You can find it in my profile (click the face)
Understanding DataOps and Its Impact on Application Quality
Understanding DataOps and Its Impact on Application QualityDevOps.com Modern day applications are data driven and data rich. The infrastructure your backends run on are a critical aspect of your environment, and require unique monitoring tools and techniques. In this webinar learn about what DataOps is, and how critical good data ops is to the integrity of your application. Intelligent APM for your data is critical to the success of modern applications. In this webinar you will learn:
The power of APM tailored for Data Operations
The importance of visibility into your data infrastructure
How AIOps makes data ops actionable
Effective Cost Management for Amazon EMR
Effective Cost Management for Amazon EMRDevOps.com Amazon EMR has become very popular as a cloud native platform for big data. However, customers are finding unexpected costs eating into their cloud budget. Furthermore, lack of visibility to root cause and general inefficiency is costing organizations thousands, if not millions in operating their Amazon EMR environment.
Join AWS and Unravel to discover best practices to effectively manage costs on Amazon EMR. We will discuss:
Advantages of running Spark and Hadoop on Amazon EMR;
Top 5 contributors to cost overruns in Amazon EMR;
Best practices to manage Amazon EMR costs with Unravel.
Measuring Data Quality with DataOps
Measuring Data Quality with DataOpsSteven Ensslen Most organisations think that they have poor data quality, but don’t know how to measure it or what to do about it. Teams of data scientists, analysts, and ETL developers are either blindly taking a “garbage in -> garbage out” approach, or worse still, “cleansing” data to fit their limited perspectives. DataOps is a systematic approach to measuring data and for planning mitigations for bad data.
Real time analytics @ netflix
Real time analytics @ netflixCody Rioux A brief overview of Real-Time Analytics at Netflix and the challenges we've faced in designing and deploying production ready products based on real-time data.
H2O World - Self Guiding Applications with Venkatesh Yadav
H2O World - Self Guiding Applications with Venkatesh YadavSri Ambati This document discusses self-guiding mobile applications that can provide engaging user experiences through predictive features. It presents a proof of concept for a photo editing app that uses crowdsourced usage data and machine learning algorithms to predict users' next actions and display relevant tools prominently. Performance results are promising. The document recommends exposing predictive models through REST APIs for loose coupling and continuous development, demonstrating how models trained on a platform can receive API requests and send predictions to applications.
Real time machine learning
Real time machine learningVinoth Kannan The document discusses real-time machine learning using the Lambda architecture. It describes the need for models that can learn incrementally from streaming data and remain accurate over time. The Lambda architecture is introduced as having a speed layer for real-time processing, a serving layer to query current and batch views, and a batch layer for immutable datasets. Mahout is described as an Apache library for scalable machine learning like recommendation, clustering, and classification using Hadoop. Basic recommendation algorithms are covered along with use cases like e-commerce personalization, fraud detection, and media metadata generation.
Dataiku - Big data paris 2015 - A Hybrid Platform, a Hybrid Team
Dataiku - Big data paris 2015 - A Hybrid Platform, a Hybrid Team Dataiku Between traditional Business Intelligence and "Big Data" approaches, many companies need to innovate and work in a hybrid manner. How and with what tools can business and technical profiles collaborate productively together? lorian Douetteau, Dataiku's CEO, answers these questions.
An Architecture for Agile Machine Learning in Real-Time Applications
An Architecture for Agile Machine Learning in Real-Time ApplicationsJohann Schleier-Smith Presented at KDD, August 11, 2015.
Abstract of the paper:
Machine learning techniques have proved effective in recommender systems and other applications, yet teams working to deploy them lack many of the advantages that those in more established software disciplines today take for granted. The well-known Agile methodology advances projects in a chain of rapid development cycles, with subsequent steps often informed by production experiments. Support for such workflow in machine learning applications remains primitive.
The platform developed at if(we) embodies a specific machine learning approach and a rigorous data architecture constraint, so allowing teams to work in rapid iterative cycles. We require models to consume data from a time-ordered event history, and we focus on facilitating creative feature engineering. We make it practical for data scientists to use the same model code in development and in production deployment, and make it practical for them to collaborate on complex models.
We deliver real-time recommendations at scale, returning top results from among 10,000,000 candidates with sub-second response times and incorporating new updates in just a few seconds. Using the approach and architecture described here, our team can routinely go from ideas for new models to production-validated results within two weeks.
Data kitchen 7 agile steps - big data fest 9-18-2015
Data kitchen 7 agile steps - big data fest 9-18-2015DataKitchen This document discusses applying agile principles and practices to data and analytics teams to address the complexity they face. It outlines seven steps to doing agile data work: 1) adding tests, 2) modularizing and containerizing work, 3) using branching and merging, 4) employing multiple environments, 5) giving analysts tools to experiment, 6) using simple storage, and 7) supporting small team, feature branch, and data governance workflows. The goal is to enable rapid experimentation and integration of new data sources through these agile practices adapted for analytics teams and their unique needs.
RightScale Webinar: Enterprise-Grade Cloud Cost Planning and Management
RightScale Webinar: Enterprise-Grade Cloud Cost Planning and ManagementRightScale This document summarizes a presentation about enterprise-grade cloud cost planning and management using RightScale. It discusses the need for a "mind shift" to understand cloud costs, which can involve over 12,000 pricing points and frequent changes. It then outlines RightScale's approach to cost management in three phases: investigation and planning, deploying and monitoring, and optimization. Key tips include choosing regions wisely, tagging all resources, understanding high availability and disaster recovery costs, monitoring costs across accounts, identifying idle resources, and using purchase options to reduce costs.
Embedding Data & Analytics With Looker
Embedding Data & Analytics With LookerLooker Delivering data and analytics to your customers should be straightforward. The Looker Data Platform allows for easy access to data through a robust API and embeddable charts, tables and dashboards.
Learn how Looker can help you:
- Embed charts, tables and dashboards into applications
- Use the Looker API to deliver data to applications, including Slack
- Build a customer portal to deliver more value to your customers
- Design the above with version control through Git, along with clustering and multi-server setup as needed
Real Time Business Platform by Ivan Novick from Pivotal
Real Time Business Platform by Ivan Novick from PivotalVMware Tanzu Korea This document discusses Pivotal's real time business platform for maximizing the value of data investments. It recommends identifying business problems with high ROI potential, then focusing data solutions on high-speed ingestion, consolidation, real-time queries, and analytics to drive real-time insights. The platform combines Gemfire for fast transactions with Greenplum for analytics. Use cases discussed include predictive maintenance, fraud detection, and recommendation engines. The platform provides a complete solution from data capture and analytics to application integration.
The paradox of big data - dataiku / oxalide APEROTECH
The paradox of big data - dataiku / oxalide APEROTECHDataiku The document discusses the paradoxes of big data. It notes that while data volumes are large, useful data can still be refined to fit in memory. It also discusses how the ecosystem around big data technologies like Hadoop and Spark has grown rapidly with many startups receiving funding. Practical uses of big data involve using tools like Dataiku's Data Science Studio to clean, model, and extract insights from multiple data sources to optimize processes like deliveries or improve search relevance. The document provides steps to get started with big data including learning Python/R and practicing on platforms like Kaggle to enter the field.
Big Data Day LA 2016/ Big Data Track - Rapid Analytics @ Netflix LA (Updated ...
Big Data Day LA 2016/ Big Data Track - Rapid Analytics @ Netflix LA (Updated ...Data Con LA This talk explores how Netflix equips its engineers with the freedom to find and introduce the right software for the job - even if it isn't used anywhere else in-house. Examples include how Netflix has enabled analysts to fluidly switch between MPP RDBMS and an auto-scaling Presto cluster, how Spark + NoSQL stores are used when deploying data sets to internal web apps, and how data scientists are enabled to work in the ML framework of their choosing and deploy models as a service.
Zero Downtime App Deployment using Hadoop
Zero Downtime App Deployment using HadoopDataWorks Summit/Hadoop Summit Hadoop can enable zero downtime app deployments by using microservices, continuous delivery, and real-time analytics. The presenters describe how Expedia saves $5M annually through zero downtime deployments. Their architecture uses microservices, continuous integration, deployment monitoring with Storm/Kafka/HDFS, and analytics in Solr/Hive to enable canary testing, fast feedback, and automated problem resolution. A live demo shows log processing, analytics, and using results to ensure smooth, high-quality deployments.
Spark and the Enterprise by Tony Baer
Spark and the Enterprise by Tony BaerSpark Summit This document discusses the growing popularity and capabilities of the Apache Spark platform for large-scale data analytics. It notes that Spark has over 40 committers, 1000 contributors, and is being used in 179 projects. The document highlights key features of Spark like its ease of use, performance (10-100x faster than MapReduce), flexibility, and ability to handle both batch and real-time processing. It also provides examples of how Spark can help businesses by enabling more complex analytics like predictive modeling, enabling smarter predictions, and allowing insights from real-time data. The document emphasizes that Spark advocates should focus on illustrating tangible business benefits over technical features when discussing Spark with higher-level business stakeholders.
Eric Andersen Keynote
Eric Andersen KeynoteData Con LA Google provides a suite of data and analytics services and tools for businesses to manage large datasets and gain insights from data. These include BigQuery for analytics, Cloud Dataproc for batch processing, Cloud Dataflow for streaming data, Cloud Pub/Sub for event delivery, and Cloud Bigtable for large-scale NoSQL databases. Google has been developing these services based on its own experiences managing big data over 15 years.
Big data prototyping in AWS cloud
Big data prototyping in AWS cloudSamuel Yee This document discusses using AWS cloud for rapid prototyping of big data minimum viable products (MVPs). Key benefits of cloud computing include no upfront costs, ability to scale quickly, and pay only for resources used. Typical big data use cases involve retrospective analysis, real-time processing, and machine learning. The document demonstrates building a basic Hadoop cluster on AWS in 15 minutes for word count analysis. It recommends measuring MVP outcomes and considering ongoing cloud use based on needs for 24/7 access, internal resources, and security requirements.
Smart App@Pivotal by Dat Tran
Smart App@Pivotal by Dat TranVMware Tanzu Korea This document discusses smart apps and how Pivotal uses data science to build them. It describes three key components of smart apps: data, a smart system that uses data science to understand user behavior, and a user interface. It then provides examples of smart apps Pivotal has developed for logistics and automotive customers, describing how machine learning models were used to predict delivery locations and road conditions. The document emphasizes an API-first approach and using cloud platforms like Cloud Foundry to operationalize models and deliver insights through predictive APIs.
Viewers also liked (20)
Predicting Retail KPIs using Magento & Machine Learning
Predicting Retail KPIs using Magento & Machine LearningRud Boruah The document discusses using machine learning to predict customer behavior for a Magento e-commerce site. It outlines collecting data from Magento like product views and quotes to build models that can predict checkout intent and prevent cart abandonment. A demo is then presented on how a scalable infrastructure with a Magento extension, slave database, and NoSQL database can be used to train models on historical data and predict customer behavior in real-time.
A Spark Framework For < $100, < 1 Hour, Accurate Personalized DNA Analy...
A Spark Framework For < $100, < 1 Hour, Accurate Personalized DNA Analy...Spark Summit This document presents a Spark framework for personalized DNA analysis at large scale for under $100 and less than 1 hour. The framework segments input DNA data and runs it through three stages on a Spark cluster: 1) mapping and static load balancing, 2) sorting and dynamic load balancing, and 3) Picard deduplication and GATK variant calling. It achieves high CPU utilization, scales linearly from 1 to 20 nodes, analyzes 400GB of data in under an hour on a 35-node cluster for under $100, and has a 99.1% concordance with serial GATK. Future work involves accelerating it using FPGAs.
A Graph-Based Method For Cross-Entity Threat Detection
A Graph-Based Method For Cross-Entity Threat DetectionJen Aman This document proposes a graph-based method for cross-entity threat detection. It models entity relationships as a multigraph and detects anomalies by identifying unexpected new connections between entities over time. It introduces two algorithms: a naive detector that identifies edges only in the detection graph, and a 2nd-order detector that identifies edges between entity clusters. An experiment on a real dataset found around 700 1st-order and 200 2nd-order anomalies in under 5 minutes, demonstrating the method's ability to efficiently detect threats across unrelated accounts.
Solving The N+1 Problem In Personalized Genomics
Solving The N+1 Problem In Personalized GenomicsSpark Summit This document discusses 9 key problems in personalized medicine and genomic analysis: 1) variant calling, 2) variant annotation, 3) variant filtering, 4) integrating clinical oncology data, 5) integrating RNA and other omics data, 6) managing metadata, 7) cohort identification, 8) dynamic recalculation of statistics, and 9) handling incomplete data from different technologies. It uses the example of Madelyn Shumaker, an 8-year old diagnosed with DIPG brain cancer, to illustrate how genomic analysis and filtering was used to identify potential treatment targets. Spark is highlighted as a tool that can help address several of these problems through capabilities like variant calling, annotation, filtering and dynamic querying of large datasets.
Spark Summit EU talk by Erwin Datema and Roeland van Ham
Spark Summit EU talk by Erwin Datema and Roeland van HamSpark Summit The document discusses KeyGene's use of Apache Spark for high-throughput genomics data analysis. KeyGene is a crop innovation company that analyzes genomic data from thousands of plants to improve crop traits like yield and quality. They previously used conventional HPC clusters for genomics pipelines but found Spark enabled more interactive analysis. KeyGene developed a "Sparkified" genomics pipeline using tools like BWA, GATK and their own Guacamole variant caller. This allowed interactive variant selection and GWAS using Spark SQL queries, demonstrating Spark is well-suited for interactive plant genomics analysis.
From MapReduce to Apache Spark
From MapReduce to Apache SparkJen Aman The document discusses the evolution of the Apache Spark and Hadoop ecosystems, highlighting how new use cases in genomics, physics, and healthcare have emerged. It also introduces Livy, a new open source REST service for Apache Spark that allows submitting Spark jobs from web and mobile apps without needing a Spark client, and provides multi-tenancy and fault tolerance to support multiple users reliably.
Massive Simulations In Spark: Distributed Monte Carlo For Global Health Forec...
Massive Simulations In Spark: Distributed Monte Carlo For Global Health Forec...Jen Aman Kyle Foreman presented on using Spark for large-scale global health simulations. The talk discussed (1) the motivation for simulations to model disease burden forecasts and alternative scenarios, (2) SimBuilder for constructing modular simulation workflows as directed acyclic graphs, and (3) benchmarks showing Spark backends can efficiently distribute simulations across a cluster. Future work aims to optimize Spark DataFrame joins and take better advantage of Numpy's vectorization for panel data simulations.
Yggdrasil: Faster Decision Trees Using Column Partitioning In Spark
Yggdrasil: Faster Decision Trees Using Column Partitioning In SparkJen Aman This document introduces Yggdrasil, a new approach for training decision trees in Spark that partitions data by column instead of by row. Column partitioning significantly reduces communication costs for deep trees with many features. Evaluation on real-world datasets with millions of rows and thousands of features shows Yggdrasil achieves up to 24x speedup over the existing row-partitioning approach in Spark MLlib. The authors propose merging Yggdrasil into Spark MLlib to provide both row and column partitioning options for optimal performance on different problem sizes and depths.
Finding Graph Isomorphisms In GraphX And GraphFrames
Finding Graph Isomorphisms In GraphX And GraphFramesSpark Summit Spark Summit 2016 talk by Michael Malak (Oracle)
Time-Evolving Graph Processing On Commodity Clusters
Time-Evolving Graph Processing On Commodity ClustersJen Aman Tegra is a system for efficiently processing time-evolving graphs on commodity clusters. It uses a distributed graph snapshot index to represent and retrieve multiple snapshots of evolving graphs. It introduces a timelapse abstraction to perform temporal analytics on windows of snapshots, avoiding redundant computation. Tegra supports both bulk and incremental graph computations using this representation, allowing results to be reused when graphs are updated. An evaluation on real-world graphs shows Tegra can store more snapshots in memory and reduce computation time compared to baseline approaches.
MmmooOgle: From Big Data to Decisions for Dairy Cows
MmmooOgle: From Big Data to Decisions for Dairy CowsSpark Summit Spark Summit EU talk by Miel Hostens
Accelerating Spark Genome Sequencing in Cloud—A Data Driven Approach, Case St...
Accelerating Spark Genome Sequencing in Cloud—A Data Driven Approach, Case St...Spark Summit Spark data processing is shifting from on-premises to cloud service to take advantage of its horizontal resource scalability, better data accessibility and easy manageability. However, fully utilizing the computational power, fast storage and networking offered by cloud service can be challenging without deep understanding of workload characterizations and proper software optimization expertise. In this presentation, we will use a Spark based programing framework – Genome Analysis Toolkit version 4 (GATK4, under development), as an example to present a process of configuring and optimizing a proficient Spark cluster on Google Cloud to speed up genome data processing. We will first introduce an in-house developed data profiling framework named PAT, and discuss how to use PAT to quickly establish the best combination of VM configurations and Spark configurations to fully utilize cloud hardware resources and Spark computational parallelism. In addition, we use PAT and other data profiling tools to identify and fix software hotspots in application. We will show a case study in which we identify a thread scalability issue of Java Instanceof operator. The fix in Scala language hugely improves performance of GATK4 and other Spark based workloads.
Huohua: A Distributed Time Series Analysis Framework For Spark
Huohua: A Distributed Time Series Analysis Framework For SparkJen Aman This document summarizes Wenbo Zhao's presentation on Huohua, a distributed time series analysis framework for Spark. Huohua addresses issues with existing time series solutions by introducing the TimeSeriesRDD data structure that preserves temporal ordering across operations like grouping and temporal join. The group function groups time series locally without shuffling to maintain order, and temporal join uses partitioning to perform localized stream joins across partitions.
Finding Needles in Genomic Haystacks with “Wide” Random Forest: Spark Summit ...
Finding Needles in Genomic Haystacks with “Wide” Random Forest: Spark Summit ...Spark Summit Recent advances in genome sequencing technologies and bioinformatics have enabled whole-genomes to be studied at population-level rather then for small number of individuals. This provides new power to whole genome association studies (WGAS
), which now seek to identify the multi-gene causes of common complex diseases like diabetes or cancer.
As WGAS involve studying thousands of genomes, they pose both technological and methodological challenges. The volume of data is significant, for example the dataset from 1000 Genomes project with genomes of 2504 individuals includes nearly 85M genomic variants with raw data size of 0.8 TB. The number of features is enormous and greatly exceeds the number of samples, which makes it challenging to apply traditional statistical approaches.
Random forest is one of the methods that was found to be useful in this context, both because of its potential for parallelization and its robustness. Although there is a number of big data implementations available (including Spark ML) they are tuned for typical dataset with large number of samples and relatively small number of variables, and either fail or are inefficient in the GWAS context especially, that a costly data preprocessing is usually required.
To address these problems, we have developed the RandomForestHD – a Spark based implementation optimized for highly dimensional data sets. We have successfully RandomForestHD applied it to datasets beyond the reach of other tools and for smaller datasets found its performance superior. We are currently applying RandomForestHD, released as part of the VariantSpark toolkit, to a number of WGAS studies.
In the presentation we will introduce the domain of WGAS and related challenges, present RandomForestHD with its design principles and implementation details with regards to Spark, compare its performance with other tools, and finally showcase the results of a few WGAS applications.
Validation of solid oral dosage form, tablet 1
Validation of solid oral dosage form, tablet 1Jamia Hamdard The document discusses process validation for oral solid dosage forms like tablets. It defines process validation and the different types - prospective, retrospective, and concurrent validation. It provides details on validation protocols, including general information, objectives, process flow charts, critical parameters, and acceptance criteria. Key processing steps for tablets are also summarized, like mixing, wet granulation, milling and factors that influence them like material properties, equipment used, and processing parameters. The goal of process validation is to ensure consistent production of tablets meeting quality standards.
GPU Computing With Apache Spark And Python
GPU Computing With Apache Spark And PythonJen Aman GPU Computing With Apache Spark And Python
- Python is a popular language for data science and analytics due to its large ecosystem of libraries and ease of use, but it is slow for number crunching tasks. GPU computing is a way to accelerate Python workloads.
- This presentation demonstrates using GPUs with Apache Spark and Python through libraries like Accelerate, which provides drop-in GPU-accelerated functions, and Numba, which can compile Python functions to run on GPUs.
- As an example, the task of image registration, which involves computationally expensive 2D FFTs, is accelerated using these GPU libraries within a PySpark job, achieving a 2-4x speedup over CPU-only versions
Recent Developments In SparkR For Advanced Analytics
Recent Developments In SparkR For Advanced AnalyticsDatabricks Since its introduction in Spark 1.4, SparkR has received contributions from both the Spark community and the R community. In this talk, we will summarize recent community efforts on extending SparkR for scalable advanced analytics. We start with the computation of summary statistics on distributed datasets, including single-pass approximate algorithms. Then we demonstrate MLlib machine learning algorithms that have been ported to SparkR and compare them with existing solutions on R, e.g., generalized linear models, classification and clustering algorithms. We also show how to integrate existing R packages with SparkR to accelerate existing R workflows.
Spark And Cassandra: 2 Fast, 2 Furious
Spark And Cassandra: 2 Fast, 2 FuriousJen Aman The document discusses the Datastax Spark Cassandra Connector. It provides an overview of how the connector allows Spark to interact with Cassandra data, including performing full table scans, pushing down filters and projections to Cassandra, distributed joins using Cassandra's partitioning, and writing data back to Cassandra in a distributed way. It also highlights some recent features of the connector like support for Cassandra 3.0, materialized views, and performance improvements from the Java Wildcard Cassandra Tester project.
Re-Architecting Spark For Performance Understandability
Re-Architecting Spark For Performance UnderstandabilityJen Aman The document discusses a new architecture called "monotasks" that is designed to make it easier to reason about the performance of Apache Spark jobs. The key aspects are:
1) Each task in a Spark job is dedicated to using a single resource (e.g. network, CPU, disk).
2) Dedicated schedulers control contention between tasks for resources.
3) The timing of individual "monotasks" can be used to model an ideal performance and understand bottlenecks.
Spark on Mesos
Spark on MesosJen Aman This document summarizes a talk on Spark on Mesos given by Dean Wampler from Lightbend and Timothy Chen from Mirantis. It discusses why Spark on Mesos is useful by allowing one cluster system to run multiple tools. It then covers recent updates like a new integration test suite, coarse-grained scheduler improvements, and Mesos framework authentication. Finally, it outlines future plans such as GPU support on Mesos and making "production" use of Spark on Mesos easier.
Ad
Similar to Utilizing Human Data Validation For KPI Analysis And Machine Learning (20)
Measuring and improving customer experience with journey analytics
Measuring and improving customer experience with journey analyticsAngie Hsu Customer Experience Measurement Framework
Customer Journey Analytics Methodologies
Tips for Deliver Solutions
Share and Tell Stanford 2016
Share and Tell Stanford 2016Stanford University agile, business model, corporate innovation, customer development, lean, lean startup, lean launchpad, stanford, steve blank, video, engr 245
A b-testing-101
A b-testing-101Madhumita Mantri A/B testing involves showing two variants of a digital experience to different user groups and measuring which performs better according to key metrics. It is used to test hypotheses about how to improve user engagement and conversion rates. The process involves researching problems, developing hypotheses, creating alternatives, validating alternatives through testing, and then implementing the best performing version. Some best practices include focusing tests, using statistical analysis, controlling for external factors, and collecting user feedback. Common areas to conduct A/B tests include websites, apps, search, ecommerce, and APIs. Popular A/B testing tools vary in features and pricing.
Usalytics.pitch.v3.1
Usalytics.pitch.v3.1Alexey Vorobiev This document discusses a personalization platform that uses A/B testing and big data to personalize the visitor experience on websites. It claims this can increase conversions by up to 40%. The platform segments visitors, predicts their behavior, and acts by showing tailored content to improve outcomes. It is a full-featured solution for marketers to optimize websites across devices. The company aims to partner with resellers, agencies, and publishers to build its business globally.
Emetrics - Oct 19 2011 - New York - X channel optimisation
Emetrics - Oct 19 2011 - New York - X channel optimisationCraig Sullivan The document discusses Belron's testing culture and multi-variate testing program. Belron has a small in-house optimization team that runs dozens of tests across its sites annually. Their testing aims to increase key metrics like revenue and customer satisfaction while lowering costs. Belron gathers ideas from analytics, customer feedback, and usability research. They employ A/B testing as well as multi-variate or "MVT" testing with dozens of variables. Through continual testing, Belron has achieved over $40 million in ROI from optimizations costing around $800,000 over two years.
Anatomy of Relevance - From Data to Action: Presented by Saïd Radhouani, Yell...
Anatomy of Relevance - From Data to Action: Presented by Saïd Radhouani, Yell...Lucidworks This document discusses relevance and how Yellow Pages leverages data to improve relevance. It outlines the importance of relevance for businesses and consumers in local search. The author then describes Yellow Pages and his role in content, search, and relevance. Next, it details the building blocks of relevance including user data, content, knowledge, search, and presentation. It emphasizes measuring relevance through key performance indicators and using data to identify gaps and drive continuous improvement through action. The goal is to use an evidence-based approach to optimize the user experience and satisfaction.
Anatomy of Search Relevance: From Data To Action
Anatomy of Search Relevance: From Data To ActionSaïd Radhouani Relevance denotes how well a search result satisfies the user information need. In addition to the search engine components (i.e., indexer and query parser), there are many other components that impact relevance. e.g., user understanding , data optimization, domain knowledge, etc. Improving relevance remains the main and most challenging goal of each search engine. Indeed, relevance can be subjective, therefore hard to measure and to improve. In this talk, Saïd will demystify the concept of relevance by defining its main components. For each component, he will present the technology enablers, the data, and processes that are required in order to measure and improve relevance. In this talk, attendees will learn how to provide a relevant user experience and track it over time.
Pricing Pitfalls...and How to Counter Them
Pricing Pitfalls...and How to Counter ThemGus Prestera This webinar discusses pricing pitfalls and building a pricing system. It is presented by Gus Prestera, a mentor, consultant, and entrepreneur. The webinar will cover countering pricing pitfalls, building a pricing system, and providing a peek under the hood of pricing approaches. It includes slides on assessing various factors like cultural, leadership, timeline, and technical considerations when pricing projects. The webinar also discusses different pricing models like hourly rates, day rates, project rates, and deliverable rates.
Trends in testing 2015 
Trends in testing 2015 Brijesh Deb The document discusses emerging trends in software testing for 2015, including testing the Internet of Things, SMAC technologies, DevOps practices, service virtualization, domain-focused testing, test centers of excellence, and crowd testing. Some of the impacts on testing include a focus on user experience, interoperability, automation, mobility, data analytics, continuous integration and delivery, API/web service testing, and output-based pricing models for crowd testing. Factors influencing these trends are the growing adoption of agile development practices and distributed teams, as well as barriers to fully implementing agile approaches.
A/B Testing Best Practices - Do's and Don'ts
A/B Testing Best Practices - Do's and Don'tsRamkumar Ravichandran A/B Testing best practices from strategic vision to operational considerations to communication and finally expectations management. We need to adhere to fundamental project management, technology, statistical, experimental design, UX Design, Customer Relationship, business and data principles to ensure that the insights and hence the decision is as trustworthy as possible.
Model Factory at ING Bank
Model Factory at ING BankDataWorks Summit At ING Bank, machine learning models are a key factor in making relevant engagements with our customers, empowering them to stay a step ahead in life and in business. In our efforts to make the model building process more rapid, compliant, validated and accessible to roles other than data scientists (such as data analysts or customer journey experts), we have structured it for an easy creation of propensity models.
In this talk, I will present this structure, focusing on pipelining data science models in Apache Spark. In particular, I will show how we use Apache Sqoop & Ranger to comply with GDPR, build a data science workflow on top of python and Jupyter, extend the SparkML libraries on PySpark to create custom standardizers and cross-validators, and show an in-house developed monitoring tool built on top of Elasticsearch for model evaluation.
Finally, I will describe the type of engagement analysts and customer journey experts have with the result set of the models created, and how we refine our dashboards (in IBM Cognos) accordingly.
Speaker: Dor Kedem, Lead Data Scientist
ING Bank
SiriusDecisions Explores the Need for Demand Orchestration
SiriusDecisions Explores the Need for Demand OrchestrationIntegrate The Crisis Of Coordination At The Top Of The Funnel Is Distracting From Lower-Funnel Efforts Needed To Scale Pipeline.
This SlideShare features content from Kerry Cunningham of Sirius Decisions and Lena Waters of Lookout discussing today’s B2B marketing climate – specifically the growing need for Demand Orchestration as marketing teams become responsible for revenue, not just leads.
Content was originally featured in a live webinar on 4.6.2017. The on-demand webinar can be viewed here: https://discover.integrate.com/webinar_the_move_to_demand_orchestration
Why is Data Science still not a mainstream in corporations - Sasa Radovanovic
Why is Data Science still not a mainstream in corporations - Sasa RadovanovicInstitute of Contemporary Sciences The main task of this talk is to see how Data Science can influence big companies to generate new revenue and more profit.
Subjects that will be addressed in this talk are:
• Understanding a value it brings to corporations on long-term (direct revenue generation not only cost reduction);
• Data Science is important part of digital transformation. Are corporations ready?
• Management dedication on investment;
• Lack of Data Science managers acting as a link between Data Scientists and Business managers. Provide motivation/interesting tasks for Data Scientists while validating investments in business environment;
• Lack of skillful Data scientists;
• Compensation of Data Scientists among other Employees (obviously a different scales needs to be applied);
• Examples of Applied Data Science as revenue generators in Telenor Serbia;
An introduction to the it recruitment - Aditya Tiwari
An introduction to the it recruitment - Aditya TiwariAaditya Tiwari Presenting an Introduction to the IT Recruitment. An overview about how recruitment done specifically in Staffing Firms/ Recruitment agencies/ IT Firms / Payroll Companies etc.
The ProPricer Proven Performance
The ProPricer Proven PerformanceDenni Griffith Denni Griffith from Executive Business Services presented on the coming of the information age in government contracting. EBS develops the ProPricer cost proposal application to help companies generate proposals more efficiently. ProPricer allows different teams to work simultaneously on proposals, ensures accurate representation of costs, and makes updates like rate changes simple. It also facilitates data sharing between contractors and agencies to improve transparency and relationships. ProPricer fits companies of all sizes and industries and provides benefits for estimators, pricing teams, auditors, and more by streamlining the entire proposal process.
Roundtable: Best Practices - Quality Assurance & Analytics
Roundtable: Best Practices - Quality Assurance & AnalyticsSheri Greenhaus This document discusses best practices for quality assurance and analytics in contact centers. It provides an overview of a roundtable discussion on the topic featuring representatives from Genesys, VPI, and inContact. Some of the key points discussed include:
- Traditional random quality monitoring of calls is time-intensive and provides an inadequate sample size. Analytics can now analyze a much larger portion of calls.
- Top strategies for improving call quality according to a survey include tying quality scores to training, using analytics to find higher value calls, automating QA workflows, and speeding up feedback to agents.
- VPI provides workforce optimization solutions including call recording, speech and data analytics, quality assurance, and performance management to over 1
The benefits of outsourcing the best online survey company
The benefits of outsourcing the best online survey companyVinay Londhe In today's data-driven world, online surveys have become an invaluable tool for businesses, researchers, and organizations seeking insights from their target audience. However, conducting effective online surveys can be a complex and time-consuming endeavour. The top online survey providers step in at this point and give their experience to speed up the procedure. We will explore the multiple advantages of outsourcing your survey needs to a reputable online survey company. Discover how this partnership can enhance the quality, efficiency, and success of your data collection efforts.
What are the benefits of outsourcing an online survey company?
Partnering with an online survey company offers numerous advantages for businesses and researchers. Here are some of them:
Benefit #1 - Access to advanced tools and technology:
The best online survey companies have access to cutting-edge survey software and analytics tools. By outsourcing, you can leverage these resources without the need for a significant upfront investment. This ensures that your best online surveys are technologically up-to-date and deliver accurate, real-time insights.
Benefit #2 - Targeted participant recruitment:
An online survey company can help you reach your ideal audience, whether it's customers, employees, or specific demographics. They have access to extensive participant panels and can employ advanced targeting techniques to ensure the right people complete your surveys.
Benefit #3 - Quality control and data accuracy:
Ensuring the accuracy and quality of survey data is paramount. Online survey companies employ rigorous quality control measures to minimize errors and bias. They can also handle data cleaning and validation, giving you confidence in the reliability of your data.
Benefit #4 - Time and cost efficiency:
Outsourcing to an online survey company saves you precious time and resources. Their streamlined processes and expertise reduce the time it takes to launch the best online surveys and analyze results. This efficiency translates into cost savings and quicker access to insights.
Benefit #5 - Customization and flexibility:
Online survey companies can tailor the best online surveys to your specific needs. Whether you require branded surveys, multilingual support, or complex question logic, they can accommodate your customization requests, ensuring that your surveys align with your objectives.
Visit https://www.samplejunction.com/article/the-benefits-of-outsourcing-the-best-online-survey-company for more information.
User Research: The Superpower Behind Experimentation Programs | VWO Webinars
User Research: The Superpower Behind Experimentation Programs | VWO WebinarsVWO User research is often a side-lined activity within the experimentation space, but it’s crucial for keeping your testing velocity up and your win rates high.
Many experimentation and optimization teams fail to make this connection due to a lack of time, resources, knowledge or the siloed structure of their organization.
In this talk, Chris will take you through some practical examples of how user research can drive the quantity of ideas, their quality, and originality, which in turn leads to a much more successful overall experimentation program.
Lean startup, customer development, and the business model canvas
Lean startup, customer development, and the business model canvasgistinitiative The document discusses key concepts in lean startup methodology, including building business models focused on customer development rather than business plans, developing minimum viable products to test hypotheses, and using an iterative build-measure-learn process. It provides examples of how startups should focus on building products that solve customer pains and create gains rather than features, and emphasizes conducting customer interviews to gather evidence and test hypotheses about the business model.
LMS process a ReLook (Chapter-2)
LMS process a ReLook (Chapter-2)Romi Bhattacharjee Lead management involves generating leads, processing them through various stages, qualifying them as opportunities, and ultimately converting them into sales. The document outlines the typical lead lifecycle and identifies gaps in the current process such as lack of data analysis and duplicate leads. It proposes improvements like linking the website to an interactive voice response system, promptly contacting hot leads, and upselling or cross-selling additional products. The goal is to advance the lead generation unit to higher levels through enhanced lead processing, relationship building, opportunity development, and analytical feedback.
Why is Data Science still not a mainstream in corporations - Sasa Radovanovic
Why is Data Science still not a mainstream in corporations - Sasa RadovanovicInstitute of Contemporary Sciences
Ad
More from Jen Aman (20)
Deep Learning and Streaming in Apache Spark 2.x with Matei Zaharia
Deep Learning and Streaming in Apache Spark 2.x with Matei ZahariaJen Aman 2017 continues to be an exciting year for Apache Spark. I will talk about new updates in two major areas in the Spark community this year: stream processing with Structured Streaming, and deep learning with high-level libraries such as Deep Learning Pipelines and TensorFlowOnSpark. In both areas, the community is making powerful new functionality available in the same high-level APIs used in the rest of the Spark ecosystem (e.g., DataFrames and ML Pipelines), and improving both the scalability and ease of use of stream processing and machine learning.
Snorkel: Dark Data and Machine Learning with Christopher Ré
Snorkel: Dark Data and Machine Learning with Christopher RéJen Aman Building applications that can read and analyze a wide variety of data may change the way we do science and make business decisions. However, building such applications is challenging: real world data is expressed in natural language, images, or other “dark” data formats which are fraught with imprecision and ambiguity and so are difficult for machines to understand. This talk will describe Snorkel, whose goal is to make routine Dark Data and other prediction tasks dramatically easier. At its core, Snorkel focuses on a key bottleneck in the development of machine learning systems: the lack of large training datasets. In Snorkel, a user implicitly creates large training sets by writing simple programs that label data, instead of performing manual feature engineering or tedious hand-labeling of individual data items. We’ll provide a set of tutorials that will allow folks to write Snorkel applications that use Spark.
Snorkel is open source on github and available from Snorkel.Stanford.edu.
Deep Learning on Apache® Spark™: Workflows and Best Practices
Deep Learning on Apache® Spark™: Workflows and Best PracticesJen Aman This document summarizes a presentation about deep learning workflows and best practices on Apache Spark. It discusses how deep learning fits within broader data pipelines for tasks like training and transformation. It also outlines recurring patterns for integrating Spark and deep learning frameworks, including using Spark for data parallelism and embedding deep learning transforms. The presentation provides tips for developers on topics like using GPUs with PySpark and monitoring deep learning jobs. It concludes by discussing challenges in the areas of distributed deep learning and Spark integration.
Deep Learning on Apache® Spark™ : Workflows and Best Practices
Deep Learning on Apache® Spark™ : Workflows and Best PracticesJen Aman The combination of Deep Learning with Apache Spark has the potential for tremendous impact in many sectors of the industry. This webinar, based on the experience gained in assisting customers with the Databricks Virtual Analytics Platform, will present some best practices for building deep learning pipelines with Spark.
Rather than comparing deep learning systems or specific optimizations, this webinar will focus on issues that are common to deep learning frameworks when running on a Spark cluster, including:
* optimizing cluster setup;
* configuring the cluster;
* ingesting data; and
* monitoring long-running jobs.
We will demonstrate the techniques we cover using Google’s popular TensorFlow library. More specifically, we will cover typical issues users encounter when integrating deep learning libraries with Spark clusters.
Clusters can be configured to avoid task conflicts on GPUs and to allow using multiple GPUs per worker. Setting up pipelines for efficient data ingest improves job throughput, and monitoring facilitates both the work of configuration and the stability of deep learning jobs.
RISELab:Enabling Intelligent Real-Time Decisions
RISELab:Enabling Intelligent Real-Time DecisionsJen Aman Spark Summit East Keynote by Ion Stoica
A long-standing grand challenge in computing is to enable machines to act autonomously and intelligently: to rapidly and repeatedly take appropriate actions based on information in the world around them. To address this challenge, at UC Berkeley we are starting a new five year effort that focuses on the development of data-intensive systems that provide Real-Time Intelligence with Secure Execution (RISE). Following in the footsteps of AMPLab, RISELab is an interdisciplinary effort bringing together researchers across AI, robotics, security, and data systems. In this talk I’ll present our research vision and then discuss some of the applications that will be enabled by RISE technologies.
Spatial Analysis On Histological Images Using Spark
Spatial Analysis On Histological Images Using SparkJen Aman This document describes using Spark for spatial analysis of histological images to characterize the tumor microenvironment. The goal is to provide actionable data on the location and density of immune cells and blood vessels. Over 100,000 objects are annotated in each whole slide image. Spark is used to efficiently calculate over 5 trillion pairwise distances between objects within a neighborhood window. This enables profiling of co-localization and spatial clustering of objects. Initial results show the runtime scales linearly with the number of objects. Future work includes integrating clinical and genomic data to characterize variation between tumor types and patients.
Deploying Accelerators At Datacenter Scale Using Spark
Deploying Accelerators At Datacenter Scale Using SparkJen Aman Spark Summit 2016 talk by Di Wu (UCLA & Falcon Computing Solutions, Inc.) and Muhuan Huang (UCLA & Falcon Computing Solutions, Inc.)
Re-Architecting Spark For Performance Understandability
Re-Architecting Spark For Performance UnderstandabilityJen Aman The document describes a new architecture called "monotasks" for Apache Spark that aims to make reasoning about Spark job performance easier. The monotasks architecture decomposes Spark tasks so that each task uses only one resource (e.g. CPU, disk, network). This avoids issues where Spark tasks bottleneck on different resources over time or experience resource contention. With monotasks, dedicated schedulers control resource contention and monotask timing data can be used to model ideal performance. Results show monotasks match Spark's performance and provide clearer insight into bottlenecks.
Low Latency Execution For Apache Spark
Low Latency Execution For Apache SparkJen Aman This document describes Drizzle, a low latency execution engine for Apache Spark. It addresses the high overheads of Spark's centralized scheduling model by decoupling execution from scheduling through batch scheduling and pre-scheduling of shuffles. Microbenchmarks show Drizzle achieves milliseconds latency for iterative workloads compared to hundreds of milliseconds for Spark. End-to-end experiments show Drizzle improves latency for streaming and machine learning workloads like logistic regression. The authors are working on automatic batch tuning and an open source release of Drizzle.
Efficient State Management With Spark 2.0 And Scale-Out Databases
Efficient State Management With Spark 2.0 And Scale-Out DatabasesJen Aman This document discusses efficient state management with Spark 2.0 and scale-out databases. It introduces SnappyData, an open source project that provides a unified in-memory database for streams, transactions, and OLAP queries to enable real-time operational analytics. SnappyData extends Spark by localizing state management and processing to avoid shuffles, supports approximate query processing for interactive queries, and provides a unified cluster architecture for OLTP, OLAP and streaming workloads.
Livy: A REST Web Service For Apache Spark
Livy: A REST Web Service For Apache SparkJen Aman Livy is an open source REST service for interacting with and managing Spark contexts and jobs. It allows clients to submit Spark jobs via REST, monitor their status, and retrieve results. Livy manages long-running Spark contexts in a cluster and supports running multiple independent contexts simultaneously from different clients. It provides client APIs in Java, Scala, and soon Python to interface with the Livy REST endpoints for submitting, monitoring, and retrieving results of Spark jobs.
Building Custom Machine Learning Algorithms With Apache SystemML
Building Custom Machine Learning Algorithms With Apache SystemMLJen Aman This document discusses Apache SystemML, which is a machine learning framework for building custom machine learning algorithms on Apache Spark. It originated from research projects at IBM involving machine learning on Hadoop. SystemML aims to allow data scientists to build ML solutions using languages like R and Python, while executing algorithms on big data platforms like Spark. It provides a high-level language for expressing algorithms and performs automatic parallelization and optimization. The document demonstrates SystemML through a matrix factorization example for a targeted advertising problem. It shows how to wrangle data, build a custom algorithm, and get results. In conclusion, it recommends that readers try out SystemML through its website.
Elasticsearch And Apache Lucene For Apache Spark And MLlib
Elasticsearch And Apache Lucene For Apache Spark And MLlibJen Aman This document summarizes a presentation about using Elasticsearch and Lucene for text processing and machine learning pipelines in Apache Spark. Some key points:
- Elasticsearch provides text analysis capabilities through Lucene and can be used to clean, tokenize, and vectorize text for machine learning tasks.
- Elasticsearch integrates natively with Spark through Java/Scala APIs and allows indexing and querying data from Spark.
- A typical machine learning pipeline for text classification in Spark involves tokenization, feature extraction (e.g. hashing), and a classifier like logistic regression.
- The presentation proposes preparing text analysis specifications in Elasticsearch once and reusing them across multiple Spark pipelines to simplify the workflows and avoid data movement between systems
Spark at Bloomberg: Dynamically Composable Analytics 
Spark at Bloomberg: Dynamically Composable Analytics Jen Aman The Bloomberg Spark Server provides a platform for dynamic composable analytics on Spark. It includes a Function Transform Registry (FTR) of reusable analytics functions. It also includes a Managed DataFrame Registry (MDFR) that allows request processors to lookup and compose analytics on named DataFrames. The request processors handle analytic requests by looking up functions from the FTR and composing them on MDFs from the MDFR. The Spark Server addresses challenges of standalone Spark apps like data redundancy and cross-asset analytics. It also handles real-time ingestion and memory management to support online analytics on Spark.
Spark Uber Development Kit
Spark Uber Development KitJen Aman This document summarizes a presentation given at Spark Summit 2016 about tools and techniques used at Uber for Spark development and jobs. It introduces SCBuilder for encapsulating cluster environments, Kafka dispersal for publishing RDD results to Kafka, and SparkPlug for kickstarting job development with templates. It also discusses SparkChamber for distributed log debugging and future work including analytics, machine learning, and resource usage auditing.
EclairJS = Node.Js + Apache Spark
EclairJS = Node.Js + Apache SparkJen Aman EclairJS allows developers to use JavaScript and Node.js to interact with Apache Spark for large-scale data processing and analytics. It provides a Spark API for Node.js so that compute-intensive workloads can be handed off to Spark running in the backend. EclairJS also enables the use of JavaScript with Jupyter notebooks, so data engineers and web developers can experiment with Spark from within the browser using familiar JavaScript syntax.
Spark: Interactive To Production
Spark: Interactive To ProductionJen Aman This document summarizes a presentation given at Spark Summit 2016 about using Spark for real-time data processing and analytics at Uber and Marketplace Data. Some key points:
- Uber generates large amounts of data across its 70+ countries and 450+ cities that is used for real-time processing, analytics, and forecasting.
- Marketplace Data uses Spark for real-time data processing, analytics, and forecasting of Uber's data, which involves challenges like complex event processing, geo aggregation, and querying large and streaming datasets.
- Jupyter notebooks are used to empower users and data scientists to work with Spark in a flexible way, though challenges remain around reliability, freshness, and isolating queries.
High-Performance Python On Spark
High-Performance Python On SparkJen Aman This document contains the slides from a presentation given by Wes McKinney on high performance Python on Apache Spark. The presentation discusses why Python is an important language, defines what is meant by "high performance Python", and explores techniques for building fast Python software such as embracing limitations of the Python interpreter and using native data structures and compiled extensions where possible. Specific examples are provided around control flow, reading CSV files, and the importance of efficient in-memory data structures.
Scalable Deep Learning Platform On Spark In Baidu
Scalable Deep Learning Platform On Spark In BaiduJen Aman This document summarizes Baidu's work on scaling deep learning using Spark. It discusses:
1) Baidu's goals of implementing Spark ML abstractions to train deep learning models with minimal code changes and leveraging Paddle's distributed training capabilities.
2) The system architecture which uses Spark and YARN for resource management and Paddle for distributed training.
3) Experiments showing Paddle can efficiently train large models like image recognition on ImageNet using many machines and GPUs, as well as sparse models.
Scaling Machine Learning To Billions Of Parameters
Scaling Machine Learning To Billions Of ParametersJen Aman This document summarizes scaling machine learning to billions of parameters using Spark and a parameter server architecture. It describes the requirements for supporting both batch and sequential optimization at web scale. It then outlines the Spark + Parameter server approach, leveraging Spark for distributed processing and the parameter server for synchronizing model updates. Examples of distributed L-BFGS and Word2Vec training are presented to illustrate batch and sequential optimization respectively.
Recently uploaded (20)
Simple_AI_Explanation_English somplr.pptx
Simple_AI_Explanation_English somplr.pptxssuser2aa19f Ai artificial intelligence ai with python course first upload
Principles of information security Chapter 5.ppt
Principles of information security Chapter 5.pptEstherBaguma Principles of information security Chapter 5.ppt
How iCode cybertech Helped Me Recover My Lost Funds
How iCode cybertech Helped Me Recover My Lost Fundsireneschmid345 I was devastated when I realized that I had fallen victim to an online fraud, losing a significant amount of money in the process. After countless hours of searching for a solution, I came across iCode cybertech. From the moment I reached out to their team, I felt a sense of hope that I can recommend iCode Cybertech enough for anyone who has faced similar challenges. Their commitment to helping clients and their exceptional service truly set them apart. Thank you, iCode cybertech, for turning my situation around!
[email protected]
How to join illuminati Agent in uganda call+256776963507/0741506136
How to join illuminati Agent in uganda call+256776963507/0741506136illuminati Agent uganda call+256776963507/0741506136 How to join illuminati Agent in uganda call+256776963507/0741506136
md-presentHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHation.pptx
md-presentHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHation.pptxfatimalazaar2004 BBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBB
computer organization and assembly language.docx
computer organization and assembly language.docxalisoftwareengineer1 computer organization and assembly language : its about types of programming language along with variable and array description..https://www.nfciet.edu.pk/
Day 1 - Lab 1 Reconnaissance Scanning with NMAP, Vulnerability Assessment wit...
Day 1 - Lab 1 Reconnaissance Scanning with NMAP, Vulnerability Assessment wit...Abodahab IHOY78T6R5E45TRYTUYIU
FPET_Implementation_2_MA to 360 Engage Direct.pptx
FPET_Implementation_2_MA to 360 Engage Direct.pptxssuser4ef83d Engage Direct 360 marketing optimization sas entreprise miner
Data Science Courses in India iim skills
Data Science Courses in India iim skillsdharnathakur29 This comprehensive Data Science course is designed to equip learners with the essential skills and knowledge required to analyze, interpret, and visualize complex data. Covering both theoretical concepts and practical applications, the course introduces tools and techniques used in the data science field, such as Python programming, data wrangling, statistical analysis, machine learning, and data visualization.
AI Competitor Analysis: How to Monitor and Outperform Your Competitors
AI Competitor Analysis: How to Monitor and Outperform Your CompetitorsContify AI competitor analysis helps businesses watch and understand what their competitors are doing. Using smart competitor intelligence tools, you can track their moves, learn from their strategies, and find ways to do better. Stay smart, act fast, and grow your business with the power of AI insights.
For more information please visit here https://www.contify.com/
How to join illuminati Agent in uganda call+256776963507/0741506136
How to join illuminati Agent in uganda call+256776963507/0741506136illuminati Agent uganda call+256776963507/0741506136
Utilizing Human Data Validation For KPI Analysis And Machine Learning
- 1. Utilizing Human Data Validation for KPI Analysis and Machine Learning Dan Morris Radius Intelligence
- 2. Overview and Key Takeaways • Data science problems @ Radius • Human validation: costs and benefits • Sampling and experimentation for multiple consumers • Positive feedback cycles in production
- 3. Radius - B2B Predictive Marketing
- 4. Radius - Data Engineering MLlib
- 5. Why Human Validation? • Business firmographic data is a difficult data problem • Our sources face the same challenges that we do • Each source must be considered a “proposal” • Independent Human Validation is (the closest thing to) ground truth
- 6. Degrees of Human Validation • Prompted Validation • Research Validation • Research Curation Value Cost PV RV RC
- 7. Prompted Validation Example Assignment: Verify the Phone Number and Address of a Business
- 8. Research Validation Example Assignment: Determine if a Business Belongs to a Chain / Franchise Business Name: Bob’s Donuts Address: 123 Main St. Website: www.bobsdonuts.biz Industry: Limited Service Restaurants Is Chain: (Y / N / U) Chain Type: (Local / Regional / National)
- 9. Research Curation Example Assignment: Where is the Headquarters of this Company Located? Company Name: Bob’s Donuts Inc. Website: www.bobsdonuts.biz Has many locations: (Y / N / U) HQ Location: ??? Source of information: ???
- 10. Human Validation: Benefits • Ground Truth • Supervised ML • Internal Metrics • Competitive Analysis • Our customers are humans, too!
- 11. Human Validation: Costs • Money • Time • Us and Them
- 12. Cost: Money • Validated data costs more than aggregated data > Validation + Data Science Pure Validation
- 13. Cost: Time • Automated experimental framework • Shift bottleneck to validation teams • Parallelized validation improves turnaround time • Be mindful of differences in teams / validators • Decay / Obsolescence of validations
- 14. Cost: Us and Them Clearly communicate expectations and interpretations
- 15. Uses for Validated Data • KPI Analysis • ML Training Sets • Spot Hypothesis Validation Challenge: minimize number of validations while meeting all downstream needs
- 16. Multiple-Consumer Sampling Standalone vs. Chain Experiment 1 value per 1 location == Easy Sampling!
- 17. Multiple-Consumer Sampling Phone Accuracy Experiment (0, 1, 2, 3, …) values to 1 location == Difficult Sampling.
- 19. Positive Feedback Production Cycle
- 20. THANKS! email me: [email protected] stalk me: @djsensei connect me: linkedin.com/in/danielepmorris work with me: radius.com/jobs