Ruben Diaz, Vision Banco + Rafael Coss, H2O ai + Luis Armenta, IBM - AI journey at Vision Banco
Download as PPTX, PDF3 likes569 views
The document outlines the AI journey at Vision Banco Paraguay, detailing their evolution in machine learning from traditional models to advanced techniques using H2O.ai and Driverless AI. The bank, a significant player in the Paraguayan financial sector, has implemented various use cases such as credit scoring and fraud detection, emphasizing the importance of model interpretability and automation in data science. Future aspirations include expanding AI applications in areas like money laundering prevention and natural language processing.
Ruben Diaz, Vision Banco + Rafael Coss, H2O ai + Luis Armenta, IBM - AI journey at Vision Banco
- 1. AI Journey at Vision Banco Paraguay Rubén Díaz Data Scientist Vision Banco @rubuntu #H2OWORLD Rafael Coss Community Maker H2O.ai @racoss
- 2. #H2OWORLD AI journey at Vision Banco Paraguay Ruben Diaz @rubuntu Data Scientist, Vision Banco Rafael Coss @racoss Community Maker, H2O.ai
- 3. #H2OWORLD Agenda Introduction • Vision Banco • Journey so far Automatic Machine Learning 101 Journey to Deployment Lessons Learned Looking to the future Tweet @h2oai @visionbanco @rubuntu @racoss #h2oworld
- 4. #H2OWORLD Vision Banco Who are we? What are our ML use Cases? What’s our env?
- 5. #H2OWORLD Paraguay Population: 6.811 million (2017) Area: 406,752 km2 / 157,048 sq mi (4.1% of USA area ) Official languages: Spanish & Guarani ROI: 2nd best (22%) in Latin America Point of interest: Asuncion, Itaipu Dam , Jesuit Missions, Chaco, Pantanal Exports: • 1st global Electric power exporter • 1st global Organic sugar exporter • 2nd global Stevia exporter • 3rd global Yerba Mate exporter (Ilex paraguaiensis) • 4th global Soybean exporter • 5th global Chia exporter • 6th global Meat exporter
- 6. #H2OWORLD • Paraguayan bank member of "Global Alliance for Banking on Values" • Top 10 in the country • The largest number of agencies (95), non- banking correspondents (2,492) and largest employer of the financial system (1,758 employees) in Paraguay • Inclusive: ⅓ of population have accounts • 800,000+ customers • Microfinance & SMBs Tus metas nos inspiran / Your goals inspire us
- 7. #H2OWORLD Vision Banco ML Journey • 1st Generation Credit Scoring Models, using Logistic Regression Models developed with IBM SPSS, deployed as a stored procedure on IBM Db2 for i (AS/400) database • 2nd Generation, state of the art algos: Random Forest, GBM, etc. Developed with SPSS, KNIME and R, exported to the standard PMML format and implemented as REST web services using openscoring.io • 3rd Generation. H2O.ai open source. More algos: XGBoost, Deep Learning, Ensembles, etc. The open source H2O platform surprised us with its speed to train models. The migration to H2O involved changing the deployment of models in PMML format to H2O’s POJOS & MOJOS • 4th Generation. Auto ML with Driverless AI on IBM Power System AC922 server accelerated with NVIDIA® Tesla® V100 GPUs Each Step improved the Accuracy and Speed of Model Building & Deploying
- 8. #H2OWORLD Vision Banco Use Cases Risk Management • Credit Scoring • Default Prediction • Fraud Detection Business • Propensity to Purchase (Predictive Lead Scoring) • Customer Churn Prediction • Customer segmentation • Recommendation Engines
- 9. #H2OWORLD Automatic Machine Learning: Driverless AI !!! Joined the Driverless AI Beta circa November 2017 What is Driverless AI? • Automates a large part of the Data Science process POC • Env: Cloud VM with GPU • Scenario: Entered the AnalyticsVidhya.com contest "Data Science Hackathon: Churn Prediction" • Result: Surprisingly, I got 8th place! https://www.linkedin.com/pulse/how-get-eighth-place-data-science-competition-using-driverless-diaz/
- 10. #H2OWORLD Driverless AI Features Targe t Data Quality and Transformation Modeling Table Model Building Model Data Integration + Driverless AI: Automates Data Science and ML Workflows
- 11. Confidential11 Confidential11 Automatic Machine Learning 101 SQL Local Amazon S3 HDFS X Y Automatic Model Optimization Automatic Scoring Pipeline Machine learning Interpretability Deploy Low-latency Scoring to Production Modelling Dataset Model Recipes • i.i.d. data • Time-series • More on the way Advanced Feature Engineering Algorithm Model Tuning+ + Survival of the Fittest Understand the data shape, outliers, missing values, etc. Powered by GPU Acceleration 1 Drag and Drop Data 2 Automatic Visualization Use best practice model recipes and the power of high performance computing to iterate across thousands of possible models including advanced feature engineering and parameter tuning 3 Automatic Model Optimization Deploy ultra-low latency Python or Java Automatic Scoring Pipelines that include feature transformations and models 4 Automatic Scoring Pipelines Bring data in from cloud, big data and desktop systems Google BigQuery Azure Blog Storage Snowflake Model Documentation
- 12. #H2OWORLD Solution Architecture (Hardware) The IBM Power System AC922 server ● Faster I/O - up to 5.6x more I/O bandwidth than x86 servers ● The best GPUs - 2-6 NVIDIA® Tesla® V100 GPUs with NVLink ● Extraordinary CPUs - 2x POWER9 CPUs, designed for AI ● Simplest AI architecture - Share RAM across CPUs & GPUs ● Enterprise-ready - PowerAI DL frameworks with IBM support ● Next Gen PCIe - PCIe Gen4 2x faster vs PCIe Gen3 in x86 ● Built for the world's biggest AI challenges The best server for enterprise AI Powered by GPU Acceleration
- 13. Confidential13 Infrastructure Modeling Deployment AI Solutions Data Sources Train Test Production Data Model Mgt Batch Scoring Real-time Scoring BI Solutions dev/ops On-Prem Cloud Machine Learning Workflow AI Architecture Data Prep
- 14. Confidential14 AI Solutions Model MgtData Prep Infrastructure Modeling Deployment Data Sources Train Test Production Data Batch Scoring Real-time Scoring BI Solutions dev/ops On-Prem Cloud Vision Banco AI Architecture IBM Notes
- 15. Confidential15 AI App Scoring Flow (Model Deployment) AI Solutions Real-time Scoring MOJO Scoring Pipeline FeaturesScore Results See: https://github.com/rubuntu/h2o_scorer App Captures Features Score Take Action 1 2 3 4 5
- 16. Confidential16 Machine Learning Interpretability Why Should I Trust Your Model?
- 17. Confidential17 Machine Learning Interpretability (cont.)
- 18. #H2OWORLD Lesson Learned • The automation of the process of Data Science reduces time and "costs less money" • It is very important that machine learning models are interpretable to explain the decisions made by machine learning algorithms to business people and even to the company's customers
- 19. #H2OWORLD Looking to the future Use Cases • Money laundering prevention • Time series forecasting • NLP • Chatbots • Voice / Sound recognition • Image recognition • Video detection
- 20. AI for good. Democratize AI for Everyone. H2O is the open leader in AI.
- 21. #H2OWORLD