Scribd
Upload
47 views

Sales Analytics

The document discusses using data analytics and machine learning for sales and marketing use cases at a pharmaceutical company. It outlines requirements for tools like Docker, Airbyte, PostgreSQL, pgAdmin, Tableau, and Power BI. It then provides steps for setting up data pipelines to extract, transform, and load data and visualize it for insights using Python libraries like NumPy, Pandas, Matplotlib, and Seaborn. Specific use cases discussed include targeted content distribution, future sales prediction, price optimization, understanding product fit, detailed lead scoring, tracking sales productivity, churn prevention, inventory management, and targeting specific patient populations.

Uploaded by

caraocultamusic
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
47 views

Sales Analytics

The document discusses using data analytics and machine learning for sales and marketing use cases at a pharmaceutical company. It outlines requirements for tools like Docker, Airbyte, PostgreSQL, pgAdmin, Tableau, and Power BI. It then provides steps for setting up data pipelines to extract, transform, and load data and visualize it for insights using Python libraries like NumPy, Pandas, Matplotlib, and Seaborn. Specific use cases discussed include targeted content distribution, future sales prediction, price optimization, understanding product fit, detailed lead scoring, tracking sales productivity, churn prevention, inventory management, and targeting specific patient populations.

Uploaded by

caraocultamusic
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 6

Sales Analytics

The project is about sales and marketing of a Pharmaceutical Company where we have
to analyze a dataset and find insights with the help of some use cases and try to make
an end to end pipeline.

Requirements :
Docker Desktop: 4.14.0 (91374)

Airbyte Version: 0.40.18

PostgreSql: 15.1

pgAdmin Desktop: 6.15

Tableau Desktop: 2022.2

Getting Started
Setting Up Docker
Download Docker Desktop for Mac or Windows. Docker Compose will be
automatically installed.

Setting Up Airbyte
Run this in Directory/Command Prompt

cd airbyte

docker-compose up

Once you see an Airbyte banner, the UI is ready to go at http://localhost:8000 You will
be asked for a username and password. By default, that's username airbyte and
password password. Once you deploy airbyte to your servers, be sure to change these in
your .env file.
Setting Up Postgres Container in Docker

Prerequisites
To use the Postgres destination, we'll need:

● A Postgres server version 9.5 or above

Run this in directory/Command Prompt

docker run --name airbyte -e POSTGRES_PASSWORD=password -p 5432:5432 -d


postgres

Install PostgreSql
Download and install PostgreSql from here.

Install pgAdmin
Download and install pgAdmin from here.

Install Tableau
Download Tableau Desktop for Mac or Windows.

Install PowerBI
Download Power BI for Mac or Windows.

After Installation (Deployment)

Airbyte Setup
After setting up airbyte and postgres, on airbyte setup source as file that will be
your dataset, and setup destination as postgres i.e what we setup earlier postgres
container in docker. For doubts while setting up postgres you can follow instruction as
given here, follow from Step 2

Connect source and destination, sync them.

pgAdmin Setup
Create a database in preferred server,

That would be under servers < servername < Database, refer here in case of doubt.

Create table in that database corresponding to your dataset,


That would be under servers < servername < Database < Database Name < Schemas <
public < tables refer here in case of doubt.

import dataset in that table, refer here in case of doubt.

Sync Tableau and Postgres


import dataset that we set up earlier in pgAdmin.

Refer these steps to import the dataset in Tableau.

A Step by Step Guide for Data Visualization using Power Bi


● Getting Started with Power BI click here.
● Connect to data click here to view step by step guide.
● For Visualization click here to view step by step guide.
● For Formatting, Calculating Fields and Parameter click here to view step
by step guide
● Create your own dashboard with the following steps.

Python scripting for Data Visualization

I did data visualization, data cleaning, data analysis with the help of python and
created insights from the data. Python provides various libraries that come with
different features for visualizing data. All these libraries come with different features
and can support various types of graphs.The libraries which I have used are as follows.
● Numpy
● Pandas
● Matplotlib
● Seaborn

Numpy
NumPy is a general-purpose array-processing package. It provides a high-
performance multidimensional array object, and tools for working with these arrays. It is
the fundamental package for scientific computing with Python. For reference click here.

To install using pip:

pip install Numpy

Pandas
Pandas is an open source library in Python. It provides ready to use high-
performance data structures and data analysis tools. Pandas module runs on top of
NumPy and it is popularly used for data science and data analytics.To see user guide
click here.

To install using pip:

pip install pandas

Matplotlib
Matplotlib is an easy-to-use, low-level data visualization library that is built on
NumPy arrays. It consists of various plots like scatter plot, line plot, histogram, etc.
Matplotlib provides a lot of flexibility. Click here to find documentation.

Install using pip:

pip install matplotlib

Seaborn
Seaborn is a library that uses Matplotlib underneath to plot graphs. It will be used
to visualize random distributions.To see user guide click here.

To install using pip:

pip install seaborn

Use cases which is used :

Targeted content distribution :


Which types of content work better for certain leads can be answered with
predictive analytics. Once you know not only which type of content resonates with a
specific audience, but also what channel to best reach them on, you can customize
content creation and distribution. When leads receive higher-quality communication
from an organization, this increases the probability of sales conversion.

Future Sales Prediction :


The prospect of future sales gives the companies that work with sales enormous
relief. The model of prediction requires specific data. This includes the number of
customers acquired, the number of clients lost, the average sales volume as well as the
saison trends. In addition, the expectations of sales - changing conditions that can
affect sales dramatically - should be predetermined. Future sales can enable these
issues to be avoided and better decisions to be taken.
Price Optimization :
One of the most arduous tasks of all time is to set the proper pricing. For both
sellers and buyers, the price should be satisfactory. It is rather difficult to achieve this
equilibrium. Many pricing schemes can be utilized for this assignment. Data science
has taken the lead in price definition and considerably enhanced this procedure.

Understanding Product Fit :


Equipped with historical purchase, behavior and leads data, businesses can
better understand exactly what customers’ needs and wants are. This may translate to
developing future products to further meet those needs or improving upon existing
products that aren’t meeting their sales targets.

Detailed Lead Scoring :


Lead scoring means ranking leads based on where they are in the funnel. It
allows marketing and sales divisions to collaborate in a more meaningful way, since
every lead is different. With prescriptive analytics, every lead will be scored based on its
readiness to purchase. This helps to inform the next step in marketing or selling to a
prospective lead based on predictions about their future buying habits.

Tracking Sales Productivity :


Managers utilize sales analytics to track their sales funnel and performance.
They also use this data to determine each sales rep’s success KPIs and discover gaps.
These can also help the sales team develop a basic standard methodology.

Churn Prevention :
Customer churn refers to the percentage of customers who have stopped buying
and using the product for a specific period. Machine learning algorithms are used to
identify trends and features in the behavior, communication, and ordering of customers
who have ceased shopping through customer relationship management information.Try
to rely on and take into consideration your best customers to prevent or minimize their
customer churn, provide feedback and communicate promptly, offer bonuses, inquire
about the thoughts of your consumers

Inventory management :
The stock referred to the stocking of products and afterward used in crisis times.
For enterprises to optimize resources and increase sales, inventory management is
therefore vital.Powerful machine learning algorithms evaluate and supply data in depth
and identify buying patterns and correlations. The analyst then evaluates this data and
provides a strategy for revenue increase, timely delivery, and inventory management.
Target specific patient populations more effectively :
With information from genomic sequencing, medical sensor data (a device that
can, for instance, be worn and track physical changes in an individual during treatment),
and electronic medical records more readily available than ever before, pharmaceutical
companies are able to dig into the root causes of specific pathologies and realizing that
one size truly does not fit all. Within any disease or condition, different patients will
respond differently to treatments – for a host of reasons. Combining the data from
these different sources can allow drug companies to spot trends and patterns that will
allow them to come up with more targeted medications for patients that share common
features.

You might also like