This slide present Data Analytics concept. Topics are level of analytics, CRISP-DM, data science use cases e.g., customer segmentation, churn prediction, product recommendation, demand forecasting
Practical Data Science Use-cases in Retail & eCommerce
1. Practical Data Science
Use-cases in Retail & eCommerce
By Eakasit Pacharawongsakda, Ph.D.
Co-founder of Data Cube
eakasit@datacubeth.ai
Data Analytics Sharing @Home
26 April 2020 1:30-4:30 pm
8. practice without theory is blind”
“Theory without practice is empty,
— Kant
“ถ้ารู้ทฤษฎีแต่ขาดการปฏิบัติก็ทำงานไม่ได้
ถ้ารู้แต่ปฏิบัติไม่รู้ทฤษฎีก็พัฒนาต่อไม่ได้”
facebook.com/datacube.th
9. http://dataminingtrend.com http://facebook.com/datacube.th
Data is a new oil
• “เมื่อข้อมูลมีค่าดั่งน้ำมัน”
9Source: https://www.raconteur.net/technology/drilling-for-new-oil-of-big-data
Customer
Data
Transaction
Data
Website
Data
Survey
Data
Social
Network
Data Employee
Data
Reports
Actionable
Insight
Predictive
Model
Recommended
Products
facebook.com/datacube.th
17. http://www.datacubeth.ai http://facebook.com/datacube.th
BI & Data Mining
17
Business
Intelligence
Data
Mining
Time
Analytical
Approach
Past Future
Explanatory
Exploratory
source:Data Science and Big Data Analytics: Discovering, analyzing, visualizing and presenting data
BI questions
• What happened last
quarter?
• How many unit sold?
• Where is the problem? In
which situations
Data Mining questions
• What if … ?
• What will happen next?
• Why is this happen?
facebook.com/datacube.th
21. http://dataminingtrend.com http://facebook.com/datacube.th
CRISP-DM
21
STAGE DESCRIPTION
Business Understanding Define the project.
Data Understanding Examine the data; identify problems in the data.
Data Preparation Fix problems in the data; create derived variables.
Modeling Build predictive or descriptive models.
Evaluation Assess models; report on the expected effects of models.
Deployment Plan for use of models.
source: Applied Predictive Analytics: Principle and Techniques for the Professional Data Analyst
23. http://facebook.com/datacube.thhttp://www.datacubeth.ai
Data Science Use Cases
23
• Churn Prevention
• Identify customers likely to leave, take
preventative action.
• Customer Lifetime Value
• Distinguish between customers based on
business value.
• Customer Segmentation
• Create meaningful customer groups for
more relevant interactions.
• Demand Forecasting
• Know what volumes to expect to improve
planning.
• Fraud Detection
• Identify fraudulent activity quickly, and
end it.
• Next Best Action
• The right action at the right time for the
right customer.
• Price Optimization
• Set prices that balance demand, profit,
and risk.
• Product Propensity
• Predict what your customers will buy,
before even they know it.
facebook.com/datacube.th
24. http://facebook.com/datacube.thhttp://www.datacubeth.ai
Data Science Use Cases
24
• Text Mining
• Extract insight from unstructured content.
• Next Best Action
• The right action at the right time for the
right customer.
• Price Optimization
• Set prices that balance demand, profit,
and risk.
• Product Propensity
• Predict what your customers will buy,
before even they know it.
• Quality Assurance
• Resolve quality issues before they
become a problem.
• Predictive Maintenance
• Predict equipment failure, plan cost-
effective maintenance.
• Risk Management
• Understand risk to manage it.
• Up- and Cross-Selling
• Convince customers to buy more.
facebook.com/datacube.th