Advanced Customer Analytics for Managers

Description

Course description:

This course will make a jump-start introduction to applications of ML and AI to create a customer-centric analysis. The course will cover practical steps of Segmentations, Churn analysis, Live Time Value models, Optimization of campaigns, Recommendation Systems, Dynamic Pricing, and Customer Network analysis combined with theoretical methodologies, which we are using on a daily basis. The course will contain six workshops where students will be working with data from Telco, Banking, and/or Retail.

The course will be based on the MS Power BI tool, however, interested students will be able to benefit from R/Python-based notebooks. The course is co-developed based on the experience and efforts of Liubomyr Bregman, Richard Bobek, and Adam Blascik.

Course structure:

1. How and why to make Customer Segmentation?
2. Churn Analysis and early detection
3. Life Time Value Forecast. Use cases and popular approaches.
4. Campaign Optimization and next best actions
5. Recommendation systems for online and offline. Review of best practices
6. Social Network Analysis of Customers, how to use, and how to benefit.
7. Dynamic Pricing.

Learning outcomes:

At the end of this course, the student should be able to:

• Identify the correct use cases for her/his business model
• Build and test churn, segmentation and CLV use cases
• Understand the concepts which may be used for business optimization
• Create a Views for Deep dive and benefit analytics with zero code
• Replicate use cases discussed during the course

Language: English

Price: UAH 24 000

Date: July 24 – August 2

______________

Course outline:

• Segmentation (3 hours)

Basics of unsupervised learning. Intuitive knowledge of k-means. Other algorithm will be covered during the course

• Churn Analysis (4 hours)

Understanding of key classification algorithms like OLS and Logistic Regression.

• CLV forecast (3 hours)

Understanding key concerns of Markov Chain and Decision trees.

• Campaign optimizations and recommenders (2 hours)

Linear optimization basics, Matrix Factorization for Collaborative filtering

• Network of customers (4 hours)

No pre requirements, basic understanding of what is graphs

• Dynamic Pricing (2 hours)

Understanding the basics of demand and classification algorithms. Design and run of experiments

• Final exam (2 hours)

• Mini-Project submission (2 hours)