Course Description
This course looks at what is churn and how to identify which customers are likely to leave you. It also looks at the factors that are likely related to churn and how to reduce churn.
The course concludes with the benefits of churn and goes into detail on how to predict which customers are likely to churn using a Logistic Regression Model. We end the course with methods on evaluating churn models for their business effectiveness and accuracy.
What am I going to get from this course?
At the end of this course students will understand:
- What is Churn
- The overall benefits of Churn
- Which factors are likely related to Churn
- How to reduce Churn
- How to prevent Customers from leaving them
- How to calculate Churn
- How to evaluate Churn Models for their business effectiveness and accuracy
Prerequisites and Target Audience
What will students need to know or do before starting this course?
There are no pre-requisites for this course. This course is an introductory course. It is for students of all levels.
Who should take this course? Who should not?
This course is an introductory course. It is for all students who work in the Retail, Financial or Telecommunications Industries who are interested in learning more on how to prevent customers from leaving their business.
This course is also for data analysts, data scientists and data modellers who would like to understand what is churn, what are the benefits of churn for the business, how to run Logistic Regression Models and how to evaluate the business effectiveness and accuracy of churn models.
Curriculum
Module 1: Introduction
07:33
Lecture 1
Course Overview & Objectives
01:28
Highlights what the learner will be able to do by the end of the course.
Lecture 2
What is Churn?
02:13
Defines Churn. Provides a definition for the Churn Rate and discusses what is an acceptable Churn Rate. Concludes with how changes in the Churn Rate impact business.
Lecture 3
Why do Customers Churn?
03:52
Highlights some of the reasons why customers churn. For example, Bad On-boarding, Bad Customer Service, Lack of Ongoing Customer Success, Natural Causes, etc
Module 2: Customer Churn
10:29
Lecture 4
Types of Customer Churn
02:07
Describes what is Negative Churn, Voluntary Churn and Involuntary Churn
Lecture 5
How to Calculate Customer Churn
02:21
Gives the method for calculating customer churn rate.
Lecture 6
Why Calculate Customer Churn?
02:14
Gives examples why business needs to calculate Customer Churn
Lecture 7
Tactics for Reducing
03:47
Churn Gives examples how business can reduce Customer Churn.
Module 3: Customer Lifetime Value
06:50
Lecture 8
Customer Lifetime Value
04:33
Defines Customer Lifetime Value and describes the impact of Customer Lifetime Value on business. Provides the relationship between the Customer Lifetime Value and the Churn Rate.
Lecture 9
How to Calculate Customer Lifetime Value
02:17
Gives the formula for calculating Customer Lifetime Value
Lecture 10
What is Latency?
05:45
Defines what is Latency and gives an example on how to calculate Latency.
Lecture 11
What are the Benefits of Calculating Latency?
11:07
Describes the benefits of calculating Latency with a focus on how the Latency metric can help the business to make key decisions as to whom to market the Retention Campaign to.
Module 5: Churn Analysis/Regression Techniques
20:05
Lecture 12
Churn Analysis in the Telecommunication Industry
01:39
Background information on Churn in the Telecommunication Industry
Lecture 13
Churn Analysis using the Logistic Regression Technique
03:48
An introduction to the Logistic Regression Technique.
Lecture 14
Preparing the Data for the Logistic Regression
08:36
A brief description on Data Preparation. This includes how to do data cleaning, data relevancy check, de-duplication, outlier check and handle missing values.
Lecture 15
Data Partitioning for the Logistic Regression Technique
01:51
This lecture describes how to divide the data set into a training data set and a test data set.
Lecture 16
Data Balancing of the Logistic Regression Technique
04:11
A brief description on how to balance your data output classes for optimal results
Module 6: How to Build & Interpret the Logistic Regression Model
06:04
Lecture 17
Identifying the Significant Variables for Churn
03:12
Uses the Wald Test coefficient summary output table to explain how the significant values and the signs of the coefficients are important metrics to determine whether a variable contributes to the outcome of interest and whether the model is likely reliable and optimum.
Lecture 18
Interpreting the Odds Ratio
02:52
Describes how to interpret the odds ratio and relate it to the business for decision making.
Module 7: Evaluating the Churn Model Accuracy
11:38
Lecture 19
Evaluating the Churn Model - Accuracy
06:16
This lecture looks at how we use the Confusion Matrix, the sensitivity and specificity of the model to measure model accuracy .
Lecture 20
Evaluating the Churn Model - Receiver Operating Curve (ROC)
01:48
The Receiver Operating Curve helps you to determine the threshold value for classification and helps you to better understand the trade-offs for the sensitivity and specificity measures.
Lecture 21
Evaluating the Churn Model - Area Under the Curve (AUC)
00:54
This lecture describes the Area Under the Curve method for assessing the accuracy of the Churn Model. The closer the value is to 1, the more accurate is the model.
Lecture 22
Evaluating the Churn Model - Lift Charts
02:40
This lecture helps us to see how we can use Lift Charts to determine effectiveness of the predictive model against a random model.
