Getting Started
Let's look at the content, prerequisites, outcomes, and chapter overview of the course.
We'll cover the following
Welcome to the course
In this course, you’ll learn about applied machine learning in marketing analytics. You’ll learn everything you need to use modern data science techniques in marketing analytics, including data exploration, data preprocessing, feature engineering, model building, and evaluation. There are plenty of coding exercises and challenges to help you understand each topic in detail. In addition, you’ll be able to code along in the live coding notebooks.
Prerequisites
This course is designed to be accessible to everyone, but knowledge of the following is useful:
- Basic knowledge of Python programming
- Knowledge of Pandas DataFrame and data wrangling techniques
- Basic math and statistic concepts
- Basic marketing analytics
- Curiosity and interest in learning
Learning outcomes
In this course, you’ll learn about:
- Data exploration techniques and flexible problem solving strategies
- Linear regression models
- How to apply linear regression to predict future revenue
- A segmentation model
- How to segment your customers into different groups
- A logistic regression model
- How to predict customer churn
About each chapter
Chapter 1: Introduction gives an overview of the course.
Chapter 2: Data Manipulation offers a refresher on data preparation, cleaning, and exploration techniques using Pandas, Matplotlib, and Seaborn libraries.
Chapter 3: Predicting Customer Revenue starts the marketing analytics journey with a gentle introduction to linear regression and predictive modeling of continuous numbers.
Chapter 4: Customer Segmentation covers an unsupervised machine learning algorithm to group a customer base into buckets based on their demographic, psychographic, behavioral, and geographical attributes. This is one of the most important skills for a data analytics professional in marketing to have.
Chapter 5: Predicting Customer Churn introduces logistic regression as a classification method and shows how to predict customer churn. Logistic regression aims to squash the output of linear regression into binary classes.
Chapter 6: Predicting Customer Lifetime Value (CLV) introduces different approaches to customer lifetime value prediction. This chapter also covers how to predict CLV by combining linear regression and Recency, Frequency, and Monetary (RFM) modeling.