About this course

This course will give the participants an overview of the key techniques used in direct marketing for analysing customer data. The focus is on getting to the business results with just enough technical and mathematical detail to allow us to get there reliably. Our approach is what is usually called scientific marketing: it is about getting the facts and letting the data speak as opposed to relying on our ‘gut’ instincts.

Prerequisites: The students are expected to be comfortable using R at a basic level and to understand elementary marketing concepts. The R concepts we will need for the practical exercises of the course include: loading data using read.csv() or similar; data manipulation and aggregation, including data.frame, merge, and the *apply family of functions; and model formula (y ~ x1 * x2 + offset(t)) and model fitting using at least lm or glm.

Target audience: business owners (marketing managers, product managers, customer base managers) and their teams; customer insights professionals.

Tools: students should have access to a recent version of R and access to install packages.

Course contents

The course follows the customer life cycle from acquiring new customers, managing the existing customers for profitability, retaining good customers, and finally understanding which customers are leaving us and why.

We will be working with real (if anonymous) data from a variety of industries including telecommunications, insurance, media, and high tech.

Part 1: Inflow - acquiring new customers

Our focus is direct marketing so we will not look at advertising campaigns but instead focus on understanding marketing campaigns (e.g. direct mail). This is the foundation for almost everything else in the course.

We look at measuring and improving campaign effectiveness. including:

1. The importance of test and control groups. Universal control group.
2. Techniques: Lift curves, AUC
3. Return on investment. Optimizing marketing spend.

Part 2: Base Management: managing existing customers

Considering the cost of acquiring new customers for many businesses there are probably few assets more valuable than their existing customer base, though few think of it in this way. Topics include:

1. Cross-selling and up-selling: Offering the right product or service to the customer at the right time.
   1. Techniques: RFM models. Multinomial regression.
   2. Value of lifetime purchases.
2. Customer segmentation: Understanding the types of customers that you have.
   1. Classification models using first simple decision trees, and then
   2. random forests and other, newer techniques.

Part 3: Retention: Keeping your good customers

Understanding which customers are likely to leave and what you can do about it is key to profitability in many industries, especially where there are repeat purchases or subscriptions. We look at propensity to churn models, including

1. Logistic regression: glm (package stats) and newer techniques (especially gbm as a general tool)
2. Tuning models (caret) and introduction to ensemble models.
3. Using cloud computing for model creation and optimization.
   1. Distributed data manipulation: using dplyr.spark, sparklyr, and other tools.
   2. Distributed computing: the foreach framework in the context of caret and packages such as doAzureParallel.
   3. Comparison with other cloud-based Advanced Analytics tools: including event processing, bot frameworks, deep learning, and artificial intelligence, to understand when to consider using them.

Part 4: Outflow: Understanding who are leaving and why

Customers will leave you – that is a fact of life. What is important is to understand who are leaving and why. Is it low value customers who are leaving or is it your best customers? Are they leaving to competitors or because they no longer need your products and services? Topics include:

1. Customer lifetime value models: Combining value of purchases with propensity to churn and the cost of servicing and retaining the customer.
2. Analysing survey data. (Generally useful, but we will do a brief introduction here in the context of exit surveys.)
3. Price elasticity analysis: discovering the optimal price for your products and services.
4. Deploying models: options for deploying the model in the business, including in-database analytics and deployment.

Course format

Instructor-led training consisting of five half-day sessions with in-class exercises as well as homework. We have successfully given the course in both physical and online (virtual) classrooms.

About the instructor

Allan Engelhardt has 26 years of experience in customer insights and customer relationship management after originally graduating in experimental particle physics and working at the CERN laboratory. He has worked with large corporations across Europe and North America to transform the way they look at their customers and derive value from data, and has held interim management roles at leading Dutch and Irish mobile phone operators building their Insights and Customer Base Management teams.

Allan is one of the founders of CYBAEA, which provides analytics-as-a-service across the globe with a strong focus on commercial results.

His teaching style focuses on practical example and emphasizes results over theoretical sophistication: his courses are for practitioners who need to deliver value to their organizations and while he covers just enough theory to make sure his students are on a firm footing his teaching is not geared to more theoretical students. Expect much hands-on work and very few formulae.

Dates and more information

Contact us to register your interest and receive more information on this course, and we will let you know the next time we run a public class. If you have several colleagues who are interested then we can also run a course just for you.