Learn how to get insights from your customer data, understand your customers deeply and target the right customers with the right products!
The SPSS program offers a comprehensive customer analytics tool – the Direct Marketing module. With this tool you can conduct powerful analyses without being an expert in statistics and data analysis.
The everyday interactions with your customer generates a high amount of valuable data. The customer marketing analysis is the best solution to transform these data into real knowledge. The goal of this analysis is to get you a precise view of your customers, identify the most profitable groups of customers and send them the most appropriate marketing messages.
The Direct Marketing toolkit in SPSS includes six practical analysis procedures. Each of these procedures has its own section in this course.
Most of the procedures above use sophisticated statistical analysis techniques to process your data. However, you don’t have to be a statistician in order to use them. You can get the results you need with a few clicks only, in a few seconds. This is what you will learn in this course.
Every procedure is explained live in SPSS, and the output is interpreted in detail. At the end of each section you can find a couple of practical exercises to strengthen your knowledge.
Join this course today and you will be able to analyze your customer data using state-of-the-art predictive techniques and make informed decisions!
What are you going to learn in this course, exactly.
Just in case you're not familiar with the RFM concept in marketing, I explain here this powerful segmentation technique.
What is the independent RFM analysis method - where the recency, frequency and monetary scores are independent of each other.
What is the nested RFM method - where the recency, frequency and monetary scores depend on each other. The advantages and disadvantages of this method.
In this lecture I describe in detail the data sets we are going to use for our practical examples of RFM analysis.
How to perform the independent RFM analysis procedure in SPSS when our data represent unique customers.
Here I explain thoroughly how to interpret the output of an independent RFM analysis when our data represent unique customers.
How to execute the nested RFM analysis when our data represent unique customers and how to interpret the output.
How to execute the independent RFM analysis when our data represent unique transactions.
How to interpret the results of an independent RFM analysis when our data represent unique transactions.
How to run the nested RFM analysis when our data represent unique transactions, and how to interpret the output.
Here you can find the practical exercises for the RFM analysis.
In this lecture we present the basics of the two-step cluster method, that is used by the Direct Marketing module to segment your customers or contacts into homogeneous classes.
How to execute the two-step cluster method in the Direct Marketing module and how to interpret the main output.
More details about the output of the two-step cluster analysis.
Here you can find the practical exercises for the cluster analysis
How to run the procedure that generates prospect profiles (based on the most important prospect characteristics) and computes the response rate for each profile.
How to identify your best profiles based on the output provided by the SPSS program.
Here you can find the practical exercises for the profile generating technique
How to execute the procedure that helps identifying the postal codes with the highest response rate for your next direct mailing campaign.
The SPSS program computes a number of indicators for each postal code. We'll learn how to interpret them and how to select the postla codes with the best customers.
How to run a postal code analysis when we have to restrain the number of contacts we send the message to (it can happen frequently, for budget reasons for instance).
Here you can find the practical exercises for the postal codes analysis
How to execute the procedure that estimates the buying (or responding) probability for each contact in our list - and how to save our model for later use.
How to select the best contacts based on their buying probability (or buying propensity).
In this lecture we divide our sample of contacts in two sets: training set and test set. Next, we create the model in the training set and validate it in the test set (in other words, use it to estimate the buying probabilities of the contacts in the test set). This way we can know how our prediction model performs in an independent data set.
In this lecture we interpret the output of the validation procedure, comparing the success rate (percentage of buyers) in the training set and test set.
How to use our model predict the buying probabilities for new contacts that were just added to our list. This is all-important, because that's why we have created the model in the first place.
Here you can find the practical exercises for the propensity to purchase models
How to compare the effectiveness of two or more campaigns when the response field is categorical (e.g. yes/no, bought/did not buy etc.)
How to compare campaign effectiveness when the response field is numeric (usually, the purchase amount).
Here you can find the practical exercises for the control package test procedure
Download all the course resources: Powerpoint slides and SPSS data sets