Getting Started

Using Customer Behavior Data to Improve Customer Retention

Blog Home > Using Customer Behavior Data to Improve Customer Retention

Using Customer Behavior Data to Improve Customer Retention

We’ve uploaded some sample data sets in the IBM Watson Analytics community for you to work with as you learn more about Watson Analytics. This expert blog uses the Telco Customer Churn data set. WA_Fn-UseC_-Telco-Customer-Churn

What’s in the Telco Customer Churn data set?

This data set provides info to help you predict behavior to retain customers. You can analyze all relevant customer data and develop focused customer retention programs.

A telecommunications company is concerned about the number of customers leaving their landline business for cable competitors. They need to understand who is leaving. Imagine that you’re an analyst at this company and you have to find out who is leaving and why.

The data set includes information about:

  • Customers who left within the last month – the column is called Churn
  • Services that each customer has signed up for – phone, multiple lines, internet, online security, online backup, device protection, tech support, and streaming TV and movies
  • Customer account information – how long they’ve been a customer, contract, payment method, paperless billing, monthly charges, and total charges
  • Demographic info about customers – gender, age range, and if they have partners and dependents

If you don’t have the data set…

  1. Go to
  2. Download the Telco Customer Churn sample data file.
  3. In Watson Analytics, tap Add and upload Telco Customer Churn.
    The filename is a bit longer: WA_Fn-UseC_-Telco-Customer-Churn.csv.


The data set appears as a tile in the Welcome page and you’re ready to get to work.


Which customers are likely to leave?

  1. To find the answer to this question, tap the WA_Fn-UseC_-Telco-Customer-Churn tile and tap Prediction.

You want to learn more about customers who’ve left the company in the past month – this is the target that you want to investigate. The data is in the column called Churn, which is the column we’ve already picked as the target for the prediction. Let’s find out which variables influence customers who leave.

  1. Name the prediction and tap Create Prediction.

Watson Analytics analyzes the data and generates visualizations to provide insights into this issue.

The spiral shows you the top predictors, or key drivers, of churn in color; other drivers appear in gray. The closer the driver is to the center of the spiral, the stronger the predictive strength of the driver is.

Predictive strength


The key drivers are tenure, contract, and online security. The visualizations to the right of the spiral show how one driver at a time drives churn. The blue or green dots in the upper right of the visualizations identify which driver is being shown.

  1. Tap tenure drives Churn.

This new visualization shows that customers who have been customers for shorter periods are more likely to leave.

  1. Close this visualization by tapping the X in its upper right corner.

You can look at the visualizations for the other drivers on your own. Let’s move on and explore churn in more depth.

To the left of the spiral are options for creating visualizations that show more than one driver at a time.


  1. Let’s go straight to the deeper and more predictive analysis of the data. Tap Combination.

You get a new set of visualizations on the right, including a decision tree, that show the combination of variables that influence your target.


  1. Let’s look at the combination of key drivers that influence whether customers leave. Tap the decision tree.


  1. Let’s look at a word cloud about the key factors that influence churn. Tap Predictor Importance.

Contract, Internet Service, Tenure, and Total Charges are the most important factors.


  1. Let’s get some more details on who is leaving so we can predict who is likely to leave in the future. Tap Top Decision Rules.

The rules are specific and detailed, and are sorted by accuracy. They currently focus on customers who do not leave. We need to change that.

  1. Change the No to Yes.

A clearer view emerges. Customers who leave tend to be ones who are on a month-to-month contract, have fiber optic internet service, and have been customers for shorter periods.

You can now predict which customers are at risk to churn. Use the decision rules to identify customers who fit the churn profile so you can proactively offer them an incentive to stay.


More Getting Started Stories

Getting Started

Getting Started Tutorial for IBM Watson Analytics

We all ask questions about our data every day. Some questions are about a status or situation. Some are about why something happened. In short, when it comes to data, we want to know what is happening, why it’s happening, and what insights need to be communicated with others. IBM® Watson™ Analytics can help you understand your data, find insights that are hidden in your data and provide you with answers to make confident decisions – all on your own. This tutorial uses sample data to walk you through the skills you need to get started. Each chapter covers a different area of Watson Analytics, from importing data to discovering insights to sharing these insights in a dashboard to social media analytics. Take 15-30 minutes to complete a chapter, or complete the entire tutorial in about 90 minutes. Getting started with IBM Watson Analytics Last updated: 2017-11-22

Getting Started

VIDEO: Welcome to Watson Analytics

Take a short tour and see how quickly you can get started on analyzing your data.


Applying filters in a Watson Analytics dashboard

There’s a few different ways to apply filters to your visualizations in a dashboard. Here’s an overview of the different types of filters and how they work. You can filter visualizations in your dashboard in three main ways: Filter all visualizations in your dashboard Filter one visualization based on a column in the visualization (Keep/Exclude) Filter one visualization based on a column not in the visualization (Local Filter) What’s Filtered Right Now? To get started, here’s a quick way to check filter status. TIP: Click the Filter Status icon in a visualization to see the current filtering that is applied. Applying a global filter across all visualizations in the dashboard Use the data tray to configure a filter that applies to all visualizations in the view. This type of filter applies across all the tabs in the view for any visualization that uses that same data set. Click on a column title in the data tray and then click the filter icon. Select your filter criteria and then click away from the filter menu to close it. Here’s an example of a global filter for the Region column set to only “Mid-Atlantic” and “Northeast”. TIP: The blue line above a column in the data tray means that column has a global filter. Filter a single visualization using the Keep/Exclude option Use the Keep/Exclude filter to display or hide specific data points in a visualization. A data point can be an element or data point displayed in the visualization. For example, a bar in a bar chart, a bubble in a bubble chart, an item in a legend or an item on an axis. Right-click one or more data points in a visualization and then choose Keep or Exclude. The filter is applied to that visualization only. The other visualizations in the view do not update. After setting a filter, you can click the Filter Status icon in the visualization to see the current filter status. Tip: This type of filter can also be configured in the column panel when you edit a visualization. Filter a single visualization for a column not displayed Use the Local filter option to slice your data on a column that’s not displayed in a visualization. This type of filter is available only for visualizations you create in Assemble and does not update any other visualizations in your view. 1.Change the view into Edit mode and then click the Expand icon for the visualization. 2.Drag the column you want to filter on from the data tray to the Local filters option. 3.Select or type the criteria for the filter, and then click away from the filter pane. 4.Click the Collapse icon to return to the view. To verify the filter, click the filter icon on the border of the visualization. For more information and details see the following resources: Documentation: IBM Watson Analytics Docs > Assemble > Filtering Video: How to filter all visualizations in a dashboard or story