SPSS - Customers

TrustMark CFI

Situation

TrustMark CFI, part of the worldwide CFI Group, is a market research and management consulting business in Zollikon, Switzerland. TrustMark serves as a prime example of the data mining capabilities that market researchers can offer.

Challenge

Data mining presents market research firms with a real opportunity. It can provide in-depth analyses of survey data at great speed or it can help combine research data with other types of data to provide a much richer source of insight. PASW Modeler, a market-leading data mining tool from SPSS Inc., is widely used in many industries, but not heavily in market research—so far.

Solution

In a project for a banking customer, TrustMark CFI consultants used PASW Modeler to analyze customer satisfaction data with operational data, and then build models that would forecast future consumer activity.

Interested in TrustMark CFI? Download the PDF

Data mining is the ideal way to find out what the drivers of success in a business are.
John McConnell
SPSS Inc.

Forecasted more accurately

By combining the two data sources, the models produced by PASW Modeler were more accurate—and comparing the predictions from the model with reality proved this. When using operational data only, PASW Modeler correctly identified 65.4 percent of the customers who had increased their asset volume significantly, and 56.9 percent of those who had greatly reduced it.

However, using the two data sources together, the model was correct in 67.9 percent and 60.7 percent of cases respectively. According to Leonie van de Vijfeijken, a research analyst at TrustMark CFI, the results would have been even better if there hadn't been a large time lag between gathering the operational and survey data.

Improved financial performance

"Although the difference in the figures doesn't sound remarkable, it is significant to the bank's business and helps reduce its marketing costs," said van de Vijfeijken. Using these models on current data allows the bank to predict whether an account is likely to be profitable, at risk, or inactive. This information enables it to target marketing resources more effectively and, in the final analysis, improve financial performance.

Interestingly, had the bank not used predictive models and simply run standard analyses on the survey research data, a very different picture would have emerged. When past research data was compared with reality, it was shown that only 21 percent of the respondents who said they were going to increase their asset volume actually did so.

"TrustMark CFI identified a group of 18 key variables that together gave an accurate prediction of the change in asset volume in bank accounts," said John McConnell, a market research consultant with SPSS Inc. "However, it is market research that explains why these drivers are important."