Types of Customer Analytics
Following are the different types of analytics available for Customer Analytics. (Chapter 7 provides a more complete description of these methods.)
* Decision Trees — Decision trees classify historical data into probability hierarchies. They are used in scenarios such as identifying which customers are more likely to churn (in order to improve customer retention), or which customers keep good credit (in order to screen prospects better). The results of the decision tree can then be used to initiate a customer loyalty program.
* Scoring — Scoring scenarios may be used to identify customers of a particular market segment for a new product launch, or to categorize customers most likely to cancel service to a subscription. One of three regression types is used to perform scoring.
* Clustering — Clustering divides a set of data so that records with similar content are in the same group, while records with dissimilar content are in different groups. Clustering is also known as segmentation, since the relationships it finds can be used to identify customer or market segments.
* Association Analysis — Association analysis is a type of dependency analysis and is sometimes also referred to as market basket analysis because of its heavy use in retail. However, there are practical applications in other industries such as a telecom company offering additional services to customers who have already bought a specific set of services.
* Customer Lifetime Value Analysis — Customer lifetime value analysis treats customers as investments, and calculates their net present value depending on projections of the lifetime profitability of the customer. Predicted customer profitability and the predicted relationship life span of the customer are the primary factors for the analysis. Maximum lifetime profit for minimum investment is what is sought via CLTV analysis. The costs of acquiring and keeping a customer must be evaluated by the stream of profits the customer is expected to bring.
* RFM Analysis — RFM analysis evaluates the recency, frequency, and monetary value of customer purchases to determine the likelihood that a given customer will respond to a campaign. It is an empirical method that has long been applied to campaign planning and optimization as an alternative to segmenting a customer base by less effective demographic means.
