Predictive modeling of consumer financial behavior

A system for predicting consumer financial behavior, comprising:

• a plurality of merchant segments, each merchant segment having a set of merchants associated therewith;
• a plurality of merchant segment predictive models, each model associated with one of the merchant segments for predicting spending by an individual consumer in the merchant segment in a predicted time period as a function of transaction statistics of the consumer for transactions in a prior time period;
• and
• a data processing module that receives transaction data for a consumer, and constructs the transaction statistics for the prior time period for input into selected ones of the merchant segment predictive models.

A system for forming merchant segments, comprising:

• a data processing module that receives consumer transaction data for a plurality of consumer accounts, and organizes the transaction data by account, and within account, sequences the transactions by time;
• a data processing module that determines from the sequenced transaction data an expected frequency of co-occurrence for each merchant, and that constructs for each merchant a merchant vector as a function of unexpected frequency of co-occurrences of the merchant;
• and
• a clustering module that clusters the merchant vectors into merchant segment by determining merchant vectors that are closely aligned with each other.