Abstract: Systems and methods for aggregating customer social media and transaction data and using the aggregated data to predict future customer behavior are disclosed. In embodiments, social media messages are matched to customer profiles by attempting to match a social media identifier attribute to a set of social media identifiers of a stored customer profile in a customer database, or attempting to match other profile information. If no matches are found, a new customer profile can be created and stored based on the social media message. In embodiments, one or more scores are calculated based on the known behavior of a set of similar customers determined from the customer database and the transaction database. Similar customers can include customers with similar demographic information, location, or customers that have expressed interest in similar products. The one or more scores are stored in a score database in embodiments, for access by prediction consumption systems.