Business Problem
A pharma company wanted to build a comprehensive marketing campaign for their existing and prospective customers. The challenge is to map customer information from the internal system to 3rd party information since there is no common customer entity key between the two systems.
Solution
An entity matching system was built to compare and match market entity with internal customer entity. The market data is first processed into an internal standard. Then, candidate pairs are generated based on an initial matching criterion. Next, cosine similarities are calculated for each candidate pair, and based on the user-defined matching threshold, the entities between systems are matched. The matched data is tested for accuracy. Finally, this process of matching is implemented to standardize internal data and remove duplicates.
Impact
Here entities were matched with 85% accuracy. Developed entity mapping algorithm is further utilized to manage master keys in Master Data.
** The client has chosen AIDAS Analytics Office (subscription-based pay-as-you-go) services to run business analytics projects.
