Customer Prospecting model

Problem Statement


An Omni channel retailer based in Long Island partnered with a MSO from North East US. With the help of third-party data providers, the retailer identified their most valuable customers from the MSO subscriber base. (To identify similar customers for targeted marketing)




Demographic data provided by third party and viewership data from the MSO were used as primary attributes.


Feature Engineering to create meaningful attributes From the viewership information available. This included considering the network affinity, day of week affinity, daypart affinity so on and so forth.


Multiple classification models were developed to identify similar customers along with their propensity Outcome to visit the store.




~10% of the customers(~2M Customers) similar to existing ones were identified 


Upon deep dive analysis, It was observed that the look-alikes were dominated by people who are in the age group of 50 and above are from a medium to high income group and are college graduates.


Marketing Team was given the responsibility to design targeted campaigns to acquire these customers.