Cross Sell – Up sell Analytics services help organizations identify and target customers who have a higher propensity of purchasing additional products.
Market Equations helps a leading financial services group leverage its huge customer database to attract customers towards its various other financial products using innovative and smartly designed cross sell strategies.
- Identify and target prospective customers for cross selling
- Identify who should be targeted, with which product and the optimum price point
- Build a scorecard to calculate the propensity of the target customers to purchase various products
- Insufficient , inaccurate and unstructured data
- Only data made available was the customer coordinates
- Creating surrogate data based on past cross sell campaigns to build a robust model
Cross Sell – Up Sell Analytics outsourcing services from Market Equations India helps organizations build smartly designed cross sell – up sell strategies to help them acquire and retain the most profitable customers. Contact Us
Given the inconsistency and inaccuracy in the data available and the only available data being the customer coordinates, it was critical to examine the quality of the data. Inaccuracies and inconsistencies in the data were removed to develop a clean data set that could be used for further analysis.
Since the data available was insufficient to build a robust model, the next step was to develop a model to compare purchase patterns of customers from a successful campaign run in the recent past. The result of the clustering was then used to match the profiles to the existing customer data to profile and segment customers with similar buying patterns.
Using this tested logic, surrogate data fields were created e.g. income range for vehicle owners using information on vehicle-make and vehicle-age (on which we used statistical techniques e.g. correlation between two fields), survey results e.g. percentage of income of customers who invest in insurance, micro-economic factors e.g. purchasing power of people depending on demographics etc.
The final step was to use this data powerhouse to build a scoring engine to identify who should be targeted, with which product and the optimum price point that would lead to a higher propensity of purchase.
The model output was developed to reflect a comparative score (normalized between 0 and 100) such that higher the score of a customer for a given product higher the propensity of cross selling that particular product to that customer. For each product individual scorecards were developed and these scores were then aligned with the profitability to decide on the strategies for cross-selling.