Our client is one of the most recognized automobile brands in the world. It is at the echelon of the automobile industry, producing products that are known for a combination of quality, utility, and style, operating in over 150 countries and has production facilities at more than 30 locations worldwide.
TransOrg Analytics used various machine learning techniques to analyze customer lifetime value and developed a scoring methodology based on the weights decided by the business for different customer attributes, for the client to execute smart promotions and sales planning.
Different filters were used for RFM segmentation which was based on: –
- Customers who share similar age groups, in percentiles according to their recency, frequency, and monetary performance.
- Customers characterized by similar car ownership counts can be grouped, and their positioning in percentiles can be determined based on recency, frequency, and monetary performance
- The integration of these two factors also enables a dual-tier segmentation strategy for customers
For Customer Lifetime Value (CLV) modelling, there were many methodologies that deal with the portion of CLV associated with direct purchases, but the two most broad classes are generally defined as: –
- Historical CLV
- Predictive CLV
TransOrg used predictive modelling approach where, it segmented the problem statement into two parts. Here CLV was defined as combination of two things which were purchase visit frequency and average order value.
- Clear insights for Customer Lifetime Value enabled client for customized engagement method, informed decision making to maximize client connection and support long term success.
- There was an increase in model performance developed by TransOrg in comparison to client’s inhouse model which they were using earlier