Trade Spends Optimization

Challenges

1. The client is a leading multinational consumer product goods company who wanted to set-up a robust trade optimization engine for maximizing revenue uplift across outlets

2. They wanted to set trade spends targets as per system recommendation and monitor all at a single place

3. They used heuristic rule-based pricing strategy which was ineffective for multiple product categories and a wide range of campaigns

4. They were unable to effectively capture long term impact and ROI of trade spends

5. The existing system was also inefficient in utilizing multiple data sources and handling big data flowing at a higher frequency

Solution

1. ML Models - Trade spend sensitivity analysis across outlets for the targeted brands to determine which outlets are most sensitive to Trade spends

   • Classified the outlets based on historical trade spends and Market share data using clustering algorithm for multiple locality types

   • Created Generalized Linear models for each of the outlet groups which can determine the volume output from the outlets based on the trade spends over the month/ year

   • Dependent value - Volume, independent variables - constant, AND, Market share,AND of nearby outlets(2 KM area),Locality Type, Locality

2. Volume Salience - Coupled the outlet sensitivity with volume salience to get the max revenue growth

3. Spends simulator - Created a simulator based on the inputs from the model above to determine the spends distribution across outlets to maximize the revenue

Business Impact

1. More time spent on decision making then manual calibrations with automated models to efficiently distribute AND across outlets.

2. Revenue growth 10% (QoQ) & Cash savings upto 2 % (of net sales)

Contact us

Whether you have a request, a query, or want to work with us, use the form below to get in touch with our team.