Objective
Identify relationships between sales and various marketing activities to understand how various elements of the marketing mix combine to drive sales in a competitive framework.
Approach
From the client’s transnational database, we have considered the retail audit data like Volume sales, WARP, Weighted Distribution, and Promotion volumes. From media data, both GRP and NGRP for their premium brands on monthly basis were obtained. We observed that most of the brands/SKUs have non-intuitive relationship with variables at the uni-variate level and hence, we created some transformed variables by using domain knowledge such as SOV, Adstock and Price index –etc., and built a Multiplicative model to capture the interactive effect by using an Empirical Bayesian framework to estimate the relationships.
The model was evaluated on the basis of MAPE (Mean Absolute Percentage Error) and we determined the price elasticity and contribution of each activity on the sales.
Impact
The client was able to assess the impact of self and competitors activities on sales which impacted its ability to allocate marketing budget based on impact – deriving maximum return on investment.
