Our work in



Case Study

Data science to recommend CPG campaigns to targeted audiences to maximize ROI and sales lift

Train machine learning models to predict consumer purchase behavior to optimize CPG campaigns


Our client, a digital marketing platform, enables CPG brands to reach customers via retail locations. The brands need predictive insights on which campaigns are most likely to generate sales lift and/or ROI, based on past behavior.


We aggregated point of sale data from 6,000+ locations over a three-year period to identify campaigns based on price discounts. Seasonal sales trends were modeled to identify true sales lift for the campaign. Campaign costs were estimated to generate a campaign ROI / margin. Ensemble machine learning methods were used to learn past campaign behavior to predict sales lift and ROI. Our client saw a 4x increase in sales leads from a major industry conference based on the newly introduced campaign insights.

BackBack to tech case studies
View related case studies