Promotions, advertising and other forms of “demand shaping” can be enormously expensive, costing up to more than 15% of gross revenues. Yet determining their “lift” remains a daunting challenge. A large number of variables with complex interactions are buried in huge amounts of data with a high degree of noise. Even with substantial expertise and fairly consistent baseline demand, it’s usually not possible to understand correlations among variables.
But automatically capturing this behaviour is critical to producing an accurate forecast. To solve this problem, we complement the baseline stochastic model with powerful machine learning technology that allows us to account for a multitude of attributes, ranging from product and market to social activity.This technique recognises the shared characteristics of promotional events and identifies their effect on normal sales with deep learning algorithms that greatly enhance the responsiveness of the forecast. Fast multi-dimensional modelling that handles both qualitative and quantitative variables is particularly well suited to describe and predict the non-linear demand driven by promotional activity.
Our software helps planners and marketers automatically correlate promotional data with demand. It helps planners optimise both promotional activity strategy and stock availability, while providing visibility into the real ROIs of different promotions types for individual items and specific selling areas.