Machine Learning Driven Campaign Budget Allocation: A Large-Scale Empirical Study of Malls

Abstract

Evaluating the returns to marketing spending and designing optimal budget allocations have been challenging tasks for businesses. New data availability and novel machine learning methods provide new opportunities to significantly improve such decisions. The goal of this paper is to prescribe the optimal marketing budget allocation for a major shopping mall chain, specifying the timing, content, and budget allocated to different campaigns. We use a unique daily-level dataset on customer traffic and campaigns across 25 malls during a two-year period for the analysis. Then we propose a novel machine learning model, generalized additive model with a neural network term to learn the relationship between campaign budget and customer traffic. We classify the campaigns into different categories based on customer intentions, sales incentives, experience incentives, and online promotion conflicts and compare the ROI for each category. Results indicate that during the off-season, campaigns with experience incentives lead to larger increases in customer traffic than campaigns with sales incentives only; during the peak-season, campaigns with both incentives have similar impacts on customer traffic as those with experience incentives only. In addition, we find that malls can piggyback on online shopping promotion events and boost customer traffic with sufficient marketing spending in the same period. We further compute an optimal budget allocation scheme based on the prediction results. The optimization step yields an additional insight that malls should reduce budget during the peak-season and increase budget during the off-season to avoid over-marketing. Overall, we estimate that holding the total budget fixed, malls are expected to see an 11% increase in ROI from implementing the budget optimization.

Keywords: Machine Learning, Budget Allocation, Generalized Additive Models, Marketing Campaigns