Abstract
The volatility in a CPG market is modeled using a bottom up simulation approach and validated against disaggregated supermarket transactions data. The simulation uses independent agents, each agent representing unique households in the data. A simple behavioral model incorporates household preferences for product attributes and prices. Our validation strategy tests the model predictions at both macro and micro levels and benchmarks the performance in each against a random choice model. The model significantly outperforms the benchmark at both levels. At the macro level, choices made by heterogenous agents accurately captures the volatility in market shares - with the direction of change being more accurately predicted than the magnitude. At the micro level, it achieves a reasonable degree of prediction accuracy of household level SKU choice and a substantially higher accuracy for attribute choice