A Probabilistic Simulator of Spatial Demand for Product Allocation

TL;DR

This paper introduces a probabilistic model for spatial demand in physical retail, improving demand prediction and enabling automated product placement using Deep Q-Learning to optimize store layouts.

Contribution

The paper presents a novel stochastic model for spatial demand prediction and demonstrates how to learn optimal product placement policies with reinforcement learning.

Findings

The model outperforms existing demand prediction baselines.

Deep Q-Learning effectively learns optimal product allocation policies.

The approach reduces the need for costly physical experimentation.

Abstract

Connecting consumers with relevant products is a very important problem in both online and offline commerce. In physical retail, product placement is an effective way to connect consumers with products. However, selecting product locations within a store can be a tedious process. Moreover, learning important spatial patterns in offline retail is challenging due to the scarcity of data and the high cost of exploration and experimentation in the physical world. To address these challenges, we propose a stochastic model of spatial demand in physical retail. We show that the proposed model is more predictive of demand than existing baselines. We also perform a preliminary study into different automation techniques and show that an optimal product allocation policy can be learned through Deep Q-Learning.