Online Learning and Matching for Resource Allocation Problems

TL;DR

This paper develops online algorithms for resource allocation in e-commerce, optimizing recommendations under stock constraints with non-stationary customer arrivals, validated through large-scale synthetic experiments.

Contribution

It introduces integrated online learning and optimization algorithms for non-stationary customer arrivals, improving resource allocation under constraints.

Findings

Algorithms outperform baseline methods in synthetic experiments.

Time segmentation effectively handles non-stationary customer arrivals.

Proposed methods are scalable and efficient for large-scale data.

Abstract

In order for an e-commerce platform to maximize its revenue, it must recommend customers items they are most likely to purchase. However, the company often has business constraints on these items, such as the number of each item in stock. In this work, our goal is to recommend items to users as they arrive on a webpage sequentially, in an online manner, in order to maximize reward for a company, but also satisfy budget constraints. We first approach the simpler online problem in which the customers arrive as a stationary Poisson process, and present an integrated algorithm that performs online optimization and online learning together. We then make the model more complicated but more realistic, treating the arrival processes as non-stationary Poisson processes. To deal with heterogeneous customer arrivals, we propose a time segmentation algorithm that converts a non-stationary problem into a series of stationary problems. Experiments conducted on large-scale synthetic data demonstrate the effectiveness and efficiency of our proposed approaches on solving constrained resource allocation problems.