Business Metric-Aware Forecasting for Inventory Management

TL;DR

This paper introduces a method to optimize time-series forecasts directly for business metrics in inventory management, improving downstream performance over traditional forecasting objectives.

Contribution

It presents an end-to-end differentiable approach to optimize proxies of business metrics, aligning forecasts with business goals in inventory management.

Findings

End-to-end optimization outperforms standard forecasting metrics by up to 54%.

The approach is effective across different models, including simple scaling and LSTM.

Optimizing for business metrics improves inventory management outcomes.

Abstract

Time-series forecasts play a critical role in business planning. However, forecasters typically optimize objectives that are agnostic to downstream business goals and thus can produce forecasts misaligned with business preferences. In this work, we demonstrate that optimization of conventional forecasting metrics can often lead to sub-optimal downstream business performance. Focusing on the inventory management setting, we derive an efficient procedure for computing and optimizing proxies of common downstream business metrics in an end-to-end differentiable manner. We explore a wide range of plausible cost trade-off scenarios, and empirically demonstrate that end-to-end optimization often outperforms optimization of standard business-agnostic forecasting metrics (by up to 45.7% for a simple scaling model, and up to 54.0% for an LSTM encoder-decoder model). Finally, we discuss how our findings could benefit other business contexts.