Challenges in Achieving Explainability & Control with Supply Chain Forecasts

Rishab Guha, Phillip Jang, Andrea Tambalotti

Keywords: supply chain forecasting, time series forecasting, econometrics

TL;DR: This paper details the explainability and controllability requirements that have prevented AI from taking over aggregate time-series forecasting applications (e.g., forecasting total demand flow for a supply chain).

Abstract: [Industry Challenge Submission] AI and Deep Learning methods have revolutionized many forecasting applications but have not achieved widespread adoption in industry for aggregate forecasting. This paper challenges the AI research community by identifying three critical capabilities that current AI approaches lack: (1) multivariate consistency at scale, (2) explainable and controllable long-run assumptions, and (3) flexible incorporation of forward-looking external inputs. We describe a Bayesian state-space framework that is used in production to address these requirements at a major e-commerce retailer, where our forecasts influence billions of dollars in spending decisions. By detailing how traditional time series methods solve these challenges today, we identify concrete opportunities for AI researchers to develop hybrid approaches that combine the accuracy advantages of modern AI with the explainability and control benefits of traditional methods.

Submission Number: 24