Resilient Neural Forecasting Systems

TL;DR

This paper presents a resilient neural forecasting system that effectively handles data challenges like distribution shifts, missing values, and anomalies, ensuring autonomous and stable labor planning forecasts.

Contribution

It introduces a comprehensive approach combining retraining, native missing value handling, and anomaly detection to enhance neural forecasting resilience in industrial settings.

Findings

System outperforms hybrid models with human overrides

Handles missing data without imputation

Maintains stability amid data distribution shifts

Abstract

Industrial machine learning systems face data challenges that are often under-explored in the academic literature. Common data challenges are data distribution shifts, missing values and anomalies. In this paper, we discuss data challenges and solutions in the context of a Neural Forecasting application on labor planning.We discuss how to make this forecasting system resilient to these data challenges. We address changes in data distribution with a periodic retraining scheme and discuss the critical importance of model stability in this setting. Furthermore, we show how our deep learning model deals with missing values natively without requiring imputation. Finally, we describe how we detect anomalies in the input data and mitigate their effect before they impact the forecasts. This results in a fully autonomous forecasting system that compares favorably to a hybrid system consisting of the algorithm and human overrides.