An industry case of large-scale demand forecasting of hierarchical components

TL;DR

This paper presents an industry case study on large-scale demand forecasting for hierarchical components, introducing new methods and tools to improve accuracy and interpretability in manufacturing settings.

Contribution

It offers a comprehensive benchmark of forecasting methods, a novel data transformation, an alternative matrix factorization approach, a topological data analysis-based model selection technique, and a new dataset.

Findings

Benchmark of 14 demand forecast methods

Effective data transformation technique

Matrix factorization as an ARIMA alternative

Abstract

Demand forecasting of hierarchical components is essential in manufacturing. However, its discussion in the machine-learning literature has been limited, and judgemental forecasts remain pervasive in the industry. Demand planners require easy-to-understand tools capable of delivering state-of-the-art results. This work presents an industry case of demand forecasting at one of the largest manufacturers of electronics in the world. It seeks to support practitioners with five contributions: (1) A benchmark of fourteen demand forecast methods applied to a relevant data set, (2) A data transformation technique yielding comparable results with state of the art, (3) An alternative to ARIMA based on matrix factorization, (4) A model selection technique based on topological data analysis for time series and (5) A novel data set. Organizations seeking to up-skill existing personnel and increase forecast accuracy will find value in this work.