Bombardier Aftermarket Demand Forecast with Machine Learning

42 Pages Posted: 8 Nov 2021 Last revised: 3 Jun 2022

See all articles by Pierre Dodin

Pierre Dodin

Bombardier Aerospace

Jingyi Xiao

HEC Montreal

Yossiri Adulyasak

HEC Montréal

Neda Etebari Alamdari

IVADO Labs

Lea Gauthier

IVADO Labs

Philippe Grangier

IVADO Labs

Paul Lemaitre

IVADO Labs

William Hamilton

McGill University

Date Written: November 5, 2021

Abstract

Intermittent demand patterns are commonly present in business aircraft spare-parts supply chains. Due to the infrequent arrivals and large variations in demand, aircraft aftermarket demand is difficult to forecast, which often leads to shortages or overstocking of spare parts. In this paper, we present the development and implementation of an advanced analytics framework at Bombardier Aerospace which is carried out by the Bombardier inventory planning team and IVADO Labs to improve the aftermarket demand forecasting process. This integrated predictive analytics pipeline leverages machine-learning (ML) models as well as traditional time-series models in a single framework in a systematic fashion. We also make use use of a tree-based machine-learning method, with a large set of input features, to estimate two components of intermittent demand, namely demand sizes and inter-demand intervals. Through the ML models, we incorporate different features including those derived from flight data. Outputs of different forecasting models are combined using an ensemble technique that enhances the robustness and accuracy of the forecasts for different groups of aftermarket spare parts categorized by demand patterns. The validation results show an improvement in forecast accuracy of approximately 7% and in unbiased forecast of 5%. The ML-based Bombardier Aftermarket forecasting system has been successfully deployed and used to forecast the aftermarket demand at Bombardier of more than 1 billion dollars on a regular basis.

Keywords: Demand forecasting, machine learning, spare parts, aftermarket, forecast ensemble

JEL Classification: C53, L62

Suggested Citation

Dodin, Pierre and Xiao, Jingyi and Adulyasak, Yossiri and Etebari Alamdari, Neda and Gauthier, Lea and Grangier, Philippe and Lemaitre, Paul and Hamilton, William, Bombardier Aftermarket Demand Forecast with Machine Learning (November 5, 2021). Available at SSRN: https://ssrn.com/abstract=3957452 or http://dx.doi.org/10.2139/ssrn.3957452

Pierre Dodin

Bombardier Aerospace

Toronto, Ontario
Canada

Jingyi Xiao

HEC Montreal ( email )

3000, Chemin de la Côte-Sainte-Catherine
Montreal, Quebec H2X 2L3
Canada

Yossiri Adulyasak (Contact Author)

HEC Montréal ( email )

3000, Chemin de la Côte-Sainte-Catherine
Montreal, Quebec H2X 2L3
Canada

HOME PAGE: http://yossiri.info/

Neda Etebari Alamdari

IVADO Labs ( email )

5100 4e avenue
Montreal, H1Y 2V3
Canada

Lea Gauthier

IVADO Labs ( email )

5100 4e avenue
Montreal, H1Y 2V3
Canada

Philippe Grangier

IVADO Labs ( email )

5100 4e avenue
Montreal, H1Y 2V3
Canada

Paul Lemaitre

IVADO Labs ( email )

5100 4e avenue
Montreal, H1Y 2V3
Canada

William Hamilton

McGill University ( email )

1001 Sherbrooke St. W
Montreal, Quebec H3A 1G5
Canada

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
186
Abstract Views
697
rank
223,224
PlumX Metrics