Automobile demand forecasting: Spatiotemporal and hierarchical modeling, life cycle dynamics, and user-generated online information

2025-11-21

AI Summary

German premium automotive OEMs face significant challenges in monthly demand forecasting across diverse product variants, geographically dispersed markets, and multiple organizational levels—stemming from sparse variant-level data, highly dynamic product lifecycles, and volatile market conditions. To address this, we propose a unified framework integrating spatiotemporal dependencies, product lifecycle dynamics, and user online behavioral signals for both point and probabilistic forecasting. Methodologically, we couple LightGBM with quantile regression to model fine-grained demand; employ Shapley values for interpretable factor attribution; and formulate a mixed-integer linear program (MILP) to enforce cross-level forecast consistency. Empirical results demonstrate that online engagement metrics, strategic planning targets, and competitive benchmarks strongly explain medium- to long-term demand; integer constraints substantially enhance operational feasibility; and the framework achieves statistically significant accuracy improvements over state-of-the-art baselines—validating the efficacy of hierarchical coordination and behavioral data integration.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Machine Learning: Calibration & Uncertainty Quantification
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Premium automotive manufacturers face increasingly complex forecasting challenges due to high product variety, sparse variant-level data, and volatile market dynamics. This study addresses monthly automobile demand forecasting across a multi-product, multi-market, and multi-level hierarchy using data from a German premium manufacturer. The methodology combines point and probabilistic forecasts across strategic and operational planning levels, leveraging ensembles of LightGBM models with pooled training sets, quantile regression, and a mixed-integer linear programming reconciliation approach. Results highlight that spatiotemporal dependencies, as well as rounding bias, significantly affect forecast accuracy, underscoring the importance of integer forecasts for operational feasibility. Shapley analysis shows that short-term demand is reactive, shaped by life cycle maturity, autoregressive momentum, and operational signals, whereas medium-term demand reflects anticipatory drivers such as online engagement, planning targets, and competitive indicators, with online behavioral data considerably improving accuracy at disaggregated levels.

Problem

• Forecasting automobile demand across multi-level product hierarchies and markets
• Addressing sparse data and volatile dynamics in premium automotive manufacturing
• Integrating spatiotemporal dependencies and online behavioral data for accuracy

Innovation

• LightGBM ensembles with pooled training sets
• Quantile regression for probabilistic forecasting
• Mixed-integer linear programming reconciliation approach