Beyond Accuracy: Evaluating Forecasting Models by Multi-Echelon Inventory Cost

2026-03-17

AI Summary

This study addresses the limitation of conventional forecasting evaluation, which overemphasizes prediction accuracy while neglecting its impact on operational costs in multi-echelon inventory systems. The authors propose an end-to-end joint optimization framework that integrates statistical models, machine learning, and deep time-series architectures—including Temporal CNNs and LSTMs—within a unified simulation environment. Using the M5 Walmart dataset, they evaluate inventory cost performance under both single- and two-echelon newsvendor settings. Moving beyond accuracy-centric paradigms, the work introduces a decision-oriented evaluation metric grounded in multi-echelon inventory costs. Experimental results demonstrate that deep time-series models substantially reduce inventory costs and improve order fill rates. Sensitivity analyses and multi-echelon evaluations further confirm the robustness and scalability of the approach, offering a novel paradigm for data-driven supply chain decision-making.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Learning to Search
• Machine Learning: Time-Series/Data Streams

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This study develops a digitalized forecasting-inventory optimization pipeline integrating traditional forecasting models, machine learning regressors, and deep sequence models within a unified inventory simulation framework. Using the M5 Walmart dataset, we evaluate seven forecasting approaches and assess their operational impact under single- and two-echelon newsvendor systems. Results indicate that Temporal CNN and LSTM models significantly reduce inventory costs and improve fill rates compared to statistical baselines. Sensitivity and multi-echelon analyses demonstrate robustness and scalability, offering a data-driven decision-support tool for modern supply chains.

Problem

• forecasting evaluation
• multi-echelon inventory
• inventory cost
• supply chain
• operational impact

Innovation

• forecasting-inventory integration
• multi-echelon inventory cost
• Temporal CNN
• LSTM
• digital supply chain