Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ye, Tinghan, Hijazi, Amira, Van Hentenryck, Pascal
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.17340
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916874532421632
author Ye, Tinghan
Hijazi, Amira
Van Hentenryck, Pascal
author_facet Ye, Tinghan
Hijazi, Amira
Van Hentenryck, Pascal
contents Accurate estimation of order fulfillment time is critical for e-commerce logistics, yet traditional rule-based approaches often fail to capture the inherent uncertainties in delivery operations. This paper introduces a novel framework for distributional forecasting of order fulfillment time, leveraging Conformal Predictive Systems and Cross Venn-Abers Predictors -- model-agnostic techniques that provide rigorous coverage or validity guarantees. The proposed machine learning methods integrate granular spatiotemporal features, capturing fulfillment location and carrier performance dynamics to enhance predictive accuracy. Additionally, a cost-sensitive decision rule is developed to convert probabilistic forecasts into reliable point predictions. Experimental evaluation on a large-scale industrial dataset demonstrates that the proposed methods generate competitive distributional forecasts, while machine learning-based point predictions significantly outperform the existing rule-based system -- achieving up to 14% higher prediction accuracy and up to 75% improvement in identifying late deliveries.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17340
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Conformal Predictive Distributions for Order Fulfillment Time Forecasting
Ye, Tinghan
Hijazi, Amira
Van Hentenryck, Pascal
Machine Learning
Accurate estimation of order fulfillment time is critical for e-commerce logistics, yet traditional rule-based approaches often fail to capture the inherent uncertainties in delivery operations. This paper introduces a novel framework for distributional forecasting of order fulfillment time, leveraging Conformal Predictive Systems and Cross Venn-Abers Predictors -- model-agnostic techniques that provide rigorous coverage or validity guarantees. The proposed machine learning methods integrate granular spatiotemporal features, capturing fulfillment location and carrier performance dynamics to enhance predictive accuracy. Additionally, a cost-sensitive decision rule is developed to convert probabilistic forecasts into reliable point predictions. Experimental evaluation on a large-scale industrial dataset demonstrates that the proposed methods generate competitive distributional forecasts, while machine learning-based point predictions significantly outperform the existing rule-based system -- achieving up to 14% higher prediction accuracy and up to 75% improvement in identifying late deliveries.
title Conformal Predictive Distributions for Order Fulfillment Time Forecasting
topic Machine Learning
url https://arxiv.org/abs/2505.17340