Uncertainty-Aware Delivery Delay Duration Prediction via Multi-Task Deep Learning

2026-02-23

AI Summary

This work addresses the challenge of accurately predicting rare yet high-impact freight delays in highly imbalanced and heterogeneous logistics networks. The authors propose an end-to-end trainable multitask deep learning framework that jointly models classification and regression tasks to separately handle on-time and delayed shipments. A dedicated embedding layer is introduced to effectively process high-dimensional tabular features, enabling uncertainty-aware probabilistic predictions. Evaluated on a real-world freight dataset comprising over ten million records, the method reduces the mean absolute error in delay duration prediction to 0.67–0.91 days, outperforming single-step and two-stage tree-based models by 41–64% and 15–35%, respectively. This approach significantly enhances both the detection and quantification of rare delay events.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Accurate delivery delay prediction is critical for maintaining operational efficiency and customer satisfaction across modern supply chains. Yet the increasing complexity of logistics networks, spanning multimodal transportation, cross-country routing, and pronounced regional variability, makes this prediction task inherently challenging. This paper introduces a multi-task deep learning model for delivery delay duration prediction in the presence of significant imbalanced data, where delayed shipments are rare but operationally consequential. The model embeds high-dimensional shipment features with dedicated embedding layers for tabular data, and then uses a classification-then-regression strategy to predict the delivery delay duration for on-time and delayed shipments. Unlike sequential pipelines, this approach enables end-to-end training, improves the detection of delayed cases, and supports probabilistic forecasting for uncertainty-aware decision making. The proposed approach is evaluated on a large-scale real-world dataset from an industrial partner, comprising more than 10 million historical shipment records across four major source locations with distinct regional characteristics. The proposed model is compared with traditional machine learning methods. Experimental results show that the proposed method achieves a mean absolute error of 0.67-0.91 days for delayed-shipment predictions, outperforming single-step tree-based regression baselines by 41-64% and two-step classify-then-regress tree-based models by 15-35%. These gains demonstrate the effectiveness of the proposed model in operational delivery delay forecasting under highly imbalanced and heterogeneous conditions.

Problem

• delivery delay prediction
• imbalanced data
• supply chain
• logistics networks
• uncertainty-aware forecasting

Innovation

• multi-task deep learning
• delivery delay prediction
• imbalanced data
• uncertainty-aware forecasting
• embedding layers