Toward Reducing Unproductive Container Moves: Predicting Service Requirements and Dwell Times

Elena Villalobos; Adolfo De Unánue T.; Fernanda Sobrino; David Aké; Stephany Cisneros; Jorge Lecona; Alejandra Matadamaz

cs.AIApr 6, 2026

Toward Reducing Unproductive Container Moves: Predicting Service Requirements and Dwell Times

Authors: Elena Villalobos, Adolfo De Unánue T., Fernanda Sobrino, David Aké, Stephany Cisneros, Jorge Lecona, Alejandra Matadamaz

Organizations: Tecnológico de Monterrey, Mexico City, Mexico · Centro de Ciencia de Datos e Inteligencia Artificial School of Government and Public Transformation Tecnológico de Monterrey Mexico City, Mexico · Container Terminal Operations, Veracruz, Mexico · Container Terminal Operations Veracruz, Mexico

Abstract

This article presents the results of a data science study conducted at a container terminal, aimed at reducing unproductive container moves through the prediction of service requirements and container dwell times. We develop and evaluate machine learning models that leverage historical operational data to anticipate which containers will require pre-clearance handling services prior to cargo release and to estimate how long they are expected to remain in the terminal. As part of the data preparation process, we implement a classification system for cargo descriptions and perform deduplication of consignee records to improve data consistency and feature quality. These predictive capabilities provide valuable inputs for strategic planning and resource allocation in yard operations. Across multiple temporal validation periods, the proposed models consistently outperform existing rule-based heuristics and random baselines in precision and recall. These results demonstrate the practical value of predictive analytics for improving operational efficiency and supporting data-driven decision-making in container terminal logistics.

Figures & tables

Dwell Time Label	Cumulative Percentage	Label Percentage
1	8%	8%
2	18.36%	10%
3	30.60%	12%
4	42%	12%
5	54.07%	12%
6	64.27%	10%

Table 1: Baserate dwell-time distribution over the study period.

Variable
Net weight	Container dimension
Gross weight	Container type
Hazardous cargo indicator	Cargo type
Liner client (yes/no)	Shipping line
Consignee*	Shipping line route
Chapter and section**

Table 2: Base variables available prior to container arrival.

Category	Description
Simple variables	Directly available from base container information, 24 hours prior to arrival.
Simple counts	Frequency of occurrence of specific variables within a defined time window.
Aggregated metrics	Ratios, proportions, and relationships between counts across temporal spans.
Differences	Temporal variations, percentage changes, and dispersion measures between periods.
Service	Frequency of services by consignee, chapter, or shipping line over time.
Dwell time	Descriptive statistics derived from historical container departure records.

Table 3: Feature categories and descriptions.

Task	Best Model	Precision	Recall	vs. Baseline
Service ( $k=300$ )	Random Forest	75%	100%	+50 pp
Dwell time $<$ 2 days	Random Forest	30–40%	80%	+50 pp
Dwell time 3–6 days	Random Forest	$<$ 25%	$<$ 40%	+15 pp
Dwell time $>$ 7 days	Random Forest	80%	90%	+40 pp

Table 4: Summary of key results across prediction tasks.

Figure 2: Weekly average precision and recall for the service label across the main evaluated models. The upper panel displays precision@k , while the lower one shows recall@k .

Figure 3: Precision and recall for different $k$ values under varying service area capacities.

Figure 4: Weekly average precision and recall for dwell times of less than two days.

Figure 5: Weekly average precision and recall for containers with a dwell time of exactly five days. This label is used as a representative case for intermediate dwell-time categories (three, four, six, and seven days).

Figure 6: Weekly average precision and recall for dwell times longer than seven days.

Figure 7: Average precision and recall of the best-performing models across dwell-time labels.

Figure 8: Correct and incorrect classifications by dwell-time category on a typical operational day.

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Algorithm	Hyperparameter	Values tested
DecisionTreeClassifier	criterion	gini
	max_depth	5, 10, 50
	min_samples_split	10, 50, 100
RandomForestClassifier	n_estimators	200, 300
	criterion	gini
	max_depth	5, 10

Appendix

Table 5: Summary of evaluated algorithms and hyperparameter configurations.

Figure 9: Jaccard similarity matrix across dwell-time labels.

Supply Chain Management

Supply chain management coordinates sourcing, production, inventory, and delivery to balance cost, service, resilience, and sustainability.

See all 73 papers

Uncertainty-Aware Delivery Delay Duration Prediction via Multi-Task Deep Learning
Feb 23, 2026Stefan Faulkner, Reza Zandehshahvar, Vahid Eghbal Akhlaghi +3Supply Chain Management Multi-Task Learning
NSF Artificial Intelligence Institute for Advances in Optimization, H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA · Kinaxis
An Integrated Forecasting Prototype for Emergency Department Boarding Time to Support Proactive Operational Decision Making
May 13, 2026Orhun Vural, Abdulaziz Ahmed, Ferhat Zengul +2Time Series Forecasting
Department of Electrical and Computer Engineering, University of Alabama at Birmingham, Birmingham, AL, USA · Department of Health Services Administration, University of Alabama at Birmingham, Birmingham, AL, USA · Department of Biomedical Informatics and Data Science, Heersink School of Medicine, University of Alabama at Birmingham, Birmingham, AL, USA +1
Travel Time Prediction in Supply Chain Management Using Machine Learning
Sep 5, 2026Balaji VenkateswaranSupply Chain Management
Swiss School of Business and Management, Geneva

Feb 23, 2026J/K move · Enter open · S save

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

Stefan Faulkner, Reza Zandehshahvar, Vahid Eghbal Akhlaghi, Sebastien Ouellet+2

NSF Artificial Intelligence Institute for Advances in Optimization, H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA · Kinaxis

Supply Chain Management Multi-Task Learning

Open paper AskPDF arXiv

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.

Abstract

Supply Chain Management

Explore similar work

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

An Integrated Forecasting Prototype for Emergency Department Boarding Time to Support Proactive Operational Decision Making

Travel Time Prediction in Supply Chain Management Using Machine Learning