Deep Learning and Statistical Models for Forecasting Transportation Demand: A Case Study of Multiple Distribution Centers

Fábio Polola Mamede (), Roberto Fray da Silva, Irineu de Brito Junior, Hugo Tsugunobu Yoshida Yoshizaki, Celso Mitsuo Hino and Carlos Eduardo Cugnasca
Additional contact information
Fábio Polola Mamede: Graduate Program in Logistics Systems Engineering, University of São Paulo, São Paulo 05508-010, Brazil
Roberto Fray da Silva: Institute of Advanced Studies, University of São Paulo, São Paulo 05508-010, Brazil
Irineu de Brito Junior: Graduate Program in Logistics Systems Engineering, University of São Paulo, São Paulo 05508-010, Brazil
Hugo Tsugunobu Yoshida Yoshizaki: Graduate Program in Logistics Systems Engineering, University of São Paulo, São Paulo 05508-010, Brazil
Celso Mitsuo Hino: Department of Production Engineering, University of São Paulo, São Paulo 05508-010, Brazil
Carlos Eduardo Cugnasca: Graduate Program in Logistics Systems Engineering, University of São Paulo, São Paulo 05508-010, Brazil

Logistics, 2023, vol. 7, issue 4, 1-19

Abstract: Background : Transportation demand forecasting is an essential activity for logistics operators and carriers. It leverages business operation decisions, infrastructure, management, and resource planning activities. Since 2015, there has been an increase in the use of deep learning models in this domain. However, there is a gap in works comparing traditional statistics and deep learning models for transportation demand forecasts. This work aimed to perform a case study of aggregated transportation demand forecasts in 54 distribution centers of a Brazilian carrier. Methods : A computational simulation and case study methods were applied, exploring the characteristics of the datasets through autoregressive integrated moving average (ARIMA) and its variations, in addition to a deep neural network, long short-term memory, known as LSTM. Eight scenarios were explored while considering different data preprocessing methods and evaluating how outliers, training and testing dataset splits during cross-validation, and the relevant hyperparameters of each model can affect the demand forecast. Results : The long short-term memory networks were observed to outperform the statistical methods in ninety-four percent of the dispatching units over the evaluated scenarios, while the autoregressive integrated moving average modeled the remaining five percent. Conclusions : This work found that forecasting transportation demands can address practical issues in supply chains, specially resource planning management.

Keywords: transportation demand forecasting; supply chain management; LSTM; ARIMA; data preprocessing (search for similar items in EconPapers)
JEL-codes: L8 L80 L81 L86 L87 L9 L90 L91 L92 L93 L98 L99 M1 M10 M11 M16 M19 R4 R40 R41 R49 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2305-6290/7/4/86/pdf (application/pdf)
https://www.mdpi.com/2305-6290/7/4/86/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jlogis:v:7:y:2023:i:4:p:86-:d:1285024

Access Statistics for this article

Logistics is currently edited by Ms. Mavis Li

More articles in Logistics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().