Deep Learning-Based Demand Forecasting for Korean Postal Delivery Service

Lkhagvadorj Munkhdalai,Kwang Ho Park,Erdenebileg Batbaatar,Nipon Theera-Umpon,Keun Ho Ryu

doi:10.1109/access.2020.3030938

Lkhagvadorj Munkhdalai, Kwang Ho Park + Show 3 more

Open Access

PDF Available

https://doi.org/10.1109/access.2020.3030938

Copy DOI

Export

Save

Cite

Journal: IEEE Access	Publication Date: Jan 1, 2020
Citations: 13	License type: CC BY 4.0

Affiliation: Chungbuk National University, Chiang Mai University

Abstract
Highlights/Summary
Full-Text PDF
Similar Papers

Abstract

Listen

Proper demand forecasting for postal delivery service can be used for optimal logistic management, staff scheduling and topology planning. More especially, during special holidays, such as the Lunar New Year and the Chuseok (Mid-autumn day), the demand for delivery service increases sharply in South Korea. It makes a challenge to forecast demand to provide a normal delivery schedule for the Korean mail center. To address this problem, we propose a novel deep learning model equipped with selection and update layers (MLP-SUL) to achieve high predictive performance. The proposed model consists of three main parts: the first part of the model learns to generate context-dependent weights to decide which input feed to the next layer; the second part updates the weighted input to prepare encoded input, and the third part is a prediction layer that consists of a linear layer. A linear layer takes encoded input for forecasting demand. We also introduce a special data preprocessing step for our task that requires long-term forecasting. The experimental results show that our proposed deep learning model outperforms state-of-the-art baselines on Korean mail center datasets.

Highlights

Accurate postal demand forecasting is a key role in deciding how to allocate resources efficiently for its distribution
This work proposes a deep learning model to forecast the demand for postal delivery service to obtain better predictive accuracy
We propose model equipped with selection and update layers (MLP-SUL), a novel deep learning-based time series forecasting model consisting of the selection and updating layers

Summary

Introduction

Accurate postal demand forecasting is a key role in deciding how to allocate resources efficiently for its distribution. During special holidays, such as the Lunar New Year and the Chuseok (Mid-autumn day) in South Korea, the demand for delivery service extremely increases. At this point, in order to provide the normal operation of the postal delivery service, one of the most important issues is to accurately predict the demand [1]. This work proposes a deep learning model to forecast the demand for postal delivery service to obtain better predictive accuracy. Our task is slightly different from the traditional time series forecasting, which is to forecast the long-term demand for postal delivery service during special holidays.

Objectives

Methods

Findings

Conclusion