《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (5): 1616-1623.DOI: 10.11772/j.issn.1001-9081.2021030504

• 前沿与综合应用 • 上一篇    下一篇

基于双长短期记忆网络组合的网络货运平台成交定价预测模型

李由之, 胡志华(), 陈春, 杨培蓓, 董雅静   

  1. 上海海事大学 物流研究中心,上海 201306
  • 收稿日期:2021-04-02 修回日期:2021-07-07 接受日期:2021-07-07 发布日期:2022-06-11 出版日期:2022-05-10
  • 通讯作者: 胡志华
  • 作者简介:李由之(1998—),女,湖南娄底人,硕士研究生,主要研究方向:供应链管理、机器学习
    胡志华(1977—),男,湖南长沙人,教授,博士,主要研究方向:物流管理 541847747@qq.com
    陈春(1994—),男,安徽安庆人,硕士研究生,主要研究方向:物流管理
    杨培蓓(1996—),女,江苏南通人,硕士研究生,主要研究方向:物流管理
    董雅静(1998—),女,浙江台州人,硕士研究生,主要研究方向:博弈论。
  • 基金资助:
    国家自然科学基金资助项目(71871136)

Prediction model of transaction pricing in internet freight transport platform based on combination of dual long short-term memory networks

Youzhi LI, Zhihua HU(), Chun CHEN, Peibei YANG, Yajing DONG   

  1. Logistics Research Center,Shanghai Maritime University,Shanghai 201306,China
  • Received:2021-04-02 Revised:2021-07-07 Accepted:2021-07-07 Online:2022-06-11 Published:2022-05-10
  • Contact: Zhihua HU
  • About author:LI Youzhi, born in 1998,M. S. candidate. Her research interestsinclude supply chain management,machine learning.
    HU Zhihua, born in 1977, Ph. D., professor. His researchinterests include logistics management.
    CHEN Chun, born in 1994, M. S. candidate. His researchinterests include logistics management.
    YANG Peibei, born in 1996, M. S. candidate. Her researchinterests include logistics management.
    DONG Yajing, born in 1998,M. S. candidate. Her researchinterests include game theory.
  • Supported by:
    National Natural Science Foundation of China(71871136)

摘要:

网络货运平台运输服务订单的成交定价的预测结果是平台运营策略和承运人决策的直接体现,显著影响平台效益和承运人市场健康发展。以顺丰速递网络货运平台为例,通过缺失值处理和类别型数据转换进行数据预处理。针对网络货运平台成交定价预测精度问题,设计了基于双长短期记忆网络(LSTM)组合的网络货运平台成交定价预测模型,并采用K-means聚类分析预测结果。双LSTM组合模型相较于LSTM、支持向量回归(SVR)、两者相融合的LSTM-SVR以及基于灰色GM(1,1)和反向传播(BP)组合(GM(1,1)-BP)等模型,平均绝对误差(MAE)、均方误差(MSE)、平均绝对百分比误差(MAPE)最低且R2最高,分别为9.90、402.54、1.48和0.999 97。而K-means聚类分析对预测的订单成交定价进行评级的结果与实际情况一致。实验结果表明,所提出的双LSTM组合模型具备有效性和准确的网络货运平台成交定价预测效果。

关键词: 网络货运平台, 定价策略, 长短期记忆网络, K-means聚类分析, 物流管理

Abstract:

Prediction results of transaction pricing of transport service orders in internet freight transport platform are the direct reflections of both platform operation strategy and carrier decision, and influences both platform benefits and the healthy development of carrier market significantly. Taking internet freight transport platform of SF Express network as an example, the data were preprocessed through missing value processing and categorical data conversion. Aiming at the prediction precision problem of transaction pricing in internet freight transport platform, a new prediction model of transaction pricing in internet freight transport platform based on combination of dual Long Short-Term Memory networks(LSTM) was designed, and the prediction results were analyzed by K-means clustering. Compared with the models such as LSTM, Support Vector Regression (SVR), Long Short-Term-Memory combined with Support Vector Regression (LSTM-SVR), and combination of grey GM(1,1) and Back Propagation (BP) (GM(1,1)-BP), the combination model of dual LSTM has the lowest Mean Absolute Error (MAE), Mean Square Error (MSE), Mean Absolute Percentage Error (MAPE) and highest R square (R2), which is 9.90, 402.54, 1.48 and 0.999 97 respectively. The evaluation results of predicted order transaction pricing by using K-means clustering analysis are consistent with the actual values. Experimental results indicate that, the proposed combination model of dual LSTM has effectiveness and precise prediction effect of transaction pricing in internet freight transport platform.

Key words: internet freight transport platform, pricing strategy, Long Short-Term Memory network (LSTM), K-means clustering analysis, logistics management

中图分类号: