Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (5): 1616-1623.DOI: 10.11772/j.issn.1001-9081.2021030504
• Frontier and comprehensive applications • Previous Articles Next Articles
Youzhi LI, Zhihua HU(), Chun CHEN, Peibei YANG, Yajing DONG
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.Supported by:
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、机器学习基金资助:
CLC Number:
Youzhi LI, Zhihua HU, Chun CHEN, Peibei YANG, Yajing DONG. Prediction model of transaction pricing in internet freight transport platform based on combination of dual long short-term memory networks[J]. Journal of Computer Applications, 2022, 42(5): 1616-1623.
李由之, 胡志华, 陈春, 杨培蓓, 董雅静. 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[J]. 《计算机应用》唯一官方网站, 2022, 42(5): 1616-1623.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2021030504
订单序号 | 任务id | 总里程/km | 线路总成本/元 | 线路不含税指导价/元 | 交易对象 | … | 线路不含税成交价格/元 |
---|---|---|---|---|---|---|---|
1 | 4 713 | 45 | 281.82 | 282 | 1 | … | 238 |
2 | 4 721 | 144 | 672.47 | 672 | 1 | … | 1 010 |
3 | 4 722 | 144 | 681.23 | 681 | 1 | … | 1 100 |
4 | 4 724 | 144 | 681.23 | 681 | 1 | … | 1 100 |
Tab. 1 Partial platform dataset of historical orders after preprocessing
订单序号 | 任务id | 总里程/km | 线路总成本/元 | 线路不含税指导价/元 | 交易对象 | … | 线路不含税成交价格/元 |
---|---|---|---|---|---|---|---|
1 | 4 713 | 45 | 281.82 | 282 | 1 | … | 238 |
2 | 4 721 | 144 | 672.47 | 672 | 1 | … | 1 010 |
3 | 4 722 | 144 | 681.23 | 681 | 1 | … | 1 100 |
4 | 4 724 | 144 | 681.23 | 681 | 1 | … | 1 100 |
参数 | 值 |
---|---|
输入张量(input_shape) | (1,163) |
输入层神经元数 | 24 |
输入层激活函数 | tanh |
隐藏层 | 2 |
隐藏层神经元数 | 12 |
输出层神经元数 | 1 |
训练轮次(epochs) | 100 |
批量大小(batch_size) | 8 |
Tab. 2 Parameter setting of combination model of dual LSTM
参数 | 值 |
---|---|
输入张量(input_shape) | (1,163) |
输入层神经元数 | 24 |
输入层激活函数 | tanh |
隐藏层 | 2 |
隐藏层神经元数 | 12 |
输出层神经元数 | 1 |
训练轮次(epochs) | 100 |
批量大小(batch_size) | 8 |
模型 | R2 | MAE | MSE | MAPE/% | MAPE/%* |
---|---|---|---|---|---|
双LSTM | 0.999 97 | 9.90 | 402.54 | 1.48 | 1.27 |
LSTM | 0.999 12 | 21.21 | 11 519.69 | 1.64 | 1.39 |
SVR | 0.996 68 | 122.79 | 42 983.60 | 24.73 | 24.70 |
LASSO | 0.969 88 | 269.71 | 315 963.66 | 42.78 | 17.60 |
ELM | 0.991 55 | 181.40 | 108 324.93 | 36.28 | 34.86 |
Tab. 3 Experimental results of evaluation indicators between combination model of dual LSTM and single models
模型 | R2 | MAE | MSE | MAPE/% | MAPE/%* |
---|---|---|---|---|---|
双LSTM | 0.999 97 | 9.90 | 402.54 | 1.48 | 1.27 |
LSTM | 0.999 12 | 21.21 | 11 519.69 | 1.64 | 1.39 |
SVR | 0.996 68 | 122.79 | 42 983.60 | 24.73 | 24.70 |
LASSO | 0.969 88 | 269.71 | 315 963.66 | 42.78 | 17.60 |
ELM | 0.991 55 | 181.40 | 108 324.93 | 36.28 | 34.86 |
模型 | R2 | MAE | MSE | MAPE/% | MAPE/%* |
---|---|---|---|---|---|
LSTM-SVR | 0.999 23 | 33.36 | 10 041.56 | 6.16 | 6.17 |
GM(1,1)-BP | 0.999 67 | 30.12 | 4 236.59 | 4.15 | 6.69 |
双LSTM | 0.999 97 | 9.90 | 402.54 | 1.48 | 1.27 |
Tab. 4 Experimental results of evaluation indicators between combination model of dual LSTM and other combination models
模型 | R2 | MAE | MSE | MAPE/% | MAPE/%* |
---|---|---|---|---|---|
LSTM-SVR | 0.999 23 | 33.36 | 10 041.56 | 6.16 | 6.17 |
GM(1,1)-BP | 0.999 67 | 30.12 | 4 236.59 | 4.15 | 6.69 |
双LSTM | 0.999 97 | 9.90 | 402.54 | 1.48 | 1.27 |
等级 | 成交定价范围 | 占比/% | 说明 |
---|---|---|---|
1 | [113,360] | 33.0 | 订单容易完成 |
2 | (360,540] | 1.0 | 订单较容易完成 |
3 | (540,868] | 18.3 | 订单完成难度中等 |
4 | (868,8 225] | 41.4 | 订单较难完成 |
5 | (8 225,20 539] | 6.3 | 订单非常难完成 |
Tab. 5 Classification standard and order proportion of transaction pricing
等级 | 成交定价范围 | 占比/% | 说明 |
---|---|---|---|
1 | [113,360] | 33.0 | 订单容易完成 |
2 | (360,540] | 1.0 | 订单较容易完成 |
3 | (540,868] | 18.3 | 订单完成难度中等 |
4 | (868,8 225] | 41.4 | 订单较难完成 |
5 | (8 225,20 539] | 6.3 | 订单非常难完成 |
1 | 刘德智,张柳叶.考虑可靠性的无车承运平台信息共享价值研究[J].数学的实践与认识,2020,50(7):136-146. |
LIU D Z, ZHANG L Y. Research on information sharing value of non-truck operating common carrier considering reliability [J]. Mathematics in Practice and Theory, 2020, 50(7): 136-146. | |
2 | 高博,史言,李玮.典型地区推动无车承运人发展的经验比对研究[J].综合运输,2018,40(8):111-113. |
GAO B, SHI Y, LI W. Comparative study of typical region transport departments promoting the development of truck broker experience [J]. China Transportation Review, 2018, 40(8): 111-113. | |
3 | 李博,白冰峰.基于平台经济理论视角的网络货运平台研究综述[J].供应链管理,2021,2(2):121-127. |
LI B, BAI B F. A literature review of online freight transport platforms based on the perspective of platform economy theory [J]. Supply Chain Management, 2021, 2(2): 121-127. | |
4 | 贺政纲,杨晓蕾,贾艳丽.基于无车承运的多式联运流线网络匹配研究[J].交通运输系统工程与信息,2018,18(6):236-242. 10.16097/j.cnki.1009-6744.2018.06.033 |
HE Z G, YANG X L, JIA Y L. Construction of intermodality streamline network matching based on the “carrier broker” [J]. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(6): 236-242. 10.16097/j.cnki.1009-6744.2018.06.033 | |
5 | 尤美虹,骆温平,陶君成.无车承运人及货运平台监管调查分析[J].中国流通经济,2019,33(8):45-53. 10.14089/j.cnki.cn11-3664/f.2019.08.005 |
YOU M H, LUO W P, TAO J C. Investigation and analysis on supervision on NTOCC and freight platform [J]. China Business and Market, 2019, 33(8): 45-53. 10.14089/j.cnki.cn11-3664/f.2019.08.005 | |
6 | 王蓓蓓,崔杰.公路货运车货匹配研究综述[J].价值工程,2019,38(17):282-284. |
WANG B B, CUI J. Research overview of highway freight vehicle cargo matching [J]. Value Engineering, 2019, 38(17): 282-284. | |
7 | 聂福海,李电生.不对称信息下无车承运人平台定价策略研究[J].工业工程与管理,2020,25(5):121-128. |
NIE F H, LI D S. Study of pricing strategies for non-car operating carriers platform under asymmetric information [J]. Industrial Engineering and Management, 2020, 25(5): 121-128. | |
8 | 程静,桂云苗.考虑匹配率的物流O2O平台定价研究[J].安徽工程大学学报,2020,35(2):70-77. 10.3969/j.issn.2095-0977.2020.02.011 |
CHENG J, GUI Y M. Research on logistics O2O platform pricing considering matching rate [J]. Journal of Anhui Polytechnic University, 2020, 35(2): 70-77. 10.3969/j.issn.2095-0977.2020.02.011 | |
9 | LI J B, ZHENG Y T, DAI B, et al. Implications of matching and pricing strategies for multiple-delivery-points service in a freight O2O platform [J]. Transportation Research Part E: Logistics and Transportation Review, 2020, 136(4): Article No.101871. 10.1016/j.tre.2020.101871 |
10 | HURLEY W J, PETERSEN E R. Optimal freight transport pricing and the freight network equilibrium problem [M]// BIANCO L, TOTH P. Advanced Methods in Transportation Analysis. Berlin: Springer, 1996: 389-412. 10.1007/978-3-642-85256-5_18 |
11 | CLARKE S M, GRIEBSCH J H, SIMPSON T W. Analysis of support vector regression for approximation of complex engineering analyses [J]. Journal of Mechanical Design, 2005, 127(6): 1077-1087. 10.1115/1.1897403 |
12 | TU J V. Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes [J]. Journal of Clinical Epidemiology, 1996, 49(11): 1225-1231. 10.1016/s0895-4356(96)00002-9 |
13 | MARTÍNEZ-MARTÍNEZ J M, ESCANDELL-MONTERO P, SORIA-OLIVAS E, et al. Regularized extreme learning machine for regression problems [J]. Neurocomputing, 2011, 74(17):3716-3721. 10.1016/j.neucom.2011.06.013 |
14 | XIONG Z Y, SU Y K. Dynamic game pricing model of car-free carrier platform based on GA-BP theory [J]. Journal of Physics: Conference Series, 2020, 1629: Article No.12053. 10.1088/1742-6596/1629/1/012053 |
15 | ZHAO J L, QU H, ZHAO J H, et al. Towards traffic matrix prediction with LSTM recurrent neural networks [J]. Electronics Letters, 2018, 54(9): 566-568. 10.1049/el.2018.0336 |
16 | 熊红林,冀和,樊重俊,等.基于LSTM-SVR模型的航空旅客出行指数预测[J].系统管理学报,2020,29(6):1169-1176. |
XIONG H L, JI H, FAN C J, et al. Forecast of travel index of air passengers based on LSTM-SVR model [J]. Journal of Systems and Management, 2020, 29(6): 1169-1176. | |
17 | GERS F A, SCHMIDHUBER E. LSTM recurrent networks learn simple context-free and context-sensitive languages [J]. IEEE Transactions on Neural Networks, 2001, 12(6): 1333-1340. 10.1109/72.963769 |
18 | 孙轶轩,邵春福,计寻,等.基于ARIMA与信息粒化SVR组合模型的交通事故时序预测[J].清华大学学报(自然科学版),2014,54(3):348-353,359. |
SUN Y X, SHAO C F, JI X, et al. Urban traffic accident time series prediction model based on combination of ARIMA and information granulation SVR [J]. Journal of Tsinghua University (Science and Technology), 2014, 54(3): 348-353, 359. | |
19 | GREFF K, SRIVASTAVA R K, KOUTNÍK J, et al. LSTM: a search space odyssey [J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(10): 2222-2232. 10.1109/tnnls.2016.2582924 |
20 | ZHAO C Y, ZHANG H X, ZHANG X Y, et al. Application of Support Vector Machine (SVM) for prediction toxic activity of different data sets [J]. Toxicology, 2006, 217(2/3): 105-119. 10.1016/j.tox.2005.08.019 |
21 | LU Y M, ROYCHOWDHURY V. Parallel randomized sampling for Support Vector Machine (SVM) and Support Vector Regression (SVR) [J]. Knowledge and Information Systems, 2008, 14(2): 233-247. 10.1007/s10115-007-0082-6 |
22 | ZOU H. The adaptive lasso and its oracle properties [J]. Journal of the American Statistical Association, 2006, 101(476): 1418-1429. 10.1198/016214506000000735 |
23 | HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: theory and applications [J]. Neurocomputing, 2006, 70(1/2/3): 489-501. 10.1016/j.neucom.2005.12.126 |
24 | 王宇胜,陈德旺,蔡俊鹏,等.基于LSTM-SVR的锂电池健康状态预测研究[J].电源技术,2020,44(12):1784-1787. 10.3969/j.issn.1002-087X.2020.12.019 |
WANG Y S, CHEN D W, CAI J P, et al. Research on lithium battery state of health prediction based on LSTM-SVR [J]. Chinese Journal of Power Sources, 2020, 44(12): 1784-1787. 10.3969/j.issn.1002-087X.2020.12.019 | |
25 | 李德营,殷坤龙.基于影响因子的GM(1,1)-BP模型在八字门滑坡变形预测中的应用[J].长江科学院院报,2013,30(2):6-11. 10.3969/j.issn.1001-5485.2013.02.002 |
LI D Y, YIN K L. Application of GM(1,1)-BP model to the deformation prediction of Bazimen landslide in consideration of influencing factors [J]. Journal of Yangtze River Scientific Research Institute, 2013, 30(2): 6-11. 10.3969/j.issn.1001-5485.2013.02.002 |
[1] | Fangxing GENG, Zhuo LI, Xin CHEN. Incentive mechanism design for hierarchical federated learning based on multi-leader Stackelberg game [J]. Journal of Computer Applications, 2023, 43(11): 3551-3558. |
[2] | Hexuan HU, Huachao SUI, Qiang HU, Ye ZHANG, Zhenyun HU, Nengwu MA. Runoff forecast model based on graph attention network and dual-stage attention mechanism [J]. Journal of Computer Applications, 2022, 42(5): 1607-1615. |
[3] | DING Yin, SANG Nan, LI Xiaoyu, WU Feizhou. Prediction method of capacity data in telecom industry based on recurrent neural network [J]. Journal of Computer Applications, 2021, 41(8): 2373-2378. |
[4] | GAO Yilu, HU Zhihua. Path planning for automated guided vehicles based on tempo-spatial network at automated container terminal [J]. Journal of Computer Applications, 2020, 40(7): 2155-2163. |
[5] | WANG Lilin, LIU Jun. Ship behavior recognition method based on multi-scale convolution [J]. Journal of Computer Applications, 2019, 39(12): 3691-3696. |
[6] | WEI Xin, WU Shuhong, WANG Yaoli. Forest fire smoke detection model based on deep convolution long short-term memory network [J]. Journal of Computer Applications, 2019, 39(10): 2883-2887. |
[7] | MA Shugang, YANG Jianhua. Cloud manufacturing service resource combination optimization model and algorithm under group buying mode [J]. Journal of Computer Applications, 2015, 35(8): 2147-2152. |
[8] | . Random load oriented pricing strategy for resource reservation in computational grid [J]. Journal of Computer Applications, 2009, 29(06): 1711-1727. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||