Due to the complexity of pricing in the service industry, it is important to provide an efficient pricing framework for real-life and large-sized applications. To this end, we combined an optimization approach with a regression-based machine learning method to provide a reliable and efficient framework for integrated pricing and train formation problem under hybrid uncertainty. To do so, firstly, a regression-based machine learning model is applied to forecast the ticket price of the passenger railway, and then, the obtained price in is used as the input of a train formation optimization model. Further, in order to deal with the hybrid uncertainty of demand parameters, a robust fuzzy stochastic programming model is proposed. Finally, a real transportation network from the Iran railway is applied to demonstrate the efficiency of the proposed model. The analysis of numerical results indicated that the proposed framework is able to state the optimal price with less complexity in comparison to traditional models.
Keywords: Regression-based machine learning, pricing, train formation problem, hybrid uncertainty, robust fuzzy stochastic programming
@article{RO_2022__56_3_1429_0,
author = {Yousefi, Atiye and Pishvaee, Mir Saman},
title = {A hybrid machine learning-optimization approach to pricing and train formation problem under demand uncertainty},
journal = {RAIRO. Operations Research},
pages = {1429--1451},
year = {2022},
publisher = {EDP-Sciences},
volume = {56},
number = {3},
doi = {10.1051/ro/2022052},
mrnumber = {4437997},
zbl = {1493.62016},
language = {en},
url = {https://www.numdam.org/articles/10.1051/ro/2022052/}
}
TY - JOUR AU - Yousefi, Atiye AU - Pishvaee, Mir Saman TI - A hybrid machine learning-optimization approach to pricing and train formation problem under demand uncertainty JO - RAIRO. Operations Research PY - 2022 SP - 1429 EP - 1451 VL - 56 IS - 3 PB - EDP-Sciences UR - https://www.numdam.org/articles/10.1051/ro/2022052/ DO - 10.1051/ro/2022052 LA - en ID - RO_2022__56_3_1429_0 ER -
%0 Journal Article %A Yousefi, Atiye %A Pishvaee, Mir Saman %T A hybrid machine learning-optimization approach to pricing and train formation problem under demand uncertainty %J RAIRO. Operations Research %D 2022 %P 1429-1451 %V 56 %N 3 %I EDP-Sciences %U https://www.numdam.org/articles/10.1051/ro/2022052/ %R 10.1051/ro/2022052 %G en %F RO_2022__56_3_1429_0
Yousefi, Atiye; Pishvaee, Mir Saman. A hybrid machine learning-optimization approach to pricing and train formation problem under demand uncertainty. RAIRO. Operations Research, Tome 56 (2022) no. 3, pp. 1429-1451. doi: 10.1051/ro/2022052
[1] , , and , Airline ticket price and demand prediction: a survey. J. King Saud Univ. – Comput. Inf. Sci. 33 (2021) 375–391.
[2] , and , Pricing commercial train path requests based on societal costs. Transp. Res. Part A 132 (2020) 452–464.
[3] , , and , Advanced evaluation of simultaneous train formation methods based on fuzzy compromise programing. E3S Web Conf. 135 (2019) 02026. | DOI
[4] , , and , Long-distance rail prices in a competitive market. Evidence from head-on competition in Italy. J. Rail Transp. Planning Manage. 12 100144. | DOI
[5] , and , Ticket sales prediction and dynamic pricing strategies in public transport. Big Data Cong. Comput. 4 (2020) 36.
[6] and , Investigation into train flow system on Ukraine’s railways with methods of complex network analysis. Am. J. Ind. Eng. 1 (2013) 41–45.
[7] , and , One-block train formation in large-scale railway networks: an exact model and a tree-based decomposition algorithm. Transp. Res. Part B Methodol. 118 (2018) 1–30. | DOI
[8] , , and , The effect of train formation length and service frequency on the determination of train schedules. Proc. Inst. Mech. Eng. Part F J. Rail Rapid Transit 228 (2014) 378–388. | DOI
[9] , , and , A novel robust fuzzy stochastic programming for closed loop supply chain network design under hybrid uncertainty. Fuzzy Sets Syst. 341 (2018) 69–91. | MR | Zbl | DOI
[10] , and , A robust fuzzy stochastic programming model for the design of a reliable green closed-loop supply chain network. Human Ecol. Risk Assess. Int. J. 23 (2017) 2119–2149. | DOI
[11] , and , Suboptimal pricing model and analysis of high-speed railway. J. Interdisciplinary Math. 20 (2017) 1203–1222. | DOI
[12] , and , Sub-time pricing model and effect analysis of high-speed railway. J. Discrete Math. Sci. Cryptography 20 (2017) 971–990. | Zbl | DOI
[13] , The effect of intermodal competition on the pricing behavior of a railway company: evidence from the German case. Res. Transp. Econ. 72 (2018) 49–64. | DOI
[14] and , A latent class choice-based model system for railway optimal pricing and seat allocation. Transp. Res. Part E 61 (2014) 68–83. | DOI
[15] , and , Pricing model of train passenger transport based on the value of travel time and bi-level programming. In: 20th International Conference on Management Science & Engineering. Harbin, P.R. China (2013) 393–399.
[16] and, , Predictive maintenance using machine learning and data mining: a pioneer method implemented to Greek railways. Designs 5 (2021) 5. | DOI
[17] , , , and , An optimization method of the multi-group train formation at flat yards. Int. J. Rail Transp. 9 (2021) 61–78. | DOI
[18] , and , A bi-level programming model for operative decisions on special trains: an Indian railways perspective. J. Rail Transp. Planning Manage. 8 (2018) 184–206. | DOI
[19] , , and , A robust optimization model for multi-site production planning problem in an uncertain environment. Eur. J. Oper. Res. 181 (2007) 224–238. | Zbl | DOI
[20] , Integrating car path optimization with train formation plan: a non-linear binary programming model and simulated annealing-based heuristics. Optim. Control Preprint (2017). | arXiv
[21] and , The systematic optimization of train formation in loading stations. Symmetry 11 (2019) 1238. | DOI
[22] , and , Passenger assignment and pricing strategy for a passenger railway transportation system. Transp. Lett. Int. J. Transp. Res. 11 (2019) 320–331. | DOI
[23] , , , , and , An optimization approach to the low-frequency entire train formation at the loading area. Sustainability 11 (2019) 5500. | DOI
[24] , , and , Integrating traffic routing optimization and train formation plan using simulated annealing algorithm. Appl. Math. Modell. 93 (2021) 811–830. | MR | Zbl | DOI
[25] , , , , Pricing of urban rail transit for different operation stages based on game theory. In: 2th IEEE International Conference on Information and Financial Engineering. Chongqing, China (2010) 17–19.
[26] and , Optimizing Efficiency of Electric Train Service (ETS) ticket pricing. In: Proceedings of the Second International Conference on the Future of ASEAN (ICoFA). Singapore (2018) 381–391.
[27] , and , Robust possibilistic programming for socially responsible supply chain network design: a new approach. Fuzzy Sets Syst. 206 (2012) 1–20. | MR | Zbl | DOI
[28] , and , Credibility-based fuzzy mathematical programming model for green logistics design under uncertainty. Comput. Ind. Eng. 62 (2012) 624–32. | DOI
[29] , A practical approach to revenue management in passenger train services: a case study of the Indonesian railways Argo Parahyangan. J. Rail Transp. Planning Manage. 13 (2020) 100161. | DOI
[30] , and , Railway passenger ticket pricing policy portfolio. In: International Conference on Logistics, Informatics and Service Sciences (LISS). Sydney, NSW, Australia (2016) 24–27.
[31] , , and , Deferential pricing strategies of high-speed railway based on prospect theory: an empirical study from China. Sustainability 11 (2019) 3804. | DOI
[32] , Statistical matching using file concatenation with adjusted weights and multiple imputations. J. Bus. Econ. Stat. 4 (1986) 87–94. | DOI
[33] and , Dynamic pricing of high-speed rail with transport competition. J. Revenue Pricing Manage. 11 (2012) 548–559. | DOI
[34] , The CRISP-DM Model: the new blueprint for data mining. J. Data Warehousing 5 (2000) 13–22.
[35] , and , Effect of high-speed rail competition on airlines’ intertemporal price strategies. J. Air Transp. Manage. 80 (2019) 101694. | DOI
[36] and , The Theory and Practice of Revenue Management. Springer, Boston (2005). | MR | Zbl
[37] , and , Humanitarian logistics network design under mixed uncertainty. Eur. J. Oper. Res. 250 (2016) 239–250. | MR | Zbl | DOI
[38] and , Congestion pricing in a road and rail network with heterogeneous values of time and schedule delay. Transp. A Transp. Sci. 10 (2014) 377–400.
[39] , Competition in Swedish passenger railway: entry in an open access market and its effect on prices. Econ. Transp. 11 (2017) 49–59. | DOI
[40] , Dynamic pricing considering strategic customers. In: 2016 International Conference on Logistics, Informatics and Service Sciences (LISS). Sydney, NSW (2016) 1–5.
[41] , , and , Effects of train speed on airline demand and price: theory and empirical evidence from a natural experiment. Transp. Res. Part B 114 (2018) 99–130. | DOI
[42] , , , and , Collaborative optimization of dynamic pricing and seat allocation for high-speed railways: an empirical study from China. IEEE Access 7 (2019) 139409–139419. | DOI
[43] and , Comprehensive optimization of the one-block and two-block train formation plan. J. Rail Transp. Planning Manage. 6 (2016) 218–236. | DOI
[44] , and , Solving the train formation plan network problem of the single-block train and two-block train using a hybrid algorithm of genetic algorithm and tabu search. Transp. Res. Part C: Emerg. Technol. 86 (2018) 124–146. | DOI
[45] , and , Dynamic pricing for passenger groups of high-speed rail transportation. J. Rail Transp. Planning Manage. 6 (2017) 346–356. | DOI
[46] and , Research on the bi-level programming model for ticket fare pricing of urban rail transit based on particle swarm optimization algorithm. Proc. Soc. Behav. Sci. 96 (2013) 633–642. | DOI
[47] , and , An improved local branching approach for train formation planning. Appl. Math. Modell. 37 (2013) 2300–2307. | MR | Zbl | DOI
[48] , and , Solving train formation problem using simulated annealing algorithm in a simplex framework. J. Adv. Transp. 48 (2014) 402–416. | DOI
[49] , and , A hybrid solution method for fuzzy train formation planning. Appl. Soft Comput. 31 (2015) 257–265. | DOI
[50] , and , Collaborative optimization of resource capacity allocation and fare rate for high-speed railway passenger transport. J. Rail Transp. Planning Manage. 10 (2020) 23–33. | DOI
[51] and , Applying price and time differentiation to modeling cabin choice in high-speed rail. Transp. Res. Part E 47 (2011) 73–84. | DOI
[52] and , Effects of high-speed rail and air transport competition on prices, profits and welfare. Transp. Res. Part B 46 (2012) 1322–1333. | DOI
[53] and , A fuzzy optimization approach to integration of physical and financial flows in a global supply chain under exchange rate uncertainty. Int. J. Fuzzy Syst. 20 (2018) 2415–2439. | MR | DOI
[54] and , Estimating the demand for rail freight transport in Pakistan: a time series analysis. J. Rail Transp. Planning Manage. 14 (2020) 100176. | DOI
[55] and , An integrated planning/pricing decision model for rail container transportation. Int. J. Civil Eng. 17 (2019) 1537–1546. | DOI
[56] , , and , Competition of airline and high-speed rail in terms of price and frequency: empirical study from China. Transp. Policy 78 (2019) 8–18. | DOI
[57] , , , and , Integrated optimization of train formation plan and rolling stock scheduling with multiple turnaround operations under uneven demand in an urban rail transit line. In: 23rd International Conference on Intelligent Transportation Systems (ITSC). Rhodes, Greece (2020) 1–6.
Cité par Sources :
