Online air-ticket agent choice based on a multinomial logit model
YANG Xiaofang1,2, WANG Zhe1, JIANG Hai1
1. Department of Industrial Engineering, Tsinghua University, Beijing 100084, China;
2. Transportation Institute, Inner Mongolia University, Hohhot 010070, China
Abstract：The online air-ticket agent can significantly improve an air-ticket search system for online travel search engines. The paper analyzes the air-ticket agent behavior based on user air-ticket searches and booking data from an online travel search engine. A multinomial logit model is used to analyze the effects of the agents' quote, grades, value-added services, positions on the page and market shares to build a log-price multinomial logit model for user online air-ticket agent choices. The results show that the price quotes are the principal user concern and that including insurance and fewer raters lead to fear selections of the agent which value-added services and higher grades attract user attention. Users are more inclined to choose the agents showed on the front of the page and then the agents listed at the bottom. Agents with large market shares significantly influence the choice. Tests show that the predictions of this model are better than those using historical data.
杨晓芳, 王喆, 姜海. 基于多项logit模型的在线机票代理商选择行为[J]. 清华大学学报（自然科学版）, 2017, 57(4): 437-442.
YANG Xiaofang, WANG Zhe, JIANG Hai. Online air-ticket agent choice based on a multinomial logit model. Journal of Tsinghua University(Science and Technology), 2017, 57(4): 437-442.
Smyth B, Cotter P. A personalized TV listings service for the digital TV age[J]. Knowledge-Based Systems, 2000, 13(2-3)： 53-59.
[2]
Jansen B J, Spink A, Bateman J, et al. Real life information retrieval： A study of user queries on the web[J]. SIGIR Forum, 1998, 32(1)： 5-17.
[3]
Coldren G M, Koppelman F S, Kasturirangan K, et al. Air travel itinerary share prediction： Logit model development at a major US airline[J]. Journal of Air Transport Management, 2003, 9(6)： 361-369.
[4]
Coldren G M, Koppelman F S. Modeling the proximate covariance property of air travel itineraries along the time-of-day dimension[J]. Journal of the Transportation Research Board, 2005(1915)： 112-123.
[5]
Jiang H. A nested logit-based approach to measuring air shopping screen quality and predicting market share[J]. Journal of Revenue and Pricing Management, 2009, 8： 134-147.
[6]
Warburg V, Bhat C, Adler T. Modeling demographic and unobserved heterogeneity in air passenger's sensitivity to service attributes in itinerary choice[J]. Journal of the Transportation Research Board, 2006(1951)： 7-16.
[7]
Van Eggermond M, Schüessler N, Axhausen K W. Accounting for Similarities in Air Transport Route Choice[D]. Zürich： ETH, Eidgenössische Technische Hochschule Zürich, IVT, 2008.
[8]
Garrow L A, Jones S P, Parker R A. How much airline customers are willing to pay： An analysis of price sensitivity in online distribution channels[J]. Journal of Revenue and Pricing Management, 2007, 5(4)： 271-290.
[9]
梅虎. 航空旅客选择行为及其在收益管理中的应用研究[D]. 南京： 南京航空航天大学, 2007.MEI Hu. Research on Air Passenger Choice Behavior and Its Application to Revenue Management[D]. Nanjing： Nanjing University of Aeronautics and Astronautics, 2007. (in Chinese)
[10]
叶峰. 基于出行链的航空旅客选择行为研究[D]. 上海： 同济大学, 2008.YE Feng. Trip Chain Based Air Passenger Behavior Choice Research[D]. Shanghai： Tongji University, 2008. (in Chinese)
[11]
Ben-Akiva M, Lerman S. Discrete Choice Analysis： Theory and Application to Travel Demand[M]. Cambridge： MIT Press, 1985.
[12]
Train K E. Discrete Choice Methods with Simulation[M]. Cambridge： Cambridge University Press, 2003.
2017, Vol. 57 
