رویکردهای همسایگی جدید در الگوریتم ممتیک برای یافتن نوع مشتری
محورهای موضوعی : مهندسی کامپیوتر و فناوری اطلاعات
حامد شرافت مولا
1
(گروه مهندسی کامپیوتر، واحد یاسوج، دانشگاه آزاد اسلامی، یاسوج، ایران)
هادی یعقوبیان
2
(گروه مهندسی کامپیوتر، واحد یاسوج، دانشگاه آزاد اسلامی، یاسوج، ایران)
راضیه ملک حسینی
3
(گروه مهندسی کامپیوتر، واحد یاسوج، دانشگاه آزاد اسلامی، یاسوج، ایران)
کرم الله باقری فرد
4
(گروه مهندسی کامپیوتر ، واحد یاسوج، دانشگاه آزاد اسلامی، یاسوج، ایران)
کلید واژه: مدیریت درآمد, الگوریتم‌های فراابتکاری, الگوریتم ژنتیک, الگوریتم ممتیک,
چکیده مقاله :
سیستم‌های «مدیریت سود» امروزه به‌صورت فراوان در صنایع مختلفی استفاده می‌شوند. یکی از پایه‌های اصلی مدیریت سود، «برآورد تقاضا» است که بر اساس آن تقاضای محصولات و خدمات پیش‌بینی می‌شود. شناخت مشتریان و علایق آنها زیربنای برآورد تقاضاست و این شناخت با حل مسئله «کشف نوع مشتری» به‌دست می‌آید. به تازگی این مسئله با استفاده از روش فراابتکاری «ژنتیک» حل‌شده¬است و در این تحقیق با استفاده از رویکردهایی دیگر برای یافتن همسایگی، این مسئله را با روش فراابتکاری «ممتیک» حل خواهیم¬کرد. برای ارزیابی تحقیق خود، از داده‌های واقعی پنج هتل استفاده خواهیم¬کرد و در ادامه نشان می‌دهیم که روش پیشنهادی درمجموع با 10.5 درصد تعداد نسل کمتر نسبت به روش «ژنتیک» اولین راه‌حل قابل‌قبول مسئله را ارائه می‌دهد.
"Revenue management" systems are extensively utilized across various industries today. One of the primary pillars of revenue management lies in demand estimation, which predicts the demand for products and services. Understanding customers and their preferences forms the cornerstone of demand estimation, and this understanding is acquired through solving the "customer type discovery" problem. Recently, this problem has been addressed using the "genetic" meta-heuristic method. In this research, we propose solving this problem utilizing the "memetic" meta-heuristic method, employing alternative approaches to identify the neighborhood. By evaluating real data from five hotels, we demonstrate that our method offers the first viable solution to the problem, resulting in a total of 10.5% fewer iterations compared to the "genetic" method.
[1] K. T. Talluri and G. J. Van Ryzin, The Theory and Practice of Revenue Management, vol. 68. Boston, MA: Springer US, 2004.
[2] P. Liu and S. Smith, “Estimating unconstrained hotel demand based on censored booking data,” Journal of Revenue and …, July 01, 2002. http://link.springer.com/10.1057/palgrave.rpm.5170015 (accessed February 21, 2018).
[3] A. Nikseresht and K. Ziarati, “Estimating True Demand in Airline’s Revenue Management Systems using Observed Sales,” Int. J. Adv. Comput. Sci. Appl., vol. 8, no. 7, pp. 361–369, 2017, doi: 10.14569/ijacsa.2017.080748.
[4] C. Y. Goh, C. Yan, and P. Jaillet, “Estimating Primary Demand in Bike-sharing Systems,” SSRN Electron. J., Jan. 2019, doi: 10.2139/ssrn.3311371.
[5] J. P. Newman, M. E. Ferguson, L. A. Garrow, and T. L. Jacobs, “Estimation of Choice-Based Models Using Sales Data from a Single Firm,” Manuf. Serv. Oper. Manag., vol. 16, no. 2, pp. 184–197, May 2014, doi: 10.1287/msom.2014.0475.
[6] A. Aouad, V. F. Farias, and R. Levi, “Assortment Optimization under Consider-then-Rank Choice Models,” SSRN Electron. J., Jun. 2015, doi: 10.2139/ssrn.2618823.
[7] A. Aouad, V. Farias, R. Levi, and D. Segev, “The approximability of assortment optimization under ranking preferences,” Oper. Res., vol. 66, no. 6, pp. 1661–1669, Nov. 2018, doi: 10.1287/opre.2018.1754.
[8] D. Bertsimas and V. V Mišic, “Data-driven assortment optimization,” Manage. Sci., vol. 1, pp. 1–35, 2015.
[9] S. Jagabathula, “Assortment Optimization Under General Choice,” Ssrn, pp. 1–51, 2014, doi: 10.2139/ssrn.2512831.
[10] S. Jagabathula and P. Rusmevichientong, “A Nonparametric Joint Assortment and Price Choice Model,” Ssrn, no. July, 2013, doi: 10.2139/ssrn.2286923.
[11] G. Gallego, H. Topaloglu, and others, Revenue management and pricing analytics, vol. 209. Springer, 2019.
[12] G. Bitran and R. Caldentey, “An overview of pricing models for revenue management,” Manuf. Serv. Oper. Manag., vol. 5, no. 3, pp. 203–229, 2003.
[13] S. Kunnumkal, “Randomization Approaches for Network Revenue Management with Customer Choice Behavior,” Prod. Oper. Manag., vol. 23, no. 9, pp. 1617–1633, Sep. 2014, doi: 10.1111/poms.12164.
[14] L. Chen and T. Homem-de-Mello, “Mathematical programming models for revenue management under customer choice,” Eur. J. Oper. Res., vol. 203, no. 2, pp. 294–305, Jun. 2010, doi: 10.1016/J.EJOR.2009.07.029.
[15] G. Vulcano, G. van Ryzin, and R. Ratliff, “Estimating Primary Demand for Substitutable Products from Sales Transaction Data,” Ssrn, no. August 2015, 2011, doi: 10.2139/ssrn.1923711.
[16] G. van Ryzin and G. Vulcano, “A Market Discovery Algorithm to Estimate a General Class of Nonparametric Choice Models,” Manage. Sci., vol. 61, no. 2, pp. 281–300, 2015, doi: 10.1287/mnsc.2014.2040.
[17] G. van Ryzin and G. Vulcano, “Technical Note—An Expectation-Maximization Method to Estimate a Rank-Based Choice Model of Demand,” Oper. Res., vol. 65, no. 2, pp. 396–407, 2017, doi: 10.1287/opre.2016.1559.
[18] S. Jagabathula, D. Mitrofanov, and G. Vulcano, “Inferring Consideration Sets from Sales Transaction Data,” SSRN Electron. J., 2019, doi: 10.2139/ssrn.3410019.
[19] M. HajMirzaei, K. Ziarati, and A. Nikseresht, “Discovering customer types using sales transactions and product availability data of 5 hotel datasets with genetic algorithm,” J. Revenue Pricing Manag., 2020, doi: 10.1057/s41272-020-00245-3.
[20] S. Jagabathula and G. Vulcano, “A Partial-order-based Model to Estimate Individual Preferences Using Panel Data,” SSRN Electron. J., no. April, 2017, doi: 10.2139/ssrn.2560994.
[21] H. Lee and Y. Eun, “Discovering heterogeneous consumer groups from sales transaction data,” Eur. J. Oper. Res., vol. 280, no. 1, pp. 338–350, Jan. 2020, doi: 10.1016/J.EJOR.2019.05.043.
[22] M. HajMirzaei, K. Ziarati, and A. Nikseresht, “A customer type discovery algorithm in hotel revenue management systems,” J. Revenue Pricing Manag., 2021, doi: 10.1057/s41272-020-00273-z.
[23] T. Bodea, M. Ferguson, and L. Garrow, “Data Set —Choice-Based Revenue Management: Data from a Major Hotel Chain ,” Manuf. Serv. Oper. Manag., vol. 11, no. 2, pp. 356–361, 2008, doi: 10.1287/msom.1080.0231.
[24] L. Davis, Handbook of genetic algorithms. 1996.
[25] D. H. Wolpert and W. G. Macready, “No free lunch theorems for optimization,” IEEE Trans. Evol. Comput., vol. 1, no. 1, pp. 67–82, 1997.
[26] J. C. Culberson, “On the futility of blind search: An algorithmic view of ‘no free lunch,’” Evol. Comput., vol. 6, no. 2, pp. 109–127, 1998.
[27] D. E. Goldberg and S. Voessner, “Optimizing global-local search hybrids.,” in GECCO, 1999, vol. 99, pp. 220–228.
[28] P. Moscato, “On evolution, search, optimization, GAs and martial arts: toward memetic algorithms. California Inst. Technol., Pasadena,” 1989.
[29] N. Krasnogor and J. Smith, “A tutorial for competent memetic algorithms: model, taxonomy, and design issues,” IEEE Trans. Evol. Comput., vol. 9, no. 5, pp. 474–488, 2005.
[30] Wang, C. (2022). Efficient customer segmentation in digital marketing using deep learning with swarm intelligence approach. Information Processing & Management, 59(6), 103085.
[31] Narayana, V. L., Sirisha, S., Divya, G., Pooja, N. L. S., & Nouf, S. A. (2022, March). Mall customer segmentation using machine learning. In 2022 International Conference on Electronics and Renewable Systems (ICEARS) (pp. 1280-1288). IEEE.
[32] Griva, A., Zampou, E., Stavrou, V., Papakiriakopoulos, D., & Doukidis, G. (2023). A two-stage business analytics approach to perform behavioural and geographic customer segmentation using e-commerce delivery data. Journal of Decision Systems, 1-29.
