مدل ریاضی تحلیل جریان کلیک برای پیش‌بینی رفتار مشتریان اینترنتی
محورهای موضوعی : مهندسی برق و کامپیوتر
محمدمهدی سپهری
1
,
فؤاد مهدوی‌پژوه
2
1 - دانشگاه تربيت مدرس
2 - دانشگاه ايالتي اوكلاهماي آمريكا
کلید واژه: برنامه‌ریزی ریاضی تحلیل جریان کلیک مدل فروشنده دوره‌گرد گردآورنده جایزه مدل زنجیره مارکوف,
چکیده مقاله :
تحليل جريان كليك ابزار مفیدی براي پيش‌بيني مسير حركت يك مشتري خاص در يك وب سايت است كه كاربرد فراواني در زمينه‌هاي تجارت الكترونيكي، بازاريابي الكترونيكي و مديريت ارتباط با مشتري دارد. رويكرد جديد مقاله به‌دست آوردن محتمل‌ترین مسير حركت يك كاربر در يك وب سايت با استفاده از مدل‌هاي ماركوفي است كه در قالب يك مدل برنامه‌ريزي صفر و يك حاصل شده است. مدل برنامه‌ريزي صفر و يك ارائه‌شده حالت خاصي از مدل معروف مسئله پيله‌ور (فروشنده دوره‌گرد) گردآورنده جايزه مي‌باشد كه خود يك مدل NP-hard بوده و تعداد محدوديت‌هاي حذف زير تور آن با افزايش فضاي مسئله به‌طور انفجارآميزي افزايش مي‌يابد. براي حل مدل طرح‌شده الگوريتمي جامع و كارا ارائه گرديده است. براي انجام جنبه‌هاي محاسباتي و پياده‌سازي مدل پيشنهادي، داده‌هاي برگرفته از لاگ فايل‌هاي سرور يك وب سايت دانشگاهي براي 20 كاربر مختلف مورد استفاده قرار گرفت. مقايسه جواب‌هاي حاصل با جواب‌هاي به‌دست آمده از الگوريتم جيوديچي نشان مي‌دهد مدل پيشنهادي جواب‌هاي بسيار دقيق‌تر و بهتري نسبت به الگوريتم جيوديچي ارائه مي‌دهد.
Click stream analysis is known as an effective method for customer’s viewing route prediction in a particular web site. Predicting Customer viewing behavior provides considerable advantages in different areas such as e-commerce, e-business and customer relationship management. This paper aims to provide a 0-1 mathematical model based on Markov models for evaluating the most probable viewing route of a customer in a website. This problem can be formulated as an especial case of well-known Prize Collecting Traveling Salesman Problem (PCTSP) which is a NP-hard problem and its sub tour elimination constraints are increased drastically by increasing the model parameters. Also an effective algorithm is introduced in this paper to solve this NP-hard model. For model validation, the proposed model was implemented by using the log files of a university web site server for 20 different users. Comparison of the results with commonly used Giudici algorithm shows that the proposed model yields better and exacter solutions.
[1] G. P. Shapiro, Machine Learning and Data Mining, Course Notes, 2004.
[2] A. Bestavros, "Speculative data dissemination and service to reduce server load, network traffic, and service time in distributed information system," in Proc. of the 1996 Conf. on Data Engineering, pp. 18 -187, 26 Feb.-1 Mar. 1996.
[3] I. Zuckerman, D. W. Albrecht, and A. Nicholson, "Predicting user’s request on the WWW," in Proc. of the 7th Int. Conf. on User Modeling, pp. 275-284, Banff, Canada, 20-24 Jun. 1999.
[4] B. Huberman, P. Pirolli, J. Pitkow, and R. Lukose, "Strong regularities in World Wide Web surfing," Science, vol. 280. no. 5360, pp. 95-97, 3 April 1998.
[5] I. Cadez, D. Heckerman, C. Meek, P. Smyth, and S. White, Visualization of Navigation Patterns on a Web Site Using Model Based Clustering, Technical Report, MSR-TR-00-18, Microsoft Research, Redmond, WA, US, 2000.
[6] V. A. Petrushin, "eShopper Modeling and Simulation," in Proc. SPIE 2000 Conf. on Data Mining, pp. 75-83, Beijing, China, 16-20 Oct. 2000.
[7] C. Theusinger and K. P. Huber, "Analysing the footsteps of your customers," 2000.
[8] A. Goldfarb, Analysing Website Choice Using Clickstream Data, Working Paper, Northwestern University, 2001.
[9] R. E. Bucklin and C. Sismeiro, "A model of web site browsing behavior estimated on clickstream data," Journal of Marketing Research, vol. 40, no. 3, pp. 249-67, 2001.
[10] W. W. Moe and P. S. Fader, "Capturing evolving visit behavior in clickstream data," Journal of Interactive Marketing, vol. 30, no. 1, pp. 5-19, Winter 2004.
[11] A. L. Montgomery, and S. Li, K. Srinivasan, and J. Liechty, Predicting Online Purchase Conversion Using Web Path Analysis, GSIA Working Paper, Nov. 2002.
[12] A. L. Montgomery and F. Christos, Using Clickstream Data to Identify World Wide Web Browsing Trends, GSIA Working Paper #2000-E20 2002.
[13] S. Li, J. Liechty, and A. Montgomery, Modeling Category Viewership of Web Users with Multivariate Count Models, GSIA Working Paper #2003-E25, 2002.
[14] P. Giudici and C. Tarantina, Applied Data Mining, Wiley, London, 2003.
[15] Y. Park and P. S. Fader, "Modeling browsing behavior at multiple websites," Marketing Science, vol. 23, no. 3, pp. 280-303, Summer 2004.
[16] A. L. Montgomery, S. Li, K. Srinivasan, and J. Liechty, "Modeling online browsing and path analysis using clickstream data," Marketing Science, vol. 23, no. 4, pp. 579-595, Fall 2004.
[17] P. Giudici and C. Tarantina, Web Mining Pattern Discovery, Technical Report #156, University of Pavia, Italy, Sep. 2003.
[18] E. Balas, "The prize collecting traveling salesman problem," Networks, vol. 19, pp. 621-636, 1989.
[19] E. Balas and G. Martin, "Roll-a-round: software package for scheduling the sounds of a rolling mill," Balas and Martin Associates, 1985.
[20] M. Fischetti and P. Toth, "An additive approach for the optimal solution of prize-collecting traveling salesman problem," in B. L. Golden and A. A. Assad (eds.), Vehicle Routing: Methods and Studies, North Holland, Amsterdam, 1988.
[21] E. H. A. Aarts, J. H. M. Korst, and P. J. M. Van Laarhoven, "A quantitative analysis of the simulated annealing algorithm: a case study for the traveling salesman problem," J. Statistical Physics, vol. 50, no. 1-2, pp. 187-206, 1988.
[22] J. R. A. Allwright and D. B. Carpenter, "A distributed implementation of simulated annealing for traveling salesman problem," Parallel Computing, vol. 10, no. 3, pp. 335-338, May 1989.
[23] D. Johnson and A. McGeoch, "The traveling salesman problem: a case study in local optimization," in E. H. L. Aarts and J. Lenstra (eds.), Local Search in Combinatorial Optimization, John Wiley & Sons, Inc., New York, 1995.
