user behaviour analysis


Published on

user behaviour analysis

Published in: Internet
1 Like
  • Be the first to comment

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

user behaviour analysis

  1. 1. Submitted By:- Vaibhav 9910103585(F3) JAYPEE INSTITUTE OF INFORMATION TECHNOLOGY, NOIDA
  2. 2. Introduction Personalization of Web Information Retrieval Based upon User Behavior Modeling and Relevance Extraction User tracking + Analyzing details = User Behavior Analysis
  3. 3. Aim To make good relationship Track the user online User behavior tracking
  4. 4. Sources of Research papers  Scholars At Google  Pintrest  Flipcart R&D  Acm  Springer  IEEE
  5. 5. Summary of research work  There are two approaches /mode which are used to show the result on the serp page. A. The results are shown according to the relevance. B. The results are shown according to the revenue and the user behavior CTR
  6. 6. Paper 2 . Statical Features: a user will click a url if he examine the URL relevant(Depend=?) Click-Model Features: the statical features are having arbitrary nature because it is query and the URL dependent
  7. 7. Paper 3 Active page Passive page Dead page Surfing page
  8. 8. Diagrammatical Representation of Problem
  9. 9. Other Approaches . Coordinates . Snapshots chalkmark ( . Eularian distance
  10. 10. Tools & Technology  Microsoft Visual Studio  JQuery & Ajax  Google Search API  PHP  LIB SVM Classifier  Wempserver  JSON API  Mysql  Filezila  Python  C++
  11. 11. Algorithm
  12. 12. Experimental studies Answer the user accordingly.
  13. 13. Problem Statement Try to give the user the things they wants. Solution Track the user and tried to judge the requirement of the user more clearly. Show the related things of the user interest and best possible alternative.
  14. 14. Requirement specification Purpose: The purpose of the project is to provide the owner of the webpage about the details of the person who visited the owner websites.  Must be a fast system.  Dynamic capturing the user’s details.  Polymorphism  Inheritance  Encapsulation.
  15. 15. Non Functional Requirement  Security: The product is secured.  Reliability: The product is reliable.  Efficiency: The product is efficient.  Portability: The product is portable as it is available online and can be accessed from anywhere.  Maintainability: The product is easily maintained as it is global.
  16. 16. Design Model
  17. 17. Risk Analysis  Slow working  In compatible  Load on the server  Performance Decrease  Low security
  18. 18. Implementation
  19. 19. Result
  20. 20. References  [1] E. Agichtein, E. Brill, S. Dumais, and R. Ragno. Learning user interaction models for predicting web search result preferences. In Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval (SIGIR), pages 3–10, 2006.  [2] M. Beal and Z. Ghahraman. Variational Bayesian learning of directed graphical models with hidden variables. Bayesian Analysis, 1(4):793–832, 2006.  [3] A. Broder. A taxonomy of web search. SIGIR Forum, 36(2):3–10, 2002.  [4] C. Burges, T. Shaked, E. Renshaw, A. Lazier, M. Deeds, N. Hamilton, and G. Hullender. Learning to rank using gradient descent. In Proceedings of the  22nd international conference on Machine learning, pages 89–96, 2005.  [5] Y. Cao, J. Xu, T.-Y. Liu, H. Li, Y. Huang, and H.-W. Hon. Adapting ranking svm to document retrieval. In Proceedings of the 29th annual international ACM SIGIR conference on Research and development in informat ion retrieval, 2006.  [6] B. Carlin and T. Louis. Bayes and Empirical Bayes Methods for Data Analysis. Chapman & Hall/CRC, 2000.
  21. 21. Thanks..