User profiling has wide applications such as personalization, intrusion detection, and online customer analysis in e-business environments. In the past decade, most of past research on user profiling focused on factual profile construction and applications. A few researchers studied application-oriented behavioral profiling problems. In light of the advantages of behavioral profiles over their factual counterparts and the importance of fundamental understanding of them, this dissertation probes into the theoretical foundation, modeling and data-mining-based heuristic techniques for constructing behavioral profiles.We first propose a research framework for behavioral profiling and define the fundamentals. We build an optimization model for describing and solving a general type of behavioral profile construction problem. The analysis of the optimization model's analytic properties found a strong connection between the feasible solution to the model and the independent dominating set in a graph derived from the input of the model. Based on this finding, we employed two solution searching approaches: brute-force and Genetic Algorithm, and performed numerical analysis on a synthetic small-sized profiling problem. The results demonstrate the effectiveness of Genetic Algorithm for producing approximate optimal solution to the CH optimization problem.We propose an innovative data-mining-based heuristic approach - hierarchical characteristic pattern mining to find solutions to the profile construction optimization problem. This approach builds behavioral profiles based on a new type of pattern - characteristic pattern and is appropriate for large-scale problems. Experiments using relatively large amounts of synthetic data were conducted to test the performance of this approach. The results show that the data-mining-based approach outperforms the Genetic Algorithm when the characteristic patterns exist. Finally, a particular user behavioral profile application - web user identification is introduced to present problems and solutions when applying the data-mining-based behavioral profile construction approach into a real-world profile application. The experiments performed on a real-world dataset produced positive results of our approach in terms of effectiveness, efficiency, and interpretability.The main contributions of the dissertation are: (1) proposing a comprehensive profiling research framework; (2) building an optimization model for solving a general type of profile construction problem; and (3) developing an innovative data-mining based heuristic approach to building behavioral profiles.
| Identifer | oai:union.ndltd.org:arizona.edu/oai:arizona.openrepository.com:10150/195843 |
| Date | January 2005 |
| Creators | Gao, Wei |
| Contributors | Liu Sheng, Olivia R, Zeng, Daniel, Liu Sheng, Olivia R, Zeng, Daniel, Hu, Paul J., Hariri, Salim |
| Publisher | The University of Arizona. |
| Source Sets | University of Arizona |
| Language | English |
| Detected Language | English |
| Type | text, Electronic Dissertation |
| Rights | Copyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author. |
Page generated in 0.0019 seconds