![Institutional Repository [SANDBOX]](images/dias.logo.png "Institutional Repository [SANDBOX]"){kind=logo}
Institutional Repository [SANDBOX]
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI: | http://purl.tuc.gr/dl/dias/6011DAD6-17FC-4286-AD3B-24CF7673424E | ||
| Year | 2024 | ||
| Type of Item | Master Thesis | ||
| License |
|
||
| Bibliographic Citation | Anastasia Dritsa, "Algorithms for predicting online behavior ", Master Thesis, School of Production Engineering and Management, Technical University of Crete, Chania, Greece, 2024 https://doi.org/10.26233/heallink.tuc.101202 | ||
| Appears in Collections |
The awareness of the process of user behavior in the online space is a key element of digital marketing. Delving into this process allows for the categorization of users based on their behavior, which can then be analyzed. For this purpose, the study examines how algorithms such as Logistic Regression, Decision Trees, Random Forests, Support Vector Machines, and Neural Networks are used to analyze and predict user actions in the online environment.By utilizing these algorithms, businesses can gain valuable insights into user interactions, preferences, and purchase intentions, thereby enhancing the effectiveness of targeted marketing efforts. The study provides a comparative analysis of the strengths and limitations of each algorithm, offering practical guidance for selecting the most appropriate method for specific prediction tasks in the digital marketplace. The findings highlight the importance of advanced analytical techniques in understanding and influencing consumer behavior, ultimately leading to more personalized and effective marketing strategies.
Copyright © DIAS 2013
