Skip navigation
Please use this identifier to cite or link to this item: https://repository.esi-sba.dz/jspui/handle/123456789/609
Full metadata record
DC FieldValueLanguage
dc.contributor.authorSAIDOUNE, AChref HOussem-
dc.contributor.authorDJELLOULI, AHmed ABdelouhab-
dc.date.accessioned2024-09-18T08:17:04Z-
dc.date.available2024-09-18T08:17:04Z-
dc.date.issued2024-
dc.identifier.urihttps://repository.esi-sba.dz/jspui/handle/123456789/609-
dc.descriptionSupervisor : Mr. Khaldi Belkacem -Co-supervisor - Djezzy : Mme.BRADAI Yasmineen_US
dc.description.abstractIn the contemporary landscape of business analytics, the significance of data, particularly customer data, is paramount. Companies, cognizant of this fact, are amassing vast quantities of information from diverse sources, collectively known as Big Data. Leveraging this data has become imperative for companies aiming to distinguish themselves in the competitive marketplace. While propensity models have traditionally served as crucial tools for extracting insights and forecasting behaviors from these extensive datasets, alternative approaches such as affinity analysis using association rules and advanced clustering methods have emerged as promising avenues for understanding customer behavior and devising effective strategies for enhancing customer engagement and satisfaction. In the context of an end-of-studies project, an Algerian mobile operator explored advanced techniques to analyze subscription schemas and formulate strategies based on association rules between clients and offers. Instead of relying solely on propensity models, this research delves into affinity analysis and advanced clustering methods to uncover hidden patterns in customer data. This project includes a comprehensive review of literature on machine learning techniques for affinity analysis and clustering. A detailed methodology is outlined, covering problem comprehension, data understanding, preparation, modeling, evaluation, and visualization. Advanced clustering methods and association rule mining form the crux of the modeling phase, where various algorithms are tested and evaluated to identify the most effective approach for uncovering customer affinities and formulating targeted strategies. The culmination of this research is the development of a robust analytical framework that leverages advanced machine learning techniques to derive actionable insights from customer data. By employing affinity analysis and advanced clustering methods, this framework aims to empower the organization with a deeper understanding of customer preferences and behaviors, thereby facilitating the design and implementation of targeted strategies to enhance customer satisfaction and drive business growth. ***en_US
dc.language.isoenen_US
dc.subjectBig Dataen_US
dc.subjectDjezzyen_US
dc.subjectAssociations Rulesen_US
dc.subjectMachine Learningen_US
dc.subjectUpselling Strategiesen_US
dc.subjectAffinity Analysisen_US
dc.subjectClustering Methodsen_US
dc.titleMachine learning techniques for analyzing underlying patterns and upselling strategiesen_US
dc.typeThesisen_US
Appears in Collections:Ingenieur

Files in This Item:
File Description SizeFormat 
PFE_Djellouli_Saidoune_Djeezy-1-1.pdf71,08 kBAdobe PDFView/Open
Show simple item record


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.