RT Dissertation/Thesis
T1 Ensembles of choice-based models for recommender systems
A1 Almomani, Ameed Ali Ahmad
K1 Recommender Systems
K1 Ensembles
K1 Choice models
K1 Choice models Ensembles
K1 Dual Process Theory
AB In this thesis, we focused on three main paradigms: RecommenderSystems, Decision Making, and Ensembles. The work is structured as follows. First, the thesis analyzes thepotential of choice-based models. The motivation behind this was based on the idea of applying sound decisionmakingparadigms, such as choice and utility theory, in the field of Recommender Systems. Second, this researchanalyzes the cognitive process underlying choice behavior. On the one hand, neural and gaze activity wererecorded experimentally from different subjects performing a choice task in a Web Interface. On the other hand,cognitive were fitted using rational, emotional, and attentional features. Finally, the work explores the hybridizationof choice-based models with ensembles. The goal is to take the best of the two worlds: transparency andperformance. Two main methods were analyzed to build optimal choice-based ensembles: uninformed andinformed. First one, two strategies were evaluated: 1-Learner and N-Learners ensembles. Second one, we reliedon three types of prior information: (1) High diversity, (2) Low error prediction (MSE), (3) and Low crowd error.
YR 2020
FD 2020
LK http://hdl.handle.net/10347/23912
UL http://hdl.handle.net/10347/23912
LA eng
DS Minerva
RD 24 abr 2026