Gregorio F. Azevedo

Gregorio F. Azevedo

Auto-generated profile, based on publicly available information

Gregorio F. Azevedo

Federal University of São Carlos, Sorocaba, São Paulo, Brazil

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 June 2025 in Expert Systems with Applications
Verified
Journal Article
Closed access
RSRenato M. Silva
Renato M. Silva
GAGregório F. Azevedo
Gregório F. Azevedo
MBMatheus V.V. Berto
Matheus V.V. Berto
JRJean R. Rocha
Jean R. Rocha
EFEduardo C. Fidelis
Eduardo C. Fidelis
TATiago A. Almeida
Tiago A. Almeida

22 September 2025
Verified
Conference Paper
Open access
PPPedro R. Pires
Pedro R. Pires
GAGregorio F. Azevedo
Gregorio F. Azevedo
PCPietro L. P. Campos
Pietro L. P. Campos
RSRafael T. Sereicikas
Rafael T. Sereicikas
TATiago A. Almeida
Tiago A. Almeida

7 June 2026
Verified
Conference Paper
Open access
RSRafael T. Sereicikas
Rafael T. Sereicikas
PPPedro R. Pires
Pedro R. Pires
GAGregório F. Azevedo
Gregório F. Azevedo
TATiago A. Almeida
Tiago A. Almeida

23 March 2026
Verified
Conference Paper
Open access
PPPedro R. Pires
Pedro R. Pires
GAGregório F. Azevedo
Gregório F. Azevedo
RSRafael T. Sereicikas
Rafael T. Sereicikas
PCPietro L. Campos
Pietro L. Campos
TATiago A. Almeida
Tiago A. Almeida
With the increasing availability of online information, recommender systems have become an important tool for many web-based systems. Due to the continuous aspect of recommendation environments, these systems increasingly rely on contextual multi-armed bandits (CMAB) to deliver personalized and real-time suggestions. A critical yet underexplored component in these systems is the representation of user state, which typically encapsulates the user's interaction history and is deeply correlated with the model's decisions and learning. In this paper, we investigate the impact of different embedding-based state representations derived from matrix factorization models on the performance of traditional CMAB algorithms. Our large-scale experiments reveal that variations in state representation can lead to improvements greater than those achieved by changing the bandit algorithm itself. Furthermore, no single embedding or aggregation strategy consistently dominates across datasets, underscoring the need for domain-specific evaluation. These results expose a substantial gap in the literature and emphasize that advancing bandit-based recommender systems requires a holistic approach that prioritizes embedding quality and state construction alongside algorithmic innovation. The source code for our experiments is publicly available on https://github.com/UFSCar-LaSID/bandits_blind_spot.

31 March 2025
Verified
Conference Paper
Open access
PPPedro R. Pires
Pedro R. Pires
RSRafael T. Sereicikas
Rafael T. Sereicikas
GAGregorio F. Azevedo
Gregorio F. Azevedo
TATiago A. Almeida
Tiago A. Almeida