Banca de QUALIFICAÇÃO: WAGNER VIEIRA LOPES

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : WAGNER VIEIRA LOPES
DATE: 28/08/2025
TIME: 10:30
LOCAL: Sala B206 do IMD e online: https://meet.google.com/xsn-ahsz-dnu
TITLE:

Dynamic Pricing in Volatile Business Environments: A Computational Approach with Reinforcement Learning and Multivariate Simulation

KEY WORDS:

Dynamic pricing. Deep reinforcement learning. Digital retail. Artificial intelligence. Volatile environments.

PAGES: 70
BIG AREA: Ciências Exatas e da Terra
AREA: Ciência da Computação
SUMMARY:

In business environments characterized by volatility, uncertainty, and high competitiveness, pricing decisions play a strategic role in sustaining revenue, profit margins, and market positioning. In retail and e-commerce, this challenge is amplified by demand fluctuations, competitive pressures, and macroeconomic instabilities, which demand adaptive and data-driven approaches. This research proposes a dynamic pricing approach based on Deep Reinforcement Learning (DRL), focusing on continuous adaptation to market changes. The study is structured into three main stages: (i) a systematic literature review following the PRISMA protocol, mapping algorithms and research gaps in pricing applications; (ii) the modeling of a simulation environment formulated as a Markov Decision Process (MDP), incorporating critical macroeconomic and microeconomic variables; and (iii) experimentation with reinforcement learning algorithms, evaluating pricing strategies in volatile scenarios using metrics such as cumulative revenue, contribution margin, and price stability. As its main contribution, this research demonstrates the technical feasibility of AI-driven pricing strategies in complex business contexts, providing an approach capable of continuous learning, exploration–exploitation, and context-aware decision-making. The expected results highlight the potential of DRL to overcome the limitations of traditional pricing models - typically static and poorly responsive - while fostering the adoption of intelligent methods in the Brazilian digital retail sector.

COMMITTEE MEMBERS:
Presidente - 2978747 - CHARLES ANDRYE GALVAO MADEIRA
Interno - 4351681 - JOAO CARLOS XAVIER JUNIOR
Externa ao Programa - 1474874 - JANAINA DA SILVA ALVES - UFRN