Authors:
Rafael Marin Machado de Souza
1
;
2
;
3
;
Leandro Nunes de Castro
1
;
4
;
3
;
Marcio Biczyk
1
;
Marcos dos Santos
2
;
5
and
Eder Cassettari
2
Affiliations:
1
Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (HCFMUSP), InLab, Rua Doutor Ovídio Pires de Campos 75 (Portaria 1), São Paulo, SP, Brazil
;
2
Universidade de São Paulo (USP), Campus Piracicaba – Luiz de Queiroz, Rua Alexandre Herculano, 143 – Monteiro, Piracicaba, SP, Brazil
;
3
Universidade Estadual de Campinas (UNICAMP), Faculdade de Tecnologia, R. Paschoal Marmo, 1888 - Jd. Nova Itália, Limeira, SP, Brazil
;
4
Florida Gulf Coast University (FGCU), 10501 Fgcu Blvd S, Fort Myers, FL 33965, U.S.A.
;
5
Ministério da Defesa - Comando da Marinha, Centro de Análises de Sistemas Navais – CASNAV, Praça Barão de Ladário S/N° - Ed. 23, Centro, Rio de Janeiro, RJ, Brazil
Keyword(s):
Software Agent, Simulation, Monte Carlo, Inventory Theory.
Abstract:
The acquisition of innovative items or those without historical demand data considerably increases the complexity of the routine of buyers, who among the daily challenges are keeping stocks up to date, with quantities that provide maximum profitability or maximum use of the purchased items. Seeking to provide a tool to assist in these goals, this study implements a Python-based software agent employing the Monte Carlo method for stochastic simulation and proposes a solution for uncertain inventory demands, providing a decision-mak-ing tool in the absence of historical data, thereby optimizing inventory levels and maximizing profitability. Experiments conducted across both local and cloud server configurations, with a comparative analysis of CPU and GPU performance, demonstrates the agent’s capacity to generate random scenarios with a statistical tolerance margin of 1% from 10,000 simulations. Scalability tests underscore the agent’s adaptability to diverse scenarios, effectively harn
essing GPU capabilities for processing extensive data.
(More)