Eduardo Marques Braga de Faria

Este trabalho investiga como sistemas colaborativos inteligentes podem aprimorar licitações públicas brasileiras por meio da integração de sustentabilidade e saberes tradicionais. Utilizando dados governamentais abertos, são empregados algoritmos de aprendizagem de máquina e indicadores socioambientais para reduzir discrepâncias de preços e identificar irregularidades em tempo real. Os resultados mostram queda expressiva nas variações de custo ao se inserirem métricas sustentáveis. Conclui-se que a abordagem proposta reforça a transparência, a eficiência e a responsabilidade ética nas compras governamentais, ampliando a participação de comunidades locais e a preservação dos recursos naturais.

Context: With the advancement of artificial intelligence (AI), expert systems (ESs) continue to evolve and are essential to support decisions in complex domains such as healthcare, industry, and automation. Problem: The growth of AI technologies has expanded the possibilities of Expert Systems. With advances in natural language processing, there is a need for an updated mapping of the applications and methodologies of ESs, highlighting the role of new AI techniques. Solution: Literature review is essential to identify trends, methodologies, challenges, and innovations in ESs, providing a comprehensive overview of the most recent trends and their implications. IS Theory: When examining how ESs can integrate and process complex and constantly evolving data, this study is guided by the complex systems theory, which aims to explore how parts of systems exchange information and adapt to new conditions. Method: The study employs a qualitative and interpretative review to investigate the state of the art in inference methodologies, knowledge acquisition, and performance in ESs. Summary of Results: Expert systems have evolved significantly with the use of AI, including deep learning, hybrid models, and natural language processing, improving accuracy, adaptability, and the ability to process large volumes of data. Contributions and Impact on the IS Field: This study highlights the advances that make expert systems more effective, highlighting how the integration of AI improves the ability to deal with uncertainty and complex decisions. The new methodologies show potential to optimize reliability and decision making in critical environments.

Context: This research focuses on building reference prices in Brazilian public tenders, integrating statistical techniques and AI to improve automated decision accuracy and detect issues like overpricing and underpricing. Problem: Traditional methods for calculating reference prices, like arithmetic mean and lowest price, often cause distortions in public tenders. This research evaluates how AI can enhance accuracy and transparency in audits. Solution: The proposed solution is software that combines statistical algorithms with machine learning to calculate reference prices more robustly. The first version uses statistical methods; the second integrates TensorFlow, expanding irregularity detection. IS Theory: Based on Design Science Research, this study develops and evaluates artifacts to solve identified problems, applying scientific techniques to optimize reference price calculations. Method: A quantitative experiment using public tender data compares the software’s performance with traditional methods, focusing on average deviation and machine learning accuracy. Summary of Results: The first software version reduced average deviation to 2.53%, versus 15.58% for traditional methods. The machine learning version achieved 70% accuracy in detecting pricing irregularities, adding an extra verification layer. Contributions and Impacts in the IS area: This research contributes to Information Systems by proposing a system that combines statistics and AI, enhancing accuracy and transparency. The solution improves public bidding efficiency and is adaptable to other government and industry areas.