REPOSITÓRIO P.PORTO

Scientific Repository of the Porto Polytechnic

The Scientific Repository of the Polytechnic Institute of Porto's main goal is to provide all the scientific production of teachers, researchers and students of the Polytechnic Institute of Porto when possible in full text.The mission of the Scientific Repository of the Polytechnic Institute of Porto comprises up between two factors of extreme importance, the availability of scientific information and the preservation of digital information."Key Market": to make available in free access all the scientific production of the Polytechnic Institute of Porto."Contribution": aid students, researchers, teachers and the general public in obtaining reliable scientific production."Distinction": commitment that each user meets their scientific needs.

Email recipp@sc.ipp.pt

Recent Submissions

Entrelaçar histórias, evocar imagens : residência artística de Vila do Conde

Publication . ; Leal, João; Ferreira, José Quinta; Cortesão, Maria João

Trabalhos realizados nas residências artísticas do Mestrado em Cinema e Fotografia Work from the artistic residency of the Master in Film and Photography

2025Book

Open access

Adorar

Publication . Alves, Cesário; Leal, João

No século XVIII, Tintoretto pintou ‘A Adoração dos Reis Magos’. A obra está neste momento em exposição permanente na igreja do Mosteiro de Singeverga, em Roriz, Santo Tirso. A crença que terá levado o autor a produzir esta tela pintada a óleo, de 524 x 225 cm, poderá ser distinta da nossa. No entanto, admiramos a obra, o local e as pessoas que a acolhem. O generoso acesso que nos foi concedido permitiu que tivéssemos tempo e possibilidade de a olharmos de diferentes pontos de vista. A deambulação livre e prolongada contribuiu para que nos pudéssemos aproximar ao ponto de perdermos a dimensão do todo. É nessa altura que a abstração surge e que a pintura ganha mais dimensões interpretativas.

2024Book part

Open access

Sistema de localização em tempo real (RTLS) para veículos no exterior

Publication . FARO, MIGUEL PINTO DE MAGALHÃES; Dias, André Miguel Pinheiro

Este projeto, intitulado "Sistema de Localização em Tempo Real (RTLS) para Veículos no Exterior", foi realizado em contexto industrial na empresa Continental Mabor, situada em Lousado. O trabalho surge da necessidade de monitorizar com precisão a posição de veículos nas vias internas da empresa de forma a assegurar com segurança a coexistência de veículos autónomos e convencionais no mesmo espaço operacional. O projeto iniciou-se com uma análise e comparação das principais soluções de localização em tempo real existentes, bem como das tecnologias de localização, comunicação, e especialmente das técnicas de correção Global Navigation Satellite System (GNSS) mais relevantes, avaliando-se a sua viabilidade técnica e operacional no contexto específco da empresa. Após essa análise, foi desenvolvido um sistema protótipo funcional com duas abordagens distintas utilizando o mesmo hardware. Uma é baseada em correções diferenciais GNSS Real-Time Kinematic (RTK) processadas de forma centralizada, e outra recorre a correções diferenciais differential GNSS (DGNSS) com processamento distribuído, fornecidas por um serviço externo. Durante a execução do projeto foram desenvolvidas várias componentes de hardware, firmware e software, integrando múltiplos dispositivos, subsistemas de comunicação, aquisição e processamento de dados e visualização em tempo real. A validação das soluções desenvolvidas foi efetuada através de testes experimentais, concluindo-se que solução desenvolvida cumpre os requisitos previamente definidos.

2025-07-29Master thesis

Embargoed access

Bridging automation and customization: MLOps in recommender system development

Publication . JORDÃO, MIGUEL JOSÉ RIBEIRO; Pereira, Isabel Cecília Correia da Silva Praça Gomes

Recommender systems have become essential in modern digital platforms, supporting decision making and personalization across domains such as e-commerce, media, and enterprise applications. At BMW Group, MyWorkplace (MWP) is a centralized hub managed by Critical Techworks (CTW) that provides access to hundreds of internal tools. Discoverability remains challenging given the size and heterogeneity of the tools catalog. This creates inefficiencies, highlighting the need for a scalable, reliable, and auditable recommendation solution. This project presents an MLOps-first approach for a recommender grounded in the CRISPML(Q) process model. It characterizes the recommendation problem, available data sources, and success criteria, and proposes a reference architecture integrating automated ETL, feature preparation, containerized training and serving, and CI/CD for continuous delivery. Several content-based approaches are implemented and evaluated under realistic data constraints using established ranking metrics; collaborative and hybrid extensions are outlined for future phases once interaction feedback becomes available. The contributions of this work are both technical and methodological: the design and validation of a recommendation strategy for the hub platform; an assessment of operational and governance requirements, including security and compliance, and the demonstration of the system in a real-world industrial environment. In addition to the deployment within BMW Group, this project advances the understanding of how MLOps principles can be applied to balance automation and customization in recommender systems. Results indicate that an MLOps-first design improves scalability, maintainability, and auditability, and lays the groundwork for collaborative filtering, feedback loops, and, when governance permits, large language model components. The system and methodology are applicable to enterprise-scale recommendation scenarios with similar operational constraints.

2025-10-15Master thesis

Open access

Financial reporting with GenAI

Publication . CHEN, MIGUEL HUANG; Santos, Joaquim Filipe Peixoto dos

Financial reporting is a critical but time-consuming activity in the banking sector, traditionally requiring analysts to manually extract data, validate figures, and draft lengthy reports. This thesis investigates the use of Generative AI, specifically a GPT-based API, to automate the reporting workflow. A key contribution lies in the design of structured prompt engineering strategies that constrain outputs, ensure numeric accuracy, and enforce corporate formatting requirements. The proposed framework integrates three components: (i) a data extraction tool for structured retrieval of financial indicators, (ii) a Python-based orchestration layer that preprocesses data, builds prompts, and manages interaction with the Generative AI API, and (iii) a report assembly module that converts the AI’s HTML output into fully formattedWord documents. A Streamlit-based interface centralizes usage, enabling analysts to configure parameters, trigger generation, and download reports seamlessly. Evaluation followed an iterative approach with weekly user feedback cycles. Results show a reduction of over 90% in preparation time compared to the manual workflow, alongside improved consistency and reduced operational risk. The framework also demonstrated adaptability across different use cases, from quarterly statements to daily transaction-level reports. While limitations remain—such as dependence on data quality and model fragility—the study demonstrates that LLM-driven prompt engineering can deliver scalable, auditable, and efficient financial reporting automation.

2025-10-16Master thesis

Embargoed access