Entradas recentes
Artificial intelligence for corneal ectasia screening: a review and insights from data preprocessing
( 2025 ) Peller, Tayan; Mendes, Inês; Passos, Madalena Freitas; Sá, Daniel; Miranda, Vasco; Abreu, Ana; Machado, José Manuel
Keratoconus is a progressive corneal ectatic disorder that may cause irregular astigmatism, visual impairment and iatrogenic ectasia after refractive surgery. Early detection remains challenging, as conventional indices often fail to identify fruste or subclinical cases. Advances in optical coherence tomography (OCT) and biomechanical assessments have provided valuable biomarkers, yet sensitivity and generalizability are still limited. This review summarizes recent Artificial Intelligence (AI) applications for corneal ectasia screening published between 2020 and 2025. From 894 initial records, 35 studies were included, covering both Machine Learning (ML) and Deep Learning (DL) methods. Ensemble ML models, such as Random Forest and Gradient Boosting, consistently outperformed alternatives, while convolutional neural networks and transfer learning dominated DL approaches. Future work will focus on analyzing real clinical data available within our group, including OCT-derived metrics and epithelial thickness maps, to explore supervised and unsupervised ML strategies and assess their feasibility for clinical translation.
Evaluating climate risk and return premiums in resource-intensive sectors: Evidence from critical minerals and fossil fuels
( 2026 ) Ferreira, David Silves; Cortez, Maria Céu
The transition to low-carbon energy systems has heightened the strategic importance of critical minerals
while exposing the fossil fuel sector to significant climate-related transition risks. This dissertation
evaluates the financial performance and risk-return dynamics of investment portfolios comprised of critical
mineral and fossil fuel equities within developed markets. Using monthly data from 1996 to 2026,
portfolios were constructed for both resource-intensive sectors.
To assess whether climate and systematic risks translate into distinct return premiums, portfolio performance
is evaluated using established multi-factor asset pricing models, including the Fama and French
(1993, 2015, 2018) three, five, and six-factor models, as well as the Hou et al. (2021) q-factor model.
The initial baseline results indicate that the excess returns for both sectors are primarily driven by
systematic market risk, size, and value exposures, with no evidence of statistically significant abnormal
performance. However, we observe that fossil fuel portfolios show negative and statistically significant
alphas following the international financial crisis. Furthermore, when portfolios are evaluated under different
global oil market conditions, fossil fuel portfolios consistently underperform during periods of market
contraction.
Equity Research Report BMW Group
( 2026 ) Martins, Ana Carolina Santos; Silva, Florinda
Este relatório apresenta um estudo de Equity Research da Bayerische Motoren Werke AG (BMW), uma fabricante global líder a operar nos segmentos de Automóveis, Motociclos e Serviços Financeiros. O principal objetivo é estimar o valor intrínseco da empresa, explorando a sua transição estratégica para a eletrificação, as dinâmicas competitivas no mercado chinês e as implicações operacionais da futura arquitetura Neue Klasse.
O relatório está estruturado em várias secções, incluindo o perfil da empresa, uma visão geral da indústria e uma análise detalhada do desempenho financeiro e da estrutura de capital da BMW. De notar que, embora a avaliação final tenha sido consolidada através de um modelo integrado de Fluxos de Caixa Descontados (DCF), cada segmento de negócio foi analisado individualmente para captar com precisão os seus drivers de crescimento e perfis de risco específicos. Esta avaliação utiliza um Custo Médio Ponderado de Capital (WACC) de 5,16% e uma taxa de crescimento terminal de 2,00%. A robustez desta avaliação é ainda corroborada através de uma Avaliação Relativa utilizando múltiplos de pares (peer multiples), de um modelo de Avaliação de Opções de Black-Scholes e de uma extensa avaliação de risco que engloba análises de cenários e simulações de Monte Carlo.
O relatório conclui com uma recomendação de MANTER (HOLD) e um preço-alvo de 83,57 € para dezembro de 2026, representando um potencial de desvalorização (downside) de 6,59% face ao preço atual da ação de 89,46 € (à data de 27 de fevereiro de 2026).