Percorrer por autor "Martins, Margarida"
A mostrar 1 - 2 de 2
Resultados por página
Opções de ordenação
- Exploring pseudo-labeling for reject inferencePublication . Martins, Margarida; Brandão, SusanaBanks use algorithms to estimate the credit risk of loan applicants. However, we need to retrain these models. When retraining, we only know the label, meaning whether the applicant defaulted or not, for those accepted for the loan. Retraining only with the accepted will result in biased models and losses for the bank due to selection bias. To counteract this issue, we can infer the labels of those rejected. This is known as reject inference. In this thesis, we will pursue pseudo-labeling to do reject inference, which needs two models, the first to create the pseudo-labels for the rejected and the second to make the final predictions. We will create the pseudo-labels by training a lightGBM on the available data. Afterward, we will apply a logistic regression as the final model. We will compare the results against a baseline, setting all rejected to a category (default /not default). In addition, we will compare to a scenario where the rejection results from random decision-making, experiment five rejection rates, and see the effect of setting to default vs. not default. We found that doing lightGBM to infer the labels had a lower F1 score, AUC, and profit for the bank. As such, the bank should set all rejected to a category. Additionally, we found that setting all to default has a higher recall in the rejected population and higher profit. Moreover, a lower rejection rate increases profits.
- Simplified, high yielding extraction of xylan/xylo-oligosaccharides from palmaria palmata: the importance of the algae preservation treatmentPublication . Coelho, Diogo; Costa, Diogo Félix; Barroca, Mário; Cunha, Sara Alexandra; Pintado, Maria Manuela; Abreu, Helena; Martins, Margarida; Collins, TonyThe complex plant cell wall heteropolysaccharide xylan, and its breakdown products xylo-oligosaccharides and xylose, are value-added compounds with a plethora of potential applications in diverse areas. They are nonetheless currently poorly exploited, with a major bottleneck being the unavailability of efficient, low-cost, high-yield production processes. The major objective of the present study is to identify and characterise a high-yield process for the preparation of highly pure xylan/XOS products from the macroalga Palmaria palmata. Currently, most xylan is extracted from land-sourced lignocellulosic feedstocks, but we take advantage of the high xylan content, xylan aqueous solubility, lignin-free nature, weakly linked cell wall matrix, and sustainability of the macroalga to identify a simple, sustainable, high-yield, novel-xylan-structure extraction process. This is composed of five steps: alga oven drying, milling, aqueous extraction, centrifugation, and dialysis, and we show that the alga preservation step plays a critical role in component extractability, with oven drying at high temperatures, ~100 °C, enhancing the subsequent aqueous extraction process, and providing for xylan yields as high as 80% of a highly pure (~90%) xylan product. The process developed herein and the insights gained will promote a greater availability of these bioactive compounds and open up their application potential.