While Machine Learning significantly boosts the performance of predictive models, its efficacy varies across different data dimensions. It is essential to cluster time series data of similar characteristics, particularly in the financial sector. However, clustering financial time series data poses considerable challenges due to the market’s inherent complexity and multidimensionality. To address these issues, our study introduces a novel clustering framework that leverages autoencoders for a compressed yet informative representation of financial time series. We rigorously evaluate our approach through multiple dimensionality reduction and clustering algorithms, applying it to key financial indices, including IBEX-35, CAC-40, DAX-30, S&P 500, and FTSE 100. Our findings consistently demonstrate that incorporating autoencoders significantly enhances the granularity and quality of clustering, effectively isolating distinct categories of financial time series. Our findings carry significant ramifications for the financial industry. By refining clustering methodologies, we set the stage for increasingly accurate financial predictive models, offering valuable insights for optimizing investment strategies and enhancing risk management.

Defects in textured materials present a great variability, usually requiring ad-hoc solutions for each specific case. This research work proposes a solution that combines two machine learning-based approaches, convolutional autoencoders, CA; one class support vector machines, SVM. Both methods are trained using only defect free textured images for each type of analyzed texture, labeling the samples for the SVMs in an automatic way. This work is based on two image processing streams using image sensors: (1) the CA first processes the incoming image from the input to the output, producing a reconstructed image, from which a measurement of correct or defective image is obtained; (2) the second process uses the latent layer information as input to the SVM to produce a measurement of classification. Both measurements are effectively combined, making an additional research contribution. The results obtained achieve a percentage of success of 92% on average, outperforming results of previous works.

Metallographic analyses of nodular iron casting methods are based on visual comparisons according to measuring standards. Specifically, the microstructure is analyzed in a subjective manner by comparing the extracted image from the microscope to pre-defined image templates. The achieved classifications can be confused, due to the fact that the features extracted by a human being could be interpreted differently depending on many variables, such as the conditions of the observer. In particular, this kind of problem represents an uncertainty when classifying metallic properties, which can influence the integrity of castings that play critical roles in safety devices or structures. Although there are existing solutions working with extracted images and applying some computer vision techniques to manage the measurements of the microstructure, those results are not too accurate. In fact, they are not able to characterize all specific features of the image and, they cannot be adapted to several characterization methods depending on the specific regulation or customer. Hence, in order to solve this problem, we propose a framework to improve and automatize the evaluations by combining classical machine vision techniques for feature extraction and deep learning technologies, to objectively make classifications. To adapt to the real analysis environments, all included inputs in our models were gathered directly from the historical repository of metallurgy from the Azterlan Research Centre (labeled using expert knowledge from engineers). The proposed approach concludes that these techniques (a classification under a pipeline of deep neural networks and the quality classification using an ANN classifier) are viable to carry out the extraction and classification of metallographic features with great accuracy and time, and it is possible to deploy software with the models to work on real-time situations. Moreover, this method provides a direct way to classify the metallurgical quality of the molten metal, allowing us to determine the possible behaviors of the final produced parts.

While machine learning's role in financial trading has advanced considerably, algorithmic transparency and explainability challenges still exist. This research enriches prior studies focused on high‐frequency financial data prediction by introducing an explainable reinforcement learning model for portfolio management. This model transcends basic asset prediction, formulating concrete, actionable trading strategies. The methodology is applied in a custom trading environment mimicking the CAC‐40 index's financial conditions, allowing the model to adapt dynamically to market changes based on iterative learning from historical data. Empirical findings reveal that the model outperforms an equally weighted portfolio in out‐of‐sample tests. The study offers a dual contribution: it elevates algorithmic planning while significantly boosting transparency and interpretability in financial machine learning. This approach tackles the enduring ‘black‐box’ issue and provides a holistic, transparent framework for managing investment portfolios.