Context. The classification of active galactic nuclei (AGNs) is a challenge in astrophysics. Variability features extracted from light curves offer a promising avenue for distinguishing AGNs and their subclasses. This approach would be very valuable in sight of the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST). Aims. Our goal is to utilize self-organizing maps (SOMs) to classify AGNs based on variability features and investigate how the use of different subsets of features impacts the purity and completeness of the resulting classifications. Methods. We derived a set of variability features from light curves, similar to those employed in previous studies, and applied SOMs to explore the distribution of AGNs subclasses. We conducted a comparative analysis of the classifications obtained with different subsets of features, focusing on the ability to identify different AGNs types. Results. Our analysis demonstrates that using SOMs with variability features yields a relatively pure AGNs sample, though completeness remains a challenge. In particular, Type 2 AGNs are the hardest to identify, as can be expected. These results represent a promising step toward the development of tools that may support AGNs selection in future large-scale surveys such as LSST.

With Artificial intelligence (AI) to aid or automate decision-making advancing rapidly, a particular concern is its fairness. In order to create reliable, safe and trustworthy systems through human-centred artificial intelligence (HCAI) design, recent efforts have produced user interfaces (UIs) for AI experts to investigate the fairness of AI models. In this work, we provide a design space exploration that supports not only data scientists but also domain experts to investigate AI fairness. Using loan applications as an example, we held a series of workshops with loan officers and data scientists to elicit their requirements. We instantiated these requirements into FairHIL, a UI to support human-in-the-loop fairness investigations, and describe how this UI could be generalized to other use cases. We evaluated FairHIL through a think-aloud user study. Our work contributes better designs to investigate an AI model's fairness-and move closer towards responsible AI.

In recent years, the increase in the usage and efficiency of Artificial Intelligence and, more in general, of Automated Decision-Making systems has brought with it an increasing and welcome awareness of the risks associated with such systems. One of such risks is that of perpetuating or even amplifying bias and unjust disparities present in the data from which many of these systems learn to adjust and optimise their decisions. This awareness has on the one hand encouraged several scientific communities to come up with more and more appropriate ways and methods to assess, quantify, and possibly mitigate such biases and disparities. On the other hand, it has prompted more and more layers of society, including policy makers, to call for fair algorithms. We believe that while many excellent and multidisciplinary research is currently being conducted, what is still fundamentally missing is the awareness that having fair algorithms is per se a nearly meaningless requirement that needs to be complemented with many additional social choices to become actionable. Namely, there is a hiatus between what the society is demanding from Automated Decision-Making systems, and what this demand actually means in real-world scenarios. In this work, we outline the key features of such a hiatus and pinpoint a set of crucial open points that we as a society must address in order to give a concrete meaning to the increasing demand of fairness in Automated Decision-Making systems.

The Portfolio Optimization task has long been studied in the Financial Services literature as a procedure to identify the basket of assets that satisfy desired conditions on the expected return and the associated risk. A well-known approach to tackle this task is the maximization of the Sharpe Ratio, achievable with a problem reformulation as Quadratic Programming. While the sole Sharpe Ratio could be efficiently optimized via classical solvers, in business scenarios it is common that multiple additional needs arise, which have to be integrated in the optimization model as either new constraints or objective function terms. Then, in general, the problem may become non-convex and hence could potentially be not efficiently solvable via classical techniques anymore. One example of such additional objective function term consists of maximizing a diversification measure penalizing portfolios holding significant portions of investments on assets belonging to the same sector, while favouring solutions that diversify over multiple sectors. The problem of optimizing both the Sharpe Ratio and a diversification term can be mapped to a QUBO and be solved via quantum annealing devices or Hybrid Computing approaches, which are expected to find high quality solutions. We propose a new QUBO formulation for the task described and provide the mathematical details and required assumptions, showing the ease of modeling the optimization as QUBO against the effort that would be required by classical strategies. We derive results via the available QUBO solvers, as well as discussing the behaviour of Hybrid approaches to tackle large scale problems in the near term. We finally elaborate on the results showing the trade-off between the observed values of the portfolio's Sharpe Ratio and diversification, as a natural consequence of solving a multi-objective optimization problem.

Name Entity Disambiguation is the Natural Language Processing task of identifying textual records corresponding to the same Named Entity, i.e. real-world entities represented as a list of attributes (names, places, organisations, etc.). In this work, we face the task of disambiguating companies on the basis of their written names. We propose a Siamese LSTM Network approach to extract -- via supervised learning -- an embedding of company name strings in a (relatively) low dimensional vector space and use this representation to identify pairs of company names that actually represent the same company (i.e. the same Entity). Given that the manual labelling of string pairs is a rather onerous task, we analyse how an Active Learning approach to prioritise the samples to be labelled leads to a more efficient overall learning pipeline. With empirical investigations, we show that our proposed Siamese Network outperforms several benchmark approaches based on standard string matching algorithms when enough labelled data are available. Moreover, we show that Active Learning prioritisation is indeed helpful when labelling resources are limited, and let the learning models reach the out-of-sample performance saturation with less labelled data with respect to standard (random) data labelling approaches.

Environmental, Social, and Governance (ESG) datasets are frequently plagued by significant data gaps, leading to inconsistencies in ESG ratings due to varying imputation methods. This paper explores the application of established machine learning techniques for imputing missing data in a real-world ESG dataset, emphasizing the quantification of uncertainty through prediction intervals. By employing multiple imputation strategies, this study assesses the robustness of imputation methods and quantifies the uncertainty associated with missing data. The findings highlight the importance of probabilistic machine learning models in providing better understanding of ESG scores, thereby addressing the inherent risks of wrong ratings due to incomplete data. This approach improves imputation practices to enhance the reliability of ESG ratings.

In recent years, the problem of addressing fairness in Machine Learning (ML) and automatic decision-making has attracted a lot of attention in the scientific communities dealing with Artificial Intelligence. A plethora of different definitions of fairness in ML have been proposed, that consider different notions of what is a "fair decision" in situations impacting individuals in the population. The precise differences, implications and "orthogonality" between these notions have not yet been fully analyzed in the literature. In this work, we try to make some order out of this zoo of definitions.

With Artificial intelligence (AI) to aid or automate decision-making advancing rapidly, a particular concern is its fairness. In order to create reliable, safe and trustworthy systems through human-centred artificial intelligence (HCAI) design, recent efforts have produced user interfaces (UIs) for AI experts to investigate the fairness of AI models. In this work, we provide a design space exploration that supports not only data scientists but also domain experts to investigate AI fairness. Using loan applications as an example, we held a series of workshops with loan officers and data scientists to elicit their requirements. We instantiated these requirements into FairHIL, a UI to support human-in-the-loop fairness investigations, and describe how this UI could be generalized to other use cases. We evaluated FairHIL through a think-aloud user study. Our work contributes better designs to investigate an AI model's fairness-and move closer towards responsible AI.

Explainable Artificial Intelligence (XAI) is a set of techniques that allows the understanding of both technical and non-technical aspects of Artificial Intelligence (AI) systems. XAI is crucial to help satisfying the increasingly important demand of \emph{trustworthy} Artificial Intelligence, characterized by fundamental characteristics such as respect of human autonomy, prevention of harm, transparency, accountability, etc. Within XAI techniques, counterfactual explanations aim to provide to end users a set of features (and their corresponding values) that need to be changed in order to achieve a desired outcome. Current approaches rarely take into account the feasibility of actions needed to achieve the proposed explanations, and in particular they fall short of considering the causal impact of such actions. In this paper, we present Counterfactual Explanations as Interventions in Latent Space (CEILS), a methodology to generate counterfactual explanations capturing by design the underlying causal relations from the data, and at the same time to provide feasible recommendations to reach the proposed profile. Moreover, our methodology has the advantage that it can be set on top of existing counterfactuals generator algorithms, thus minimising the complexity of imposing additional causal constrains. We demonstrate the effectiveness of our approach with a set of different experiments using synthetic and real datasets (including a proprietary dataset of the financial domain).

Machine learning applications are becoming increasingly pervasive in our society. Since these decision-making systems rely on data-driven learning, risk is that they will systematically spread the bias embedded in data. In this paper, we propose to analyze biases by introducing a framework for generating synthetic data with specific types of bias and their combinations. We delve into the nature of these biases discussing their relationship to moral and justice frameworks. Finally, we exploit our proposed synthetic data generator to perform experiments on different scenarios, with various bias combinations. We thus analyze the impact of biases on performance and fairness metrics both in non-mitigated and mitigated machine learning models.