Gianluca Bontempi

Danele Lunghi, Alkis Simitsis, Olivier Caelen et al.

Data economy relies on data-driven systems and complex machine learning applications are fueled by them. Unfortunately, however, machine learning models are exposed to fraudulent activities and adversarial attacks, which threaten their security and trustworthiness. In the last decade or so, the research interest on adversarial machine learning has grown significantly, revealing how learning applications could be severely impacted by effective attacks. Although early results of adversarial machine learning indicate the huge potential of the approach to specific domains such as image processing, still there is a gap in both the research literature and practice regarding how to generalize adversarial techniques in other domains and applications. Fraud detection is a critical defense mechanism for data economy, as it is for other applications as well, which poses several challenges for machine learning. In this work, we describe how attacks against fraud detection systems differ from other applications of adversarial machine learning, and propose a number of interesting directions to bridge this gap.

Théo Verhelst, Denis Mercier, Jeevan Shrestha et al.

Counterfactuals are central in causal human reasoning and the scientific discovery process. The uplift, also called conditional average treatment effect, measures the causal effect of some action, or treatment, on the outcome of an individual. This paper discusses how it is possible to derive bounds on the probability of counterfactual statements based on uplift terms. First, we derive some original bounds on the probability of counterfactuals and we show that tightness of such bounds depends on the information of the feature set on the uplift term. Then, we propose a point estimator based on the assumption of conditional independence between the counterfactual outcomes. The quality of the bounds and the point estimators are assessed on synthetic data and a large real-world customer data set provided by a telecom company, showing significant improvement over the state of the art.

Théo Verhelst, Robin Petit, Wouter Verbeke et al.

Despite the growing popularity of machine-learning techniques in decision-making, the added value of causal-oriented strategies with respect to pure machine-learning approaches has rarely been quantified in the literature. These strategies are crucial for practitioners in various domains, such as marketing, telecommunications, health care and finance. This paper presents a comprehensive treatment of the subject, starting from firm theoretical foundations and highlighting the parameters that influence the performance of the uplift and predictive approaches. The focus of the paper is on a binary outcome case and a binary action, and the paper presents a theoretical analysis of uplift modeling, comparing it with the classical predictive approach. The main research contributions of the paper include a new formulation of the measure of profit, a formal proof of the convergence of the uplift curve to the measure of profit ,and an illustration, through simulations, of the conditions under which predictive approaches still outperform uplift modeling. We show that the mutual information between the features and the outcome plays a significant role, along with the variance of the estimators, the distribution of the potential outcomes and the underlying costs and benefits of the treatment and the outcome.

Uchechukwu F. Njoku, Alberto Abelló, Besim Bilalli et al.

Many-Objective Feature Selection (MOFS) approaches use four or more objectives to determine the relevance of a subset of features in a supervised learning task. As a consequence, MOFS typically returns a large set of non-dominated solutions, which have to be assessed by the data scientist in order to proceed with the final choice. Given the multi-variate nature of the assessment, which may include criteria (e.g. fairness) not related to predictive accuracy, this step is often not straightforward and suffers from the lack of existing tools. For instance, it is common to make use of a tabular presentation of the solutions, which provide little information about the trade-offs and the relations between criteria over the set of solutions. This paper proposes an original methodology to support data scientists in the interpretation and comparison of the MOFS outcome by combining post-processing and visualisation of the set of solutions. The methodology supports the data scientist in the selection of an optimal feature subset by providing her with high-level information at three different levels: objectives, solutions, and individual features. The methodology is experimentally assessed on two feature selection tasks adopting a GA-based MOFS with six objectives (number of selected features, balanced accuracy, F1-Score, variance inflation factor, statistical parity, and equalised odds). The results show the added value of the methodology in the selection of the final subset of features.

Martin Colot, Cédric Simar, Guy Cheron et al.

Continuous estimation of high-dimensional finger kinematics from forearm surface electromyography (EMG) could enable natural control for hand prostheses, AR/XR interfaces, and teleoperation. However, the complexity of human hand gestures and the entanglement of forearm muscles make accurate recognition intrinsically challenging. Existing approaches typically reduce task complexity by relying on classification-based machine learning, limiting the controllable degrees of freedom and compromising on natural interaction. We present an end-to-end framework for continuous EMG-to-kinematics regression using only consumer-grade hardware. The framework combines an 8-channel EMG armband, a single webcam, and an automatic synchronization procedure, enabling the collection of the EMG Finger-Kinematics dataset (EMG-FK), a 10-h dataset of synchronized EMG and 15 finger joint angles from 20 participants performing rich, unconstrained right-hand motions. We also introduce the Temporal Riemannian Regressor (TRR), a lightweight GRU-based model that uses sequences of multi-band Riemannian covariance features to decode finger motion. Across EMG-FK and the public emg2pose benchmark, TRR outperforms state-of-the-art methods in both intra- and cross-subject evaluation. On EMG-FK, it reaches an average absolute error of $9.79 °\pm 1.48$ in intra-subject and $16.71 °\pm 3.97$ in cross-subject. Finally, we demonstrate real-time deployment on a Raspberry Pi 5 and intuitive control of a robotic hand; TRR runs at nearly 10 predictions/s and is roughly an order of magnitude faster than state-of-the-art approaches. Together, these contributions lower the barrier to reproducible, real-time EMG-based decoding of high-dimensional finger motion, and pave the way toward more natural and intuitive control of embedded EMG-based systems.

Alejandro Morales-Hernández, Fabrizio De Caroa, Gian Marco Paldino et al.

Decision support systems are essential for maintaining grid stability in low-carbon power systems, such as wind power plants, by providing real-time alerts to control room operators regarding potential events, including Wind Power Ramp Events (WPREs). These early warnings enable the timely initiation of more detailed system stability assessments and preventive actions. However, forecasting these events is challenging due to the inherent class imbalance in WPRE datasets, where ramp events are less frequent (typically less than 15\% of observed events) compared to normal conditions. Ignoring this characteristic undermines the performance of conventional machine learning models, which often favor the majority class. This paper introduces a novel methodology for WPRE forecasting as a multivariate time series classification task and proposes a data preprocessing strategy that extracts features from recent power observations and masks unavailable ramp information, making it integrable with traditional real-time ramp identification tools. Particularly, the proposed methodology combines majority-class undersampling and ensemble learning to enhance wind ramp event forecasting under class imbalance. Numerical simulations conducted on a real-world dataset demonstrate the superiority of our approach, achieving over 85% accuracy and 88% weighted F1 score, outperforming benchmark classifiers.

Davide Andrea Guastella, Alejandro Morales-Hernàndez, Bruno Cornelis et al.

Simulation is a valuable tool for traffic management experts to assist them in refining and improving transportation systems and anticipating the impact of possible changes in the infrastructure network before their actual implementation. Calibrating simulation models using traffic count data is challenging because of the complexity of the environment, the lack of data, and the uncertainties in traffic dynamics. This paper introduces a novel stochastic simulation-based traffic calibration technique. The novelty of the proposed method is: (i) it performs local traffic calibration, (ii) it allows calibrating simulated traffic in large-scale environments, (iii) it requires only the traffic count data. The local approach enables decentralizing the calibration task to reach near real-time performance, enabling the fostering of digital twins. Using only traffic count data makes the proposed method generic so that it can be applied in different traffic scenarios at various scales (from neighborhood to region). We assess the proposed technique on a model of Brussels, Belgium, using data from real traffic monitoring devices. The proposed method has been implemented using the open-source traffic simulator SUMO. Experimental results show that the traffic model calibrated using the proposed method is on average 16% more accurate than those obtained by the state-of-the-art methods, using the same dataset. We also make available the output traffic model obtained from real data.

Claudio Reggiani, Yann-Aël Le Borgne, Gianluca Bontempi

This paper describes a distributed MapReduce implementation of the minimum Redundancy Maximum Relevance algorithm, a popular feature selection method in bioinformatics and network inference problems. The proposed approach handles both tall/narrow and wide/short datasets. We further provide an open source implementation based on Hadoop/Spark, and illustrate its scalability on datasets involving millions of observations or features.

Théo Verhelst, Gianluca Bontempi

Uplift modeling estimates the causal effect of an intervention as the difference between potential outcomes under treatment and control, whereas counterfactual identification aims to recover the joint distribution of these potential outcomes (e.g., "Would this customer still have churned had we given them a marketing offer?"). This joint counterfactual distribution provides richer information than the uplift but is harder to estimate. However, the two approaches are synergistic: uplift models can be leveraged for counterfactual estimation. We propose a counterfactual estimator that fits a bivariate beta distribution to predicted uplift scores, yielding posterior distributions over counterfactual outcomes. Our approach requires no causal assumptions beyond those of uplift modeling. Simulations show the efficacy of the approach, which can be applied, for example, to the problem of customer churn in telecom, where it reveals insights unavailable to standard ML or uplift models alone.

Gianluca Bontempi

Intelligent agents rely on AI/ML functionalities to predict the consequence of possible actions and optimise the policy. However, the effort of the research community in addressing prediction accuracy has been so intense (and successful) that it created the illusion that the more accurate the learner prediction (or classification) the better would have been the final decision. Now, such an assumption is valid only if the (human or artificial) decision maker has complete knowledge of the utility of the possible actions. This paper argues that AI/ML community has taken so far a too unbalanced approach by devoting excessive attention to the estimation of the state (or target) probability to the detriment of accurate and reliable estimations of the utility. In particular, few evidence exists about the impact of a wrong utility assessment on the resulting expected utility of the decision strategy. This situation is creating a substantial gap between the expectations and the effective impact of AI solutions, as witnessed by recent criticisms and emphasised by the regulatory legislative efforts. This paper aims to study this gap by quantifying the sensitivity of the expected utility to the utility uncertainty and comparing it to the one due to probability estimation. Theoretical and simulated results show that an inaccurate utility assessment may as (and sometimes) more harmful than a poor probability estimation. The final recommendation to the community is then to undertake a focus shift from a pure accuracy-driven (or obsessed) approach to a more utility-aware methodology.

Martin Colot, Cédric Simar, Mathieu Petieau et al.

Electromyograms (EMG)-based hand gesture recognition systems are a promising technology for human/machine interfaces. However, one of their main limitations is the long calibration time that is typically required to handle new users. The paper discusses and analyses the challenge of cross-subject generalization thanks to an original dataset containing the EMG signals of 14 human subjects during hand gestures. The experimental results show that, though an accurate generalization based on pooling multiple subjects is hardly achievable, it is possible to improve the cross-subject estimation by identifying a robust low-dimensional subspace for multiple subjects and aligning it to a target subject. A visualization of the subspace enables us to provide insights for the improvement of cross-subject generalization with EMG signals.

Théo Verhelst, Denis Mercier, Jeevan Shrestha et al.

Uplift modeling, also known as individual treatment effect (ITE) estimation, is an important approach for data-driven decision making that aims to identify the causal impact of an intervention on individuals. This paper introduces a new benchmark dataset for uplift modeling focused on churn prediction, coming from a telecom company in Belgium, Orange Belgium. Churn, in this context, refers to customers terminating their subscription to the telecom service. This is the first publicly available dataset offering the possibility to evaluate the efficiency of uplift modeling on the churn prediction problem. Moreover, its unique characteristics make it more challenging than the few other public uplift datasets.

Daniele Lunghi, Yannick Molinghen, Alkis Simitsis et al.

Adversarial attacks pose a significant threat to data-driven systems, and researchers have spent considerable resources studying them. Despite its economic relevance, this trend largely overlooked the issue of credit card fraud detection. To address this gap, we propose a new threat model that demonstrates the limitations of existing attacks and highlights the necessity to investigate new approaches. We then design a new adversarial attack for credit card fraud detection, employing reinforcement learning to bypass classifiers. This attack, called FRAUD-RLA, is designed to maximize the attacker's reward by optimizing the exploration-exploitation tradeoff and working with significantly less required knowledge than competitors. Our experiments, conducted on three different heterogeneous datasets and against two fraud detection systems, indicate that FRAUD-RLA is effective, even considering the severe limitations imposed by our threat model.

Anaïs Halin, Sébastien Piérard, Renaud Vandeghen et al.

Characterizing domains is essential for models analyzing dynamic environments, as it allows them to adapt to evolving conditions or to hand the task over to backup systems when facing conditions outside their operational domain. Existing solutions typically characterize a domain by solving a regression or classification problem, which limits their applicability as they only provide a limited summarized description of the domain. In this paper, we present a novel approach to domain characterization by characterizing domains as probability distributions. Particularly, we develop a method to predict the likelihood of different weather conditions from images captured by vehicle-mounted cameras by estimating distributions of physical parameters using normalizing flows. To validate our proposed approach, we conduct experiments within the context of autonomous vehicles, focusing on predicting the distribution of weather parameters to characterize the operational domain. This domain is characterized by physical parameters (absolute characterization) and arbitrarily predefined domains (relative characterization). Finally, we evaluate whether a system can safely operate in a target domain by comparing it to multiple source domains where safety has already been established. This approach holds significant potential, as accurate weather prediction and effective domain adaptation are crucial for autonomous systems to adjust to dynamic environmental conditions.

Gianluca Bontempi

Though intelligent agents are supposed to improve human experience (or make it more efficient), it is hard from a human perspective to grasp the ethical values which are explicitly or implicitly embedded in an agent behaviour. This is the well-known problem of alignment, which refers to the challenge of designing AI systems that align with human values, goals and preferences. This problem is particularly challenging since most human ethical considerations refer to \emph{incommensurable} (i.e. non-measurable and/or incomparable) values and criteria. Consider, for instance, a medical agent prescribing a treatment to a cancerous patient. How could it take into account (and/or weigh) incommensurable aspects like the value of a human life and the cost of the treatment? Now, the alignment between human and artificial values is possible only if we define a common space where a metric can be defined and used. This paper proposes to extend to ethics the conventional Anything2vec approach, which has been successful in plenty of similar and hard-to-quantify domains (ranging from natural language processing to recommendation systems and graph analysis). This paper proposes a way to map an automatic agent decision-making (or control law) strategy to a multivariate vector representation, which can be used to compare and assess the alignment with human values. The Ethics2Vec method is first introduced in the case of an automatic agent performing binary decision-making. Then, a vectorisation of an automatic control law (like in the case of a self-driving car) is discussed to show how the approach can be extended to automatic control settings.

Gian Marco Paldino, Gianluca Bontempi

Discovering causal relationships in complex multivariate time series is a fundamental scientific challenge. Traditional methods often falter, either by relying on restrictive linear assumptions or on conditional independence tests that become uninformative in the presence of intricate, non-linear dynamics. This paper proposes a new paradigm, shifting from statistical testing to pattern recognition. We hypothesize that a causal link creates a persistent and learnable asymmetry in the flow of information through a system's temporal graph, even when clear conditional independencies are obscured. We introduce Temporal Dependency to Causality (TD2C), a supervised learning framework that operationalizes this hypothesis. TD2C learns to recognize these complex causal signatures from a rich set of information-theoretic and statistical descriptors. Trained exclusively on a diverse collection of synthetic time series, TD2C demonstrates remarkable zero-shot generalization to unseen dynamics and established, realistic benchmarks. Our results show that TD2C achieves state-of-the-art performance, consistently outperforming established methods, particularly in high-dimensional and non-linear settings. By reframing the discovery problem, our work provides a robust and scalable new tool for uncovering causal structures in complex systems.

Pascal Tribel, Gianluca Bontempi

Seismic data is often sparse and unevenly distributed due to the high costs and logistical challenges associated with deploying physical seismometers, limiting the application of Machine Learning (ML) in earthquake analysis. While simulation methods exist, no tool allows the generation of large datasets containing simulated measurements of the ground motion. To address this gap, we introduce PyAWD, a Python library designed to generate high-resolution synthetic datasets simulating spatio-temporal acoustic wave propagation in both two-dimensional and three-dimensional heterogeneous media. By allowing fine control over parameters such as the wave speed, external forces, spatial and temporal discretization, and media composition, PyAWD enables the creation of ML-scale datasets that capture the complexity of seismic wave behavior. We illustrate the library's potential with an epicenter retrieval task, showcasing its suitability for designing complex, accurate seismic problems that require advanced ML approaches in the absence or lack of dense real-world data. We also show the usefulness of our tool to tackle the problem of data budgeting in the framework of epicenter retrieval.

Wissam Siblini, Guillaume Coter, Rémy Fabry et al.

The dark face of digital commerce generalization is the increase of fraud attempts. To prevent any type of attacks, state-of-the-art fraud detection systems are now embedding Machine Learning (ML) modules. The conception of such modules is only communicated at the level of research and papers mostly focus on results for isolated benchmark datasets and metrics. But research is only a part of the journey, preceded by the right formulation of the business problem and collection of data, and followed by a practical integration. In this paper, we give a wider vision of the process, on a case study of transfer learning for fraud detection, from business to research, and back to business.

Fabirzio Carcillo, Yann-Aël Le Borgne, Olivier Caelen et al.

Credit card fraud detection is a very challenging problem because of the specific nature of transaction data and the labeling process. The transaction data is peculiar because they are obtained in a streaming fashion, they are strongly imbalanced and prone to non-stationarity. The labeling is the outcome of an active learning process, as every day human investigators contact only a small number of cardholders (associated to the riskiest transactions) and obtain the class (fraud or genuine) of the related transactions. An adequate selection of the set of cardholders is therefore crucial for an efficient fraud detection process. In this paper, we present a number of active learning strategies and we investigate their fraud detection accuracies. We compare different criteria (supervised, semi-supervised and unsupervised) to query unlabeled transactions. Finally, we highlight the existence of an exploitation/exploration trade-off for active learning in the context of fraud detection, which has so far been overlooked in the literature.

Gianluca Bontempi, Maxime Flauder

The relationship between statistical dependency and causality lies at the heart of all statistical approaches to causal inference. Recent results in the ChaLearn cause-effect pair challenge have shown that causal directionality can be inferred with good accuracy also in Markov indistinguishable configurations thanks to data driven approaches. This paper proposes a supervised machine learning approach to infer the existence of a directed causal link between two variables in multivariate settings with $n>2$ variables. The approach relies on the asymmetry of some conditional (in)dependence relations between the members of the Markov blankets of two variables causally connected. Our results show that supervised learning methods may be successfully used to extract causal information on the basis of asymmetric statistical descriptors also for $n>2$ variate distributions.

Boris Iolis, Gianluca Bontempi

We demonstrate a method to optimize the combination of distinct components in a paragraph retrieval system. Our system makes use of several indices, query generators and filters, each of them potentially contributing to the quality of the returned list of results. The components are combined with a weighed sum, and we optimize the weights using a heuristic optimization algorithm. This allows us to maximize the quality of our results, but also to determine which components are most valuable in our system. We evaluate our approach on the paragraph selection task of a Question Answering dataset.