Precise estimation of cardiac patients' current and future comorbidities is an important factor in prioritizing continuous physiological monitoring and new therapies. ML models have shown satisfactory performance in short-term mortality prediction of patients with heart disease, while their utility in long-term predictions is limited. This study aims to investigate the performance of tree-based ML models on long-term mortality prediction and the effect of two recently introduced biomarkers on long-term mortality. This study utilized publicly available data from CCHIA at the Ministry of Health and Welfare, Taiwan, China. Medical records were used to gather demographic and clinical data, including age, gender, BMI, percutaneous coronary intervention (PCI) status, and comorbidities such as hypertension, dyslipidemia, ST-segment elevation myocardial infarction (STEMI), and non-STEMI. Using medical and demographic records as well as two recently introduced biomarkers, brachial pre-ejection period (bPEP) and brachial ejection time (bET), collected from 139 patients with acute myocardial infarction, we investigated the performance of advanced ensemble tree-based ML algorithms (random forest, AdaBoost, and XGBoost) to predict all-cause mortality within 14 years. The developed ML models achieved significantly better performance compared to the baseline LR (C-Statistic, 0.80 for random forest, 0.79 for AdaBoost, and 0.78 for XGBoost, vs 0.77 for LR) (P-RF<0.001, PAdaBoost<0.001, PXGBoost<0.05). Adding bPEP and bET to our feature set significantly improved the algorithms' performance, leading to an absolute increase in C-Statistic of up to 0.03 (C-Statistic, 0.83 for random forest, 0.82 for AdaBoost, and 0.80 for XGBoost, vs 0.74 for LR) (P-RF<0.001, PAdaBoost<0.001, PXGBoost<0.05). This advancement may enable better treatment prioritization for high-risk individuals.

Music popularity prediction has garnered significant attention in both industry and academia, fuelled by the rise of data-driven algorithms and streaming platforms like Spotify. This study aims to explore the predictive power of various machine learning models in forecasting song popularity using a dataset comprising 30,000 songs spanning different genres from 1957 to 2020. Methods: We employ Ordinary Least Squares (OLS), Multivariate Adaptive Regression Splines (MARS), Random Forest, and XGBoost algorithms to analyse song characteristics and their impact on popularity. Results: Ordinary Least Squares (OLS) regression analysis reveals genre as the primary influencer of popularity, with notable trends over time. MARS modelling highlights the complex relationship between variables, particularly with features like instrumentalness and duration. Random Forest and XGBoost models underscore the importance of genre, especially EDM, in predicting popularity. Despite variations in performance, Random Forest emerges as the most effective model, improving prediction accuracy by 7.1% compared to average scores. Despite the importance of genre, predicting song popularity remains challenging, as observed variations in music-related features suggest complex interactions between genre and other factors. Consequently, while certain characteristics like loudness and song duration may impact popularity scores, accurately predicting song success remains elusive.

We introduce an optimization-based reconstruction attack capable of completely or near-completely reconstructing a dataset utilized for training a random forest. Notably, our approach relies solely on information readily available in commonly used libraries such as scikit-learn. To achieve this, we formulate the reconstruction problem as a combinatorial problem under a maximum likelihood objective. We demonstrate that this problem is NP-hard, though solvable at scale using constraint programming -- an approach rooted in constraint propagation and solution-domain reduction. Through an extensive computational investigation, we demonstrate that random forests trained without bootstrap aggregation but with feature randomization are susceptible to a complete reconstruction. This holds true even with a small number of trees. Even with bootstrap aggregation, the majority of the data can also be reconstructed. These findings underscore a critical vulnerability inherent in widely adopted ensemble methods, warranting attention and mitigation. Although the potential for such reconstruction attacks has been discussed in privacy research, our study provides clear empirical evidence of their practicability.

The living-off-the-land (LOTL) offensive methodologies rely on the perpetration of malicious actions through chains of commands executed by legitimate applications, identifiable exclusively by analysis of system logs. LOTL techniques are well hidden inside the stream of events generated by common legitimate activities, moreover threat actors often camouflage activity through obfuscation, making them particularly difficult to detect without incurring in plenty of false alarms, even using machine learning. To improve the performance of models in such an harsh environment, we propose an augmentation framework to enhance and diversify the presence of LOTL malicious activity inside legitimate logs. Guided by threat intelligence, we generate a dataset by injecting attack templates known to be employed in the wild, further enriched by malleable patterns of legitimate activities to replicate the behavior of evasive threat actors. We conduct an extensive ablation study to understand which models better handle our augmented dataset, also manipulated to mimic the presence of model-agnostic evasion and poisoning attacks. Our results suggest that augmentation is needed to maintain high-predictive capabilities, robustness to attack is achieved through specific hardening techniques like adversarial training, and it is possible to deploy near-real-time models with almost-zero false alarms.

Human Activity Recognition (HAR) has been extensively studied, with recent emphasis on the implementation of advanced Machine Learning (ML) and Deep Learning (DL) algorithms for accurate classification. This study investigates the efficacy of two ML algorithms, eXtreme Gradient Boosting (XGBoost) and MiniRocket, in the realm of HAR using data collected from smartphone sensors. The experiments are conducted on a dataset obtained from the UCI repository, comprising accelerometer and gyroscope signals captured from 30 volunteers performing various activities while wearing a smartphone. The dataset undergoes preprocessing, including noise filtering and feature extraction, before being utilized for training and testing the classifiers. Monte Carlo cross-validation is employed to evaluate the models' robustness. The findings reveal that both XGBoost and MiniRocket attain accuracy, F1 score, and AUC values as high as 0.99 in activity classification. XGBoost exhibits a slightly superior performance compared to MiniRocket. Notably, both algorithms surpass the performance of other ML and DL algorithms reported in the literature for HAR tasks. Additionally, the study compares the computational efficiency of the two algorithms, revealing XGBoost's advantage in terms of training time. Furthermore, the performance of MiniRocket, which achieves accuracy and F1 values of 0.94, and an AUC value of 0.96 using raw data and utilizing only one channel from the sensors, highlights the potential of directly leveraging unprocessed signals. It also suggests potential advantages that could be gained by utilizing sensor fusion or channel fusion techniques. Overall, this research sheds light on the effectiveness and computational characteristics of XGBoost and MiniRocket in HAR tasks, providing insights for future studies in activity recognition using smartphone sensor data.

In the realm of consumer lending, accurate credit default prediction stands as a critical element in risk mitigation and lending decision optimization. Extensive research has sought continuous improvement in existing models to enhance customer experiences and ensure the sound economic functioning of lending institutions. This study responds to the evolving landscape of credit default prediction, challenging conventional models and introducing innovative approaches. By building upon foundational research and recent innovations, our work aims to redefine the standards of accuracy in credit default prediction, setting a new benchmark for the industry. To overcome these challenges, we present an Ensemble Methods framework comprising LightGBM, XGBoost, and LocalEnsemble modules, each making unique contributions to amplify diversity and improve generalization. By utilizing distinct feature sets, our methodology directly tackles limitations identified in previous studies, with the overarching goal of establishing a novel standard for credit default prediction accuracy. Our experimental findings validate the effectiveness of the ensemble model on the dataset, signifying substantial contributions to the field. This innovative approach not only addresses existing obstacles but also sets a precedent for advancing the accuracy and robustness of credit default prediction models.

As cyber-attacks become more sophisticated, improving the robustness of Machine Learning (ML) models must be a priority for enterprises of all sizes. To reliably compare the robustness of different ML models for cyber-attack detection in enterprise computer networks, they must be evaluated in standardized conditions. This work presents a methodical adversarial robustness benchmark of multiple decision tree ensembles with constrained adversarial examples generated from standard datasets. The robustness of regularly and adversarially trained RF, XGB, LGBM, and EBM models was evaluated on the original CICIDS2017 dataset, a corrected version of it designated as NewCICIDS, and the HIKARI dataset, which contains more recent network traffic. NewCICIDS led to models with a better performance, especially XGB and EBM, but RF and LGBM were less robust against the more recent cyber-attacks of HIKARI. Overall, the robustness of the models to adversarial cyber-attack examples was improved without their generalization to regular traffic being affected, enabling a reliable detection of suspicious activity without costly increases of false alarms.

We study the cost of parallelizing weak-to-strong boosting algorithms for learning, following the recent work of Karbasi and Larsen. Our main results are two-fold: - First, we prove a tight lower bound, showing that even "slight" parallelization of boosting requires an exponential blow-up in the complexity of training. Specifically, let $\gamma$ be the weak learner's advantage over random guessing. The famous \textsc{AdaBoost} algorithm produces an accurate hypothesis by interacting with the weak learner for $\tilde{O}(1 / \gamma^2)$ rounds where each round runs in polynomial time. Karbasi and Larsen showed that "significant" parallelization must incur exponential blow-up: Any boosting algorithm either interacts with the weak learner for $\Omega(1 / \gamma)$ rounds or incurs an $\exp(d / \gamma)$ blow-up in the complexity of training, where $d$ is the VC dimension of the hypothesis class. We close the gap by showing that any boosting algorithm either has $\Omega(1 / \gamma^2)$ rounds of interaction or incurs a smaller exponential blow-up of $\exp(d)$. -Complementing our lower bound, we show that there exists a boosting algorithm using $\tilde{O}(1/(t \gamma^2))$ rounds, and only suffer a blow-up of $\exp(d \cdot t^2)$. Plugging in $t = \omega(1)$, this shows that the smaller blow-up in our lower bound is tight. More interestingly, this provides the first trade-off between the parallelism and the total work required for boosting.

Gradient boosting of prediction rules is an efficient approach to learn potentially interpretable yet accurate probabilistic models. However, actual interpretability requires to limit the number and size of the generated rules, and existing boosting variants are not designed for this purpose. Though corrective boosting refits all rule weights in each iteration to minimise prediction risk, the included rule conditions tend to be sub-optimal, because commonly used objective functions fail to anticipate this refitting. Here, we address this issue by a new objective function that measures the angle between the risk gradient vector and the projection of the condition output vector onto the orthogonal complement of the already selected conditions. This approach correctly approximate the ideal update of adding the risk gradient itself to the model and favours the inclusion of more general and thus shorter rules. As we demonstrate using a wide range of prediction tasks, this significantly improves the comprehensibility/accuracy trade-off of the fitted ensemble. Additionally, we show how objective values for related rule conditions can be computed incrementally to avoid any substantial computational overhead of the new method.

Verifiable learning advocates for training machine learning models amenable to efficient security verification. Prior research demonstrated that specific classes of decision tree ensembles -- called large-spread ensembles -- allow for robustness verification in polynomial time against any norm-based attacker. This study expands prior work on verifiable learning from basic ensemble methods (i.e., hard majority voting) to advanced boosted tree ensembles, such as those trained using XGBoost or LightGBM. Our formal results indicate that robustness verification is achievable in polynomial time when considering attackers based on the $L_\infty$-norm, but remains NP-hard for other norm-based attackers. Nevertheless, we present a pseudo-polynomial time algorithm to verify robustness against attackers based on the $L_p$-norm for any $p \in \mathbb{N} \cup \{0\}$, which in practice grants excellent performance. Our experimental evaluation shows that large-spread boosted ensembles are accurate enough for practical adoption, while being amenable to efficient security verification.