RFX (Random Forests X), where X stands for compression or quantization, presents a production-ready implementation of Breiman and Cutler's Random Forest classification methodology in Python. RFX v1.0 provides complete classification: out-of-bag error estimation, overall and local importance measures, proximity matrices with QLORA compression, case-wise analysis, and interactive visualization (rfviz)--all with CPU and GPU acceleration. Regression, unsupervised learning, CLIQUE importance, and RF-GAP proximity are planned for v2.0. This work introduces four solutions addressing the proximity matrix memory bottleneck limiting Random Forest analysis to ~60,000 samples: (1) QLORA (Quantized Low-Rank Adaptation) compression for GPU proximity matrices, reducing memory from 80GB to 6.4MB for 100k samples (12,500x compression with INT8 quantization) while maintaining 99% geometric structure preservation, (2) CPU TriBlock proximity--combining upper-triangle storage with block-sparse thresholding--achieving 2.7x memory reduction with lossless quality, (3) SM-aware GPU batch sizing achieving 95% GPU utilization, and (4) GPU-accelerated 3D MDS visualization computing embeddings directly from low-rank factors using power iteration. Validation across four implementation modes (GPU/CPU x case-wise/non-case-wise) demonstrates correct implementation. GPU achieves 1.4x speedup over CPU for overall importance with 500+ trees. Proximity computation scales from 1,000 to 200,000+ samples (requiring GPU QLORA), with CPU TriBlock filling the gap for medium-scale datasets (10K-50K samples). RFX v1.0 eliminates the proximity memory bottleneck, enabling proximity-based Random Forest analysis on datasets orders of magnitude larger than previously feasible. Open-source production-ready classification following Breiman and Cutler's original methodology.

This study investigates the application of the Light Gradient Boosting Machine (LGBM) model for both deterministic and probabilistic forecasting of Bitcoin realized volatility. Utilizing a comprehensive set of 69 predictors -- encompassing market, behavioral, and macroeconomic indicators -- we evaluate the performance of LGBM-based models and compare them with both econometric and machine learning baselines. For probabilistic forecasting, we explore two quantile-based approaches: direct quantile regression using the pinball loss function, and a residual simulation method that transforms point forecasts into predictive distributions. To identify the main drivers of volatility, we employ gain-based and permutation feature importance techniques, consistently highlighting the significance of trading volume, lagged volatility measures, investor attention, and market capitalization. The results demonstrate that LGBM models effectively capture the nonlinear and high-variance characteristics of cryptocurrency markets while providing interpretable insights into the underlying volatility dynamics.

Clinical and genomic models are both used to predict breast cancer outcomes, but they are often combined using simple linear rules that do not account for how their risk scores relate, especially at the extremes. Using the METABRIC breast cancer cohort, we studied whether directly modeling the joint relationship between clinical and genomic machine learning risk scores could improve risk stratification for 5-year cancer-specific mortality. We created a binary 5-year cancer-death outcome and defined two sets of predictors: a clinical set (demographic, tumor, and treatment variables) and a genomic set (gene-expression $z$-scores). We trained several supervised classifiers, such as Random Forest and XGBoost, and used 5-fold cross-validated predicted probabilities as unbiased risk scores. These scores were converted to pseudo-observations on $(0,1)^2$ to fit Gaussian, Clayton, and Gumbel copulas. Clinical models showed good discrimination (AUC 0.783), while genomic models had moderate performance (AUC 0.681). The joint distribution was best captured by a Gaussian copula (bootstrap $p=0.997$), which suggests a symmetric, moderately strong positive relationship. When we grouped patients based on this relationship, Kaplan-Meier curves showed clear differences: patients who were high-risk in both clinical and genomic scores had much poorer survival than those high-risk in only one set. These results show that copula-based fusion works in real-world cohorts and that considering dependencies between scores can better identify patient subgroups with the worst prognosis.

Advances in technology are transforming sustainable cattle farming practices, with electronic feeding systems generating big longitudinal datasets on individual animal feed intake, offering the possibility for autonomous precision livestock systems. However, the literature still lacks a methodology that fully leverages these longitudinal big data to accurately predict feed intake accounting for environmental conditions. To fill this gap, we developed an AI-based framework to accurately predict feed intake of individual animals and pen-level aggregation. Data from 19 experiments (>16.5M samples; 2013-2024) conducted at Nancy M. Cummings Research Extension & Education Center (Carmen, ID) feedlot facility and environmental data from AgriMet Network weather stations were used to develop two novel environmental indices: InComfort-Index, based solely on meteorological variables, showed good predictive capability for thermal comfort but had limited ability to predict feed intake; EASI-Index, a hybrid index integrating environmental variables with feed intake behavior, performed well in predicting feed intake but was less effective for thermal comfort. Together with the environmental indices, machine learning models were trained and the best-performing machine learning model (XGBoost) accuracy was RMSE of 1.38 kg/day for animal-level and only 0.14 kg/(day-animal) at pen-level. This approach provides a robust AI-based framework for predicting feed intake in individual animals and pens, with potential applications in precision management of feedlot cattle, through feed waste reduction, resource optimization, and climate-adaptive livestock management.

Efficiently and meaningfully estimating prediction uncertainty is important for exploration in active learning campaigns in materials discovery, where samples with high uncertainty are interpreted as containing information missing from the model. In this work, the effect of different uncertainty estimation and calibration methods are evaluated for active learning when using ensembles of ALIGNN, eXtreme Gradient Boost, Random Forest, and Neural Network model architectures. We compare uncertainty estimates from ALIGNN deep ensembles to loss landscape uncertainty estimates obtained for solubility, bandgap, and formation energy prediction tasks. We then evaluate how the quality of the uncertainty estimate impacts an active learning campaign that seeks model generalization to out-of-distribution data. Uncertainty calibration methods were found to variably generalize from in-domain data to out-of-domain data. Furthermore, calibrated uncertainties were generally unsuccessful in reducing the amount of data required by a model to improve during an active learning campaign on out-of-distribution data when compared to random sampling and uncalibrated uncertainties. The impact of poor-quality uncertainty persists for random forest and eXtreme Gradient Boosting models trained on the same data for the same tasks, indicating that this is at least partially intrinsic to the data and not due to model capacity alone. Analysis of the target, in-distribution uncertainty, out-of-distribution uncertainty, and training residual distributions suggest that future work focus on understanding empirical uncertainties in the feature input space for cases where ensemble prediction variances do not accurately capture the missing information required for the model to generalize.

Embedded Sensing Group ESG Institute of Computer Science in V orarlberg ICV, University of St. Gallen HSG, Switzerland E-mail: leonardo.rossi@student.unisg.ch, Abstract--Triathlon training, which involves high-volume swimming, cycling, and running, places athletes at substantial risk for overuse injuries due to repetitive physiological stress. Current injury prediction approaches primarily rely on training load metrics, often neglecting critical factors such as sleep quality, stress, and individual lifestyle patterns that significantly influence recovery and injury susceptibility. We introduce a novel synthetic data generation framework tailored explicitly for triathlon. This framework generates physiologically plausible athlete profiles, simulates individualized training programs that incorporate periodization and load-management principles, and integrates daily-life factors such as sleep quality, stress levels, and recovery states. We evaluated machine learning models (LASSO, Random Forest, and XGBoost) showing high predictive performance (AUC up to 0.86), identifying sleep disturbances, heart rate variability, and stress as critical early indicators of injury risk. This wearable-driven approach not only enhances injury prediction accuracy but also provides a practical solution to overcoming real-world data limitations, offering a pathway toward a holistic, context-aware athlete monitoring. Triathlon is a demanding multi-sport discipline that combines swimming, cycling, and running.

Monitoring aquatic species, especially elusive ones like lobsters, presents challenges. This study focuses on Homarus gammarus (European lobster), a key species for fisheries and aquaculture, and leverages non-invasive Passive Acoustic Monitoring (PAM). Understanding lobster habitats, welfare, reproduction, sex, and age is crucial for management and conservation. While bioacoustic emissions have classified various aquatic species using Artificial Intelligence (AI) models, this research specifically uses H. gammarus bioacoustics (buzzing/carapace vibrations) to classify lobsters by age (juvenile/adult) and sex (male/female). The dataset was collected at Johnshaven, Scotland, using hydrophones in concrete tanks. We explored the efficacy of Deep Learning (DL) models (1D-CNN, 1D-DCNN) and six Machine Learning (ML) models (SVM, k-NN, Naive Bayes, Random Forest, XGBoost, MLP). Mel-frequency cepstral coefficients (MFCCs) were used as features. For age classification (adult vs. juvenile), most models achieved over 97% accuracy (Naive Bayes: 91.31%). For sex classification, all models except Naive Bayes surpassed 93.23%. These strong results demonstrate the potential of supervised ML and DL to extract age- and sex-related features from lobster sounds. This research offers a promising non-invasive PAM approach for lobster conservation, detection, and management in aquaculture and fisheries, enabling real-world edge computing applications for underwater species.

Feature selection is a key step in many tabular prediction problems, where multiple candidate variables may be redundant, noisy, or weakly informative. We investigate feature selection based on Kolmogorov-Arnold Networks (KANs), which parameterize feature transformations with splines and expose per-feature importance scores in a natural way. From this idea we derive four KAN-based selection criteria (coefficient norms, gradient-based saliency, and knockout scores) and compare them with standard methods such as LASSO, Random Forest feature importance, Mutual Information, and SVM-RFE on a suite of real and synthetic classification and regression datasets. Using average F1 and $R^2$ scores across three feature-retention levels (20%, 40%, 60%), we find that KAN-based selectors are generally competitive with, and sometimes superior to, classical baselines. In classification, KAN criteria often match or exceed existing methods on multi-class tasks by removing redundant features and capturing nonlinear interactions. In regression, KAN-based scores provide robust performance on noisy and heterogeneous datasets, closely tracking strong ensemble predictors; we also observe characteristic failure modes, such as overly aggressive pruning with an $\ell_1$ criterion. Stability and redundancy analyses further show that KAN-based selectors yield reproducible feature subsets across folds while avoiding unnecessary correlation inflation, ensuring reliable and non-redundant variable selection. Overall, our findings demonstrate that KAN-based feature selection provides a powerful and interpretable alternative to traditional methods, capable of uncovering nonlinear and multivariate feature relevance beyond sparsity or impurity-based measures.

Gradient Boosting Decision Tree (GBDT) is a popular machine learning algorithm, and has quite a few effective implementations such as XGBoost and pGBRT. Although many engineering optimizations have been adopted in these implementations, the efficiency and scalability are still unsatisfactory when the feature dimension is high and data size is large. A major reason is that for each feature, they need to scan all the data instances to estimate the information gain of all possible split points, which is very time consuming. To tackle this problem, we propose two novel techniques: \emph{Gradient-based One-Side Sampling} (GOSS) and \emph{Exclusive Feature Bundling} (EFB). With GOSS, we exclude a significant proportion of data instances with small gradients, and only use the rest to estimate the information gain. We prove that, since the data instances with larger gradients play a more important role in the computation of information gain, GOSS can obtain quite accurate estimation of the information gain with a much smaller data size. With EFB, we bundle mutually exclusive features (i.e., they rarely take nonzero values simultaneously), to reduce the number of features. We prove that finding the optimal bundling of exclusive features is NP-hard, but a greedy algorithm can achieve quite good approximation ratio (and thus can effectively reduce the number of features without hurting the accuracy of split point determination by much).

Gradient Boosting Decision Tree (GBDT) is a popular machine learning algorithm, and has quite a few effective implementations such as XGBoost and pGBRT. Although many engineering optimizations have been adopted in these implementations, the efficiency and scalability are still unsatisfactory when the feature dimension is high and data size is large. A major reason is that for each feature, they need to scan all the data instances to estimate the information gain of all possible split points, which is very time consuming.