Search Results (3)

Financial time-series labeling remains fundamentally limited by three critical deficiencies: temporal rigidity (fixed horizons regardless of market conditions), scale blindness (single-resolution analysis), and correlation-causation conflation. These limitations cause systematic failure during regime shifts. We introduce Adaptive Event-Driven Labeling (AEDL), integrating three core innovations: (1) multi-scale temporal analysis capturing hierarchical market patterns across five time resolutions, (2) causal inference using Granger causality and transfer entropy to filter spurious correlations, and (3) model-agnostic meta-learning (MAML) for adaptive parameter optimization. The framework outputs calibrated probability distributions enabling uncertainty-aware trading strategies. Evaluation on 16 assets spanning 25 years (2000–2025) with rigorous out-of-sample validation demonstrates substantial improvements: AEDL achieves average Sharpe ratio of 0.48 (across all models and assets) while baseline methods average near-zero or negative (Fixed Horizon: −0.29, Triple Barrier: −0.03, Trend Scanning: 0.00). Systematic ablation experiments on a 12-asset subset reveal that selective innovation deployment outperforms both minimal baselines and maximal integration: removing causal inference improves performance to 0.65 Sharpe while maintaining full asset coverage (12/12), whereas adding attention mechanisms reduces applicability to 2/12 assets due to compound filtering effects. These findings demonstrate that judicious component selection outperforms kitchen-sink approaches, with peak individual asset performance exceeding 3.0 Sharpe. Wilcoxon tests confirm statistically significant improvements over Fixed Horizon baseline (p = 0.0024). Full article

The accident risk of severe (≥5 fatalities) accidents in fossil energy chains (Coal, Oil and Natural Gas) is analyzed. The full chain risk is assessed for Organization for Economic Co-operation and Development (OECD), 28 Member States of the European Union (EU28) and non-OECD countries. Furthermore, for Coal, Chinese data are analysed separately for three different periods, i.e., 1994–1999, 2000–2008 and 2009–2016, due to different data sources, and highly incomplete data prior to 1994. A Bayesian Model Averaging (BMA) is applied to investigate the risk and associated uncertainties of a comprehensive accident data set from the Paul Scherrer Institute’s ENergy-related Severe Accident Database (ENSAD). By means of BMA, frequency and severity distributions were established, and a final posterior distribution including model uncertainty is constructed by a weighted combination of the different models. The proposed approach, by dealing with lack of data and lack of knowledge, allows for a general reduction of the uncertainty in the calculated risk indicators, which is beneficial for informed decision-making strategies under uncertainty. Full article

The impacts of energy accidents are of primary interest for risk and resilience analysts, decision makers, and the general public. They can cause human health and environmental impacts, economic and societal losses, which justifies the interest in developing models to mitigate these adverse outcomes. We present a classification model for sorting energy accidents in the natural gas sector into hazard classes, according to their potential fatalities. The model is built on decision rules, which are knowledge blocks in the form of “if (condition), then (classification to hazard class x)”. They were extracted by the rough sets method using natural gas accident data from 1970–2016 of the Energy-related Severe Accident Database (ENSAD) of the Paul Scherrer Institut (PSI), the most authoritative information source for accidents in the energy sector. This was the first attempt to explore the relationships between the descriptors of energy accidents and the consequence (fatalities). The model was applied to a set of hypothetical accidents to show how the decision-making process could be supported when there is an interest in knowing which class (i.e., low, medium, high) of fatalities an energy accident could cause. The successful use of this approach in the natural gas sector proves that it can be also adapted for other energy chains, such as oil and coal. Full article