Institution profile

University of Duisburg-Essen

Academic institutioneurope · de
Official website
Research library152linked papers
Opportunities0open roles
Selected work

Representative Papers

Online Distributional Regression

Jun 26, 2024

To address online probabilistic forecasting for large-scale streaming data, this paper proposes an incremental learning method that integrates online LASSO with the Generalized Additive Models for Location, Scale, and Shape (GAMLSS) framework—enabling, for the first time, real-time updating of regularized conditional distribution models capturing heteroscedasticity and higher-order moments. The method leverages online gradient optimization coupled with sparse regularization, achieving both statistical interpretability and substantial computational efficiency gains. Evaluated on day-ahead electricity price forecasting, it achieves state-of-the-art probabilistic forecast accuracy while reducing training time by over 80%, supporting millisecond-level dynamic calibration and industrial-grade real-time deployment. Key contributions include: (1) the first scalable online GAMLSS framework; (2) joint sparse estimation and progressive updating of distribution parameters; and (3) an open-source, high-performance Python implementation balancing modeling flexibility with engineering practicality.

1 citations1 influentialRead paper

Electricity Price Forecasting: Bridging Linear Models, Neural Networks and Online Learning

Jan 06, 2026arXiv.org

This study addresses the challenge of balancing prediction accuracy and computational efficiency in highly volatile electricity markets, where linear models fail to capture nonlinear dynamics and complex nonlinear models incur prohibitive computational costs. To overcome this limitation, the authors propose a novel multivariate architecture that deeply integrates linear and nonlinear feedforward neural networks, synergistically leveraging their respective strengths. The framework incorporates online learning and a forecast combination mechanism to effectively model the dynamic relationships between electricity prices and multiple exogenous factors—including wind and solar generation, load demand, fuel prices, and carbon prices. Extensive experiments on six years of data from six major European electricity markets demonstrate that the proposed method reduces RMSE by 12–13% and MAE by 15–18% compared to state-of-the-art models, while simultaneously achieving significantly lower computational overhead.

1 citationsRead paper

SemCAFE: When Named Entities make the Difference–Assessing Web Source Reliability through Entity-level Analytics

Apr 03, 2025Web Science Conference

To address the growing challenge of distinguishing credible from deceptive news in digital media—where semantic convergence between authentic and fabricated content obscures reliability—this paper proposes a news source credibility assessment method grounded in named entity semantic association. Departing from conventional approaches reliant on superficial textual features, our method uniquely integrates YAGO knowledge base–driven entity recognition, disambiguation, and semantic relation modeling into credibility classification, constructing article-level “semantic fingerprints” for fine-grained, interpretable reliability evaluation. We combine web page de-templating with robust NLP preprocessing to enhance feature extraction. Evaluated on a Ukraine crisis news dataset (46,020 credible vs. 3,407 unreliable samples), our approach achieves a 12% improvement in macro-F1 over the current state-of-the-art, demonstrating substantial gains in discriminative power and interpretability.

1 citationsRead paper

Online Multivariate Regularized Distributional Regression for High-dimensional Probabilistic Electricity Price Forecasting

Apr 03, 2025

Real-time decision-making in electricity markets demands short-term probabilistic price forecasting that simultaneously achieves high accuracy, computational efficiency, and interpretability. Method: We propose an online-updatable high-dimensional multivariate distributional regression model. It integrates multivariate distribution regression with online coordinate-descent LASSO to jointly model the mean, variance, and dependence structure of 24-hour day-ahead prices. A novel regularization strategy—based on dependency-complexity paths—enables dynamic sparsity learning and early stopping. We further introduce adaptive Copula modeling for time-varying dependencies and incorporate real-time marginal distribution estimation. Contribution/Results: Evaluated on the German day-ahead market, our model significantly outperforms baselines—including online univariate + static Copula and online LASSO-ARX—in both calibration and sharpness. Training speed improves by 80–400×, while maintaining high predictive accuracy and strong interpretability through sparse, physically meaningful feature selection.

1 citationsRead paper

A data-driven merit order: Learning a fundamental electricity price model

Jan 06, 2025

This paper addresses the limited interpretability of data-driven models and the insufficient fidelity of fundamental models in electricity price forecasting. We propose a novel data-driven marginal merit-order model that integrates structural economic principles with machine learning. Structurally grounded in classical merit-order theory—here innovatively embedded as a learnable special case—the model infers key parameters—including plant efficiency, bidding strategies, and available capacity—from historical market data via inverse modeling. It further introduces three original modules: hydroelectric scheduling, cross-border power flow modeling, and capacity underreporting correction. The resulting framework achieves both high predictive accuracy and strong economic interpretability. In empirical evaluation on the German day-ahead market, it significantly outperforms conventional fundamental models and state-of-the-art machine learning approaches. The model enables interpretable marginal technology identification, fuel-switching analysis, and unit-level generation attribution—bridging the gap between black-box forecasting and actionable market insights.

1 citationsRead paper
Recent publications

Latest Papers

Tactile Search: Enhancing Targeting in 3D Space

Sep 05, 2026

Visual search is crucial in daily life, from scanning for relevant information to spotting signs of danger. When sensory channels are overloaded or degraded, cognitive tasks can be supported by crossmodal information representations through vibrotactile cues. We introduce Tactile Search, an approach that uses modulation of frequency and amplitude of vibrations to the hands, for guiding attention to the location of objects in 3D space. We evaluated this approach in a competitive VR game where participants searched for targets using both vision and touch. Across two studies -- an in-the-wild demonstration (n=55) and a controlled laboratory experiment (n=28) -- we found that vibrotactile feedback significantly improved performance and increased user confidence. In the combined haptic condition, performance did not differ across target heights. We further analyzed participants'subjective experiences and search strategies highlighting the benefits of the tactile cues. Our findings suggest that Tactile Search can enhance interaction and provide design considerations for integrating haptic search into interactive systems.

0 citationsRead paper