Sara Pederzoli
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sara Pederzoli has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Francesco Guerra
University of Modena and Reggio Emilia, Modena, Italy
4 shared publications - Francesco Del Buono
Cristail Capital Scf, Carpi, Italy
3 shared publications - Marco Bergianti
Cristail Capital Scf, Carpi, Italy
2 shared publications - Marta Santacroce
University of Modena and Reggio Emilia, Modena, Italy
2 shared publications - Donato Tiano
Vita-Salute San Raffaele University (UniSR), Milano, Italy
1 shared publication - Matteo Paganelli
University of Modena and Reggio Emilia, Modena, Italy
1 shared publication
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9218-9222
AEQUITAS: A Toolkit for Stock Market Prediction and Portfolio Evaluation
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9218-9222
Open AccessAEQUITAS: A Toolkit for Stock Market Prediction and Portfolio Evaluation
- Open Access
- 9 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9661-9672
FinBench: A Benchmarking Framework for Stock Market Prediction and Portfolio Allocation
- 9 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9661-9672
Open AccessFinBench: A Benchmarking Framework for Stock Market Prediction and Portfolio Allocation
- Open Access
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 8618-8631
Trend-Error Decomposition for Self-Supervised Time Series Learning in Multivariate Forecasting Task
Self-Supervised Learning (SSL) has become a powerful paradigm in Artificial Intelligence, enabling the training of machine learning models using unlabeled data. However, in time series forecasting, SSL models are generally less effective than supervised models due to the complexity of temporal patterns, including trends, seasonality, and noise. To address this, we introduce TED4STL (Trend-Error Decomposition for Self-supervised Time-series Learning), a pipeline that decomposes each time series into two additive components, trend and error, and empirically test whether this decomposition improves the performance of SSL models. We adapt it to four SSL forecasting models and evaluate it on ten datasets. Experiments show that the decomposition consistently improves SSL forecasting accuracy, narrowing the gap with state-of-the-art supervised models and often surpassing them at short horizons.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 8618-8631
Open AccessTrend-Error Decomposition for Self-Supervised Time Series Learning in Multivariate Forecasting Task
Self-Supervised Learning (SSL) has become a powerful paradigm in Artificial Intelligence, enabling the training of machine learning models using unlabeled data. However, in time series forecasting, SSL models are generally less effective than supervised models due to the complexity of temporal patterns, including trends, seasonality, and noise. To address this, we introduce TED4STL (Trend-Error Decomposition for Self-supervised Time-series Learning), a pipeline that decomposes each time series into two additive components, trend and error, and empirically test whether this decomposition improves the performance of SSL models. We adapt it to four SSL forecasting models and evaluate it on ten datasets. Experiments show that the decomposition consistently improves SSL forecasting accuracy, narrowing the gap with state-of-the-art supervised models and often surpassing them at short horizons.
- Open Access
- 17 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 197899-197911
NOCTOWL: Adaptive Tree-Based Model for Network Anomaly Detection Under Delayed and Sampled Label Availability
The paper introduces NOCTOWL, an online, interpretable network intrusion detection system designed for streaming environments subject to distributional shifts, with delayed and partial label availability. The method combines the inherently explainable structure of a decision tree with a clustering-based strategy to create interpretable data partitions and incrementally adjust them in response to distribution shifts. The model further incorporates selective sampling to adapt to evolving distributions while preventing unnecessary growth. Experiments on five benchmark datasets simulating realistic operating conditions demonstrate that NOCTOWL achieves competitive performance compared to black-box state-of-the-art systems, while maintaining robustness under constrained annotation budgets.
- 17 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 197899-197911
Open AccessNOCTOWL: Adaptive Tree-Based Model for Network Anomaly Detection Under Delayed and Sampled Label Availability
The paper introduces NOCTOWL, an online, interpretable network intrusion detection system designed for streaming environments subject to distributional shifts, with delayed and partial label availability. The method combines the inherently explainable structure of a decision tree with a clustering-based strategy to create interpretable data partitions and incrementally adjust them in response to distribution shifts. The model further incorporates selective sampling to adapt to evolving distributions while preventing unnecessary growth. Experiments on five benchmark datasets simulating realistic operating conditions demonstrate that NOCTOWL achieves competitive performance compared to black-box state-of-the-art systems, while maintaining robustness under constrained annotation budgets.