AI for Energy Finance (AI4EFin)

create and disseminate knowledge

Project duration

36 months

Project budget

approx. 1.4 mil. Euro

Implementation

July 2023 – June 2026

Contact

office@ai4efin.ase.ro

Create and disseminate Knowledge

About AI for Energy Finance (AI4EFin)

Energy finance highlights the interdependency of energy and financial markets. Understanding this relationship and answering the crucial question of how to fuel world economies hunger for energy while decreasing greenhouse gas emission requires a new family of tools that turn the vast amounts of data in the energy finance ecosystem into insights for decision-making and ultimately enhance the efficiency, resilience, and sustainability of energy operations and their financing. AI4EFin speaks to these challenges.
Built around a methodological core, we craft novel machine learning (ML) and artificial intelligence (AI) instruments for pattern extraction, explanation, and forecasting of the high-dimensional, non-stationary, temporal data encountered in energy finance to support decision analysis and risk management. These features include probabilistic models to estimate the full conditional distribution of energy derivative prices and other targets, as well as distributional forecasts to facilitate the applicability of risk management tools. Drawing on the potential outcome framework, we also devise ML/AI instruments that model the causal effect of interventions/shocks on price developments and market outcomes.
These new causal approaches are also meant to guide policy-makers in devising/revising regulatory programs and other market interventions, and facilitate estimating the effectiveness of these interventions.

Energy finance highlights the interdependency of energy and financial markets. Understanding this relationship and answering the crucial question of how to fuel world economies hunger for energy while decreasing greenhouse gas emission requires a new family of tools that turn the vast amounts of data in the energy finance ecosystem into insights for decision-making and ultimately enhance the efficiency, resilience, and sustainability of energy operations and their financing. AI4EFin speaks to these challenges.
Built around a methodological core, we craft novel machine learning (ML) and artificial intelligence (AI) instruments for pattern extraction, explanation, and forecasting of the high-dimensional, non-stationary, temporal data encountered in energy finance to support decision analysis and risk management. These features include probabilistic models to estimate the full conditional distribution of energy derivative prices and other targets, as well as distributional forecasts to facilitate the applicability of risk management tools. Drawing on the potential outcome framework, we also devise ML/AI instruments that model the causal effect of interventions/shocks on price developments and market outcomes.
These new causal approaches are also meant to guide policy-makers in devising/revising regulatory programs and other market interventions, and facilitate estimating the effectiveness of these interventions.

Ai4EFIN

Mission & Objectives

AI4EFin involves design-oriented research to develop a set of new ML/AI methods for energy finance. Each design goal is accompanied by large-scale empirical experimentation to demonstrate the effectiveness of the new instruments vis-a-vis established benchmarks in relevant energy finance use cases related to decision analysis and risk management.

AI4EFin involves design-oriented research to develop a set of new ML/AI methods for energy finance. Each design goal is accompanied by large-scale empirical experimentation to demonstrate the effectiveness of the new instruments vis-a-vis established benchmarks in relevant energy finance use cases related to decision analysis and risk management.

  • Objective 1: To provide new ML/AI models for finance and energy market time series
  • Objective 2: To build XAI methodology for explaining deep learning-based time series forecasts
  • Objective 3: To devise probabilistic ML/AI models for energy finance risk management
  • Objective 4: To develop methodology for causal discovery and effect estimation in energy finance
  • Objective 5: To create and disseminate knowledge

Passionate – Dedicated – Professional

Meet Our Team of Experts

Introducing the Pioneers Behind Our Success: A Diverse Ensemble of Skilled Professionals and Visionaries

  • Stefan Lessmann

    Program Director

    Stefan Lessmann
  • Daniel Traian Pele

    Experienced Researcher

    Daniel Traian Pele
  • Sorin Anagnoste

    Experienced Researcher

    Sorin Anagnoste
  • Vasile Alecsandru Strat

    Experienced Researcher

    Vasile Alecsandru Strat
  • Bogdan Andrei Dumitrescu

    Experienced Researcher

    Bogdan Andrei Dumitrescu
  • Daniela Manea

    Experienced Researcher

    Daniela Manea
  • Dorel Paraschiv

    Experienced Researcher

    Dorel Paraschiv
  • Roxana Clodnitchi

    Postdoc Researcher

    Roxana Clodnitchi
  • Cosmin Octavian Cepoi

    Postdoc Researcher

    Cosmin Octavian Cepoi
  • Alla Petukhina

    Postdoc Researcher

    Alla Petukhina
  • Mihai Toma

    Postdoc Researcher

    Mihai Toma
  • Vlad Bolovaneanu

    PhD Student

    Vlad Bolovaneanu
  • Alexandru-Adrian Cramer

    PhD Student

    Alexandru-Adrian Cramer
  • Robert Grecu

    PhD Student

    Robert Grecu
  • Alexandru Andrei

    PhD Student

    Alexandru Andrei
  • Alina Luchian

    PhD Student

    Alina Luchian
  • Ana-Maria Strîmbeanu

    Master Student

    Ana-Maria Strîmbeanu
  • Orr Shahar

    Master Student

    Orr Shahar

CREATE AND DISSEMINATE KNOWLEDGE

Keysubjects

AI4EFin is a research project developed under and financed by Romania’s National Recovery and Resilience PlanPillar III. Smart, sustainable and inclusive growth, including economic cohesion, jobs, productivity, competitiveness, research, development, and innovation, and a well-functioning internal market with strong small and medium-sized enterprises (SMEs), Component C9/I8.

Energy Finance 85%
Artificial Intelligence 76%
Explainable deep neural networks 77%
Machine Learning 88%
Risk Management 66%

AI4EFin

Project’s deliverables

Explore the Cornerstones of Success: Discover Our Project’s Key Deliverables

  • Review paper, new data available, technical infrastructure

  • Case study on deep global models for forecasting and market modeling
  • Case study and survey results on time-series forecasting models and their explainability
  • Explainable deep probabilistic models
  • Causal forecasting models

Project’s deliverables

  1. Anagnoste, S., Andrei, A.-V., Bolovăneanu, V., Cepoi, C.-O., Clodnitchi, R., Cramer, A.-A., Grecu, R.-A., Lessmann, S., Pele, D. T., Petukhina, A., & Strat, V. A. (2025). The role of AI in (re)shaping energy finance: A systematic literature review. Energy Strategy Reviews, 61, 101833. https://doi.org/10.1016/j.esr.2025.101833
  2. Pele, D. T., Bolovăneanu, V., Lin, M.-B., Ren, R., Ginavar, A. T., Spilak, B., Andrei, A.-V., Toma, F.-M., Lessmann, S., & Härdle, W. K. (2025). In the beginning was the word: LLM-VaR and LLM-ES. Expert Systems with Applications, 128676. https://doi.org/10.1016/j.eswa.2025.128676
  3. Agakishiev, I., Härdle, W. K., Kopa, M., Kozmik, K., & Petukhina, A. (2025). Multivariate probabilistic forecasting of electricity prices with trading applications. Energy Economics, 141, 108008. https://doi.org/10.1016/j.eneco.2024.108008
  4. Bokelmann, B., & Lessmann, S. (2025). Heteroscedasticity-aware stratified sampling to improve uplift modeling. European Journal of Operational Research, 325(1), 118–131. https://doi.org/10.1016/j.ejor.2025.02.030
  5. Gerling, C., & Lessmann, S. (2025). Multimodal Document Analytics for Banking Process Automation. Information Fusion, 102973. https://doi.org/10.1016/j.inffus.2025.102973
  6. Grecu, R. A., Cramer, A. A., Pele, D. T., & Lessmann, S. (2025). The link between energy prices and stock markets in European Union countries. The North American Journal of Economics and Finance, 78, 102420. https://doi.org/10.1016/j.najef.2025.102420
  7. Gurgul, V., Lessmann, S. & Härdle, W.K. (2025). Deep Learning and NLP in Cryptocurrency Forecasting: Integrating Financial, Blockchain, and Social Media Data. International Journal of Forecasting. https://doi.org/10.1016/j.ijforecast.2025.02.007
  8. Kozodoi, N., Lessmann, S., Alamgir, M., Moreira-Matias, L., & Papakonstantinou, K. (2025). Fighting sampling bias: A framework for training and evaluating credit scoring models. European Journal of Operational Research. https://doi.org/10.1016/j.ejor.2025.01.040
  9. Anderloni, L., Petukhina, A., & Tanda, A. (2024). Peer-to-peer lending: Exploring borrowers’ motivations and expectations. Journal of Small Business Management, 1–33. https://doi.org/10.1080/00472778.2024.2431232
  10. Fischer, T., Sterling, M., & Lessmann, S. (2024). FX-spot predictions with state-of-the-art transformer and time embeddings. Expert Systems with Applications, 249, 123538. https://doi.org/10.1016/j.eswa.2024.123538
  11. Medina-Olivares, V., Lessmann, S., & Klein, N. (2024). The Deep Promotion Time Cure Model. IEEE Transactions on Neural Networks and Learning Systems, online first. https://doi.org/10.1109/TNNLS.2024.3398559
  12. Teng, H.-W., Härdle, W. K., Osterrieder, J., Baals, L. J., Papavassiliou, V. G., Bolesta, K., Kabasinskas, A., Filipovska, O., Thomaidis, N. S., Moukas, A. I., Goundar, S., Nasir, J. A., Weinberg, A. I., Arakelian, V., Truică, C.-O., Akar, M., Kabaklarlı, E., Apostol, E.-S., Iannario, M., Bedowska-Sojka, B., Skaftadottir, H. K., Schwendner, P., Yıldırım, Ö., Shala, A., Pisoni, G., Coita, I. F., Korba, S., Hafner, C. M., Molnár, B., Xhumari, E., Pele, D. T., & Orhun, E. (in press). Digital assets: Risks, regulations, mitigation. Financial Innovation.
  1. Săvescu, A. R., Mazurencu-Marinescu-Pele, M., Alexandra-Ioana Conda, Bolovăneanu, V., & Pele, D. T. (2025). Infodemic insights: Mapping COVID-19’s digital discourse in Romania. Management & Marketing, 20(1), 15-34. https://doi.org/10.2478/mmcks-2025-0003
  2. Oțoiu, A., Manea, D.I., Paraschiv, D M. and Ștefan, A. (2025). The Role and Potential of Blockchain Technology for the Food Processing Industry: A Scoping Review. Amfiteatru Economic, 27(69), pp. 504-517. https://doi.org/10.24818/EA/2025/69/504 or https://www.webofscience.com/wos/woscc/full-record/WOS:001500039000014
  3. Otoiu, A., Titan, E., Paraschiv, D., Manea, DI. (2025). Job polarisation OR AND upgrading! Recent evidence from Europe. The Economic and Labour Relations Review.https://doi.org/10.1017/elr.2025.12 or https://www.webofscience.com/wos/woscc/full-record/WOS:001490470000001 
  4. Paraschiv, D.M., Muhammad, A., Petrariu, I.R., Gheorghe, M., Dieaconescu, R.I. and Istudor, M., (2024). Shaping Europe’s Digital and Sustainable Future: Analysis of the Digital Economy and Society Index in the Pre- and Post-Pandemic Period. Amfiteatru Economic, 26(Special Issue No. 18), pp. 1012-1030. https://doi.org/10.24818/EA/2024/S18/1012 or https://www.webofscience.com/wos/woscc/full-record/WOS:001379092800002
  5. Popescu, I.M., Zavatin, I., Manea, D.I., Pamfilie, R., Jurconi, A., (2024), Adapting the competences of the employed personnel in the context of the integration of artificial intelligence in organisations, Amfiteatru Economic, 26, Issue 67, Page 817-831, DOI10.24818/EA/2024/67/817 or https://www.webofscience.com/wos/woscc/full-record/WOS:001289160200008
  1. Grădinaru, G. I., Manea, D. I., Andreescu, F., Toma, D. A., & Paraschiv, L. I. (2024). Identifying the Main Factors of Elaborating “Smart City” Strategy Using Machine Learning. A Comparative Study Among Romanian Cities. Economic Computation and Economic Cybernetics Studies and Research, 58(3), 53–71. https://www.webofscience.com/wos/woscc/full-record/WOS:001317110900004
  1. Strat, V., Radev, D., Pele, D. T., Chinie, C., Grosu, F., Darie, F. C., Mare, C., Damian, V., & Coita, I. (2024). Fintech Report: Romania & Bulgaria, 2023 Edition. Bucharest: Editura ASE. ISBN 978-606-34-0517-4. https://bbs.ase.ro/wp-content/uploads/2024/04/RoFin.Tech_Romania-Bulgaria_Report2023_ebook.pdf

 

  1. Shahar, O., Lessmann, S., & Pele, D. T. (2025). Causality analysis of electricity market liberalization on electricity price using novel machine learning methods (arXiv:2507.12331). arXiv. https://arxiv.org/abs/2507.12331
  2. Velev, G., Lessmann, S. (2024). Interpretable, multi-dimensional Evaluation Framework for Causal Discovery from observational i.i.d. Data. arXiv preprint, https://arxiv.org/pdf/2409.19377
  3. Vöge, L., Gurgul, V., & Lessmann, S. (2024). Leveraging Zero-Shot Prompting for Efficient Language Model Distillation. arXiv preprint, arXiv:2403.15886. https://arxiv.org/abs/2403.15886
  4. Andrei, V.A., Velev, G., Toma, F.M., Pele, D.T., Lessmann, S. (2024). Energy Price Modelling: A Comparative Evaluation of Four Generations of Forecasting Methods.            arXiv preprint arXiv:2411.03372. https://arxiv.org/abs/2411.03372
  5. Bedowska-Sojka, B., Wojcik, P., & Pele, D. T. (2024). Predicting the Undead: Using Machine Learning to Forecast Cryptocurrency Zombies. SSRN. https://ssrn.com/abstract=4793792 or http://dx.doi.org/10.2139/ssrn.4793792
  6. Bettencourt, L. O., Tetereva, A., & Petukhina, A. (2024). Advancing Markowitz: Asset Allocation Forest. SSRN 4781685.
  7. Grecu, R., Cramer, A., Pele, D. T., & Lessmann, S. (2024). The Link between Energy Prices and Stock Markets in European Union Countries. SSRN. https://ssrn.com/abstract=4989890 or http://dx.doi.org/10.2139/ssrn.4989890
  8. Lin, M. B., Pele, D. T., & Ren, R. (2024). Understanding Blockchain Technology. In Handbook of Blockchain Analytics (Springer, Forthcoming). https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4804484
  1. STAT of ML (Statistics of Machine Learning), October 5 – October 6, 2023, Czech Academy of Sciences, Prague, Czech Republic: Conference Website
    • Pele, D. T., Petukhina, A., Bolovaneanu, V., & Conda, A. Robustified Markowitz Approach for Diversified Portfolios with Crypto-Assets.
    • Gurgul, V., Ider, D., & Lessmann, S. Finetuning NLP Models for Financial Forecasting: Do or Don’t? A Cryptocurrency Return Prediction Case Study.
  2. The 17th International Conference on Computational and Financial Econometrics (CFE 2023), HTW Berlin, University of Applied Sciences, Berlin, Germany, 16-18 December 2023: Conference Website
    • Petukhina, A., Agakishev, I., Kozmik, K., Härdle, W. K., & Kopa, M. Multivariate Probabilistic Forecasting of Electricity Prices with Trading Applications.
    • Andrei, A.-V., & Pele, D. T. Deep Learning for Energy Forecasting: A Benchmark.
    • Grecu, R.-A., Pele, D. T., & Cramer, A. A. The Impact of Energy Prices on Stock Returns in Selected Central and Eastern European Countries.
    • Bolovaneanu, V., Moukas, A.-I., Petukhina, A., Pele, D. T., & Thomaidis, N. Optimizing Wind Energy Aggregation: A Comparative Analysis of Asset Allocation Techniques.
    • Conda, A., Petukhina, A., Melzer, A., Phan, M., Basangova, M., Alkhoury, S., & Bolovaneanu, V. Day-Ahead Probability Forecasting for Redispatch.
    • Lessmann, S., & Velev, G. Neural Architecture Search for Bitcoin Market Prediction.
    • Cepoi, C. O., Cramer, A. A., Clodnitchi, R., Pele, D. T., Strat, V., & Anagnoste, S. Forecasting Realized Volatility Using Machine Learning: The Case of EU Energy Listed Firms.
  3. Conference AI Innovations in Finance and Society, 30-31 October 2023, Universitat Pompeu Fabra, Barcelona, Spain: Conference Website
    • Pele, D. T. BRC Blockchain Research Center.
  4. The 18th International Conference on Business Excellence: Smart Solutions for a Sustainable Future, 21-23 March 2024, Bucharest, Romania: Conference Website
    • Grecu, R.-A., Cramer, A.-A., & Pele, D. T. The Link Between Energy Prices and Stock Markets in European Union Countries.
    • Cretulescu, A., & Popescu Cretulescu, A. Model Prediction XGBoost for Perspective of Closing Cernavoda Reactor 1 and the Impact on the Romanian Energy System.
    • Petukhina, A., Erlwein-Sayer, C., Phan, M. P., Basagnova, M., Bolovaneanu, V., & Conda, A. Day-Ahead Probability Forecasting for Redispatch 2.0 Measures.
    • Bolovaneanu, V., Pele, D. T., & Petukhina, A. Optimizing Wind Energy Aggregation: A Comparative Analysis of Asset Allocation Techniques.
    • Andrei, A.-V., Pele, D. T., & Lessmann, S. Benchmarking Generations of Time Series Forecasting Models: From Econometrics to LLM.
    • Cepoi, C.-O. Energy Uncertainty and Alternative-Nuclear Transition.
  5. The 3rd Quantum Computing Workshop on AI Optimization and Forecasting across Industries: Digital and Quantum Computing, 9-12 April 2024, National University of Singapore: Conference Website
    • Lessmann, S. Transfer learning for credit risk modeling.
  6. AI Finance Insights: Pioneering the Future of Fintech, COST FINAI Conference, 20-21 May 2024, Istanbul, Turkey: Conference Website
    • Pele, D. T. Benchmarking Generations of Time Series Forecasting Models.
  7. 33rd European Conference on Operational Research, Technical University of Denmark (DTU), 30 June – 3 July 2024: Conference Website
    • Agakishiev, I., Härdle, W. K., Kozmik, K., Kopa, M., & Petukhina, A. Multivariate Probabilistic Forecasting of Electricity Prices With Trading Applications.
    • Lessmann, S., Andrei, A.-V., Velev, G., & Pele, D. T. Energy Price Modelling: A Comparative Evaluation of Four Generations of Forecasting Methods.
    • Grecu, R.-A., Pele, D. T., & Alexandru-Adrian. The Impact of Energy Prices on European Stock Markets.
    • Cepoi, C. O., & Pele, D. T. Predicting Realized Volatility: Insights from EU Energy Listed Firms During Crises.
    • Bolovăneanu, V., Petukhina, A., Conda, A., Basangova, M., Erlwein-Sayer, C., Melzer, A., & Phan, M. P. Day-Ahead Probability Forecasting for Redispatch 2.0 Measures.
    • Lin, M.-B., Găman, Ş., Wang, R., & Pele, D. T. The Chronicles of Ethereum: An Event Study on EIPs.
    • Pele, D. T., Mazurencu Marinescu Pele, M., Conda, A., & Bag, R. C. Financial Risk Meter for the Romanian Stock Market.
    • Pele, D. T., Mazurencu Marinescu Pele, M., Găman, Ş., Conda, A., & Bag, R. C. BitMood: Analyzing Bitcoin Trends through Facebook Emotions with AI.
  8. The 7th International Conference on Econometrics and Statistics (EcoSta 2024), Beijing Normal University, Beijing, China, 17-19 July 2024
    • Bolovăneanu, V., Petukhina, A., Conda, A., Basangova, M., Erlwein-Sayer, C., Melzer, A., & Phan, M. P. Day-Ahead Probability Forecasting for Redispatch 2.0 Measures.
  9. The 17th International Conference on Applied Statistics (ICAS 2024), November 14-15, 2024, Bucharest, Romania: Conference Website
    • Tak, R., Pele, D. T., & Härdle, W. K. GAN application for automated trading systems.
    • Jheng, S.-L., Teng, H.-W., Härdle, W. K., Pele, D. T., & Costea, A. Financial risk meters in Taiwan’s high-cap sectors.
    • Ginavar, A., Pele, D. T., Manea, D. I., Conda, A. I., Mazurencu-Marinescu-Pele, M., & Stefan, A. Cryptocurrency market analysis: Insights from Metcalfe’s law and log-periodic power laws.
  10. The 4th Yushan Conference, 18th NYCU International Finance Conference, National Yang Ming Chiao Tung University, Taiwan, 5-6 December 2024: Conference Website
    • Lessmann, S. A Tale of Bias and Missingness in AI-based Scoring Systems: Evidence from the Credit Industry.
    • Petukhina, A. Day-ahead Probability Forecasting for Redispatch 2.0 Measures.
    • Spilak, B. Machine Learning for Waste Water Treatment Plant (WWTP) Control.
    • Teng, H.-W. AI in Finance.
    • Pele, D. T. In the Beginning was the Word: LLM Risk Measures.
    • Găman, Ş. Quantlet: The Code Snippet Knowledge Platform.
    • Jheng, S.-L. Financial Risk Meters in Taiwan’s High-Cap Sectors.
    • Zuo, X. A Safe Recomm System for Knowledge Platforms.
  11. 18th International Joint Conference on Computational and Financial Econometrics (CFE) and CMStatistics, King’s College London, 14-16 December 2024: Conference Website
    • Bolovăeanu, V. Bayesian Bandit Portfolio: Customized Thompson Sampling for Investor Preference.
  12. The 19th International Conference on Business Excellence: Leading Change in Disruptive Times, 20-22 March 2025, Bucharest, Romania: Conference Website
    • Pele, D.T. “In the Beginning Was the Word: LLM-Based Risk Forecasting – VaR and ES.”
    • Tak, R. & Pele, D.T. “LLM-Driven Stock Prediction: Capturing Market Trends with LLaMA.”
    • Ginavar, A.T., Conda, A.I., Mazurencu-Marinescu-Pele, M., & Pele, D.T. “Cryptocurrency Market Analysis: Insights from Metcalfe’s Law and Log-Periodic Power Laws.”
    • Jheng, S-L., Conda, A.I., Pele, D.T., & Härdle, W.K. “Cryptocurrencies in a Changing Financial Landscape: A Systematic Review.”
    • Petukhina, A. “Probabilistic forecasting of electricity prices with multivariate distributional copula regression” (with G. Mazzon and Daniele Marazzina).
  13. English Lecture Event – Unveiling Return Dynamics: Energy, Crypto, and Equity Factor Insights, Biomedical Artificial Intelligence Academy, Kaohsiung Medical University, June 17, 2025, Kaohsiung, Taiwan: Event Website
    • Pele, D. T., Conda, A.-I., Bolovăneanu, V., & Mazurencu-Marinescu Pele, M. Infodemic Insights: Mapping COVID-19’s Digital Discourse in Romania.
  14. 34th Southern District Statistical Seminar & 2025 Annual Meeting of the Chinese Society of Probability and Statistics, National Taipei University, 19-20 June 2025: Conference Website
    • Pele, D. T. LLM-Based Risk Measures.
  15. 5th Yushan-Turing/Euler Conference, June 21, 2025, Taipei, Taiwan: Conference Website
    • Pele, D. T. AI and Digital Finance.
  16. 34th European Conference on Operational Research, June 22-25, 2025, Leeds, UK: Conference Website
    • Lessmann, S. (2025). Fairness in Credit Scoring. Invited Talk presented at the 34th European Conference on Operational Research.
  17. 17th Annual Society for Financial Econometrics Conference (SOFIE), June 9-12, 2025, Cergy, France: Conference Website
    • Petukhina, A. (2025). Blockchain Characteristics and Systematic Risk: A Neural Network Based Factor Model for Cryptocurrencies?
  1. ASE Summer School 2023
  2. Workshop AI, Digital Assets and the Future of Energy Finance, 16-17 May 2024, Bucharest University of Economic Studies: https://www.meetup.com/fintech_ai_in_finance/events/299747969/
    • Pele, D. T. LLM VaR: In the Beginning Was the Word.
    • Grecu, R.-A., Cramer, A.-A., & Pele, D. T. The Link Between Energy Prices and Stock Markets in European Union Countries.
    • Bolovăneanu, V., Petukhina, A., Conda, A., Basangova, M., Erlwein-Sayer, C., Melzer, A., & Phan, M. P. Day-Ahead Probability Forecasting for Redispatch 2.0 Measures.
  3. MSCA DIGITAL Summer School, University of Twente, NL, 10-13 June 2024: https://www.digital-finance-msca.com/cost-finai-phd-school-2024
    • Pele, D. T. LLM Risk Measures.
  4. AI4EFin Workshop, Humboldt-Universität zu Berlin, Berlin, 05-06 September 2024:
    • Bolovaneanu, V. Day-ahead Probability Forecasting for Redispatch 2.0 Measures – Update.
    • Pele, D. T. LLM VaR: In the Beginning Was the Word.
    • Grecu, R.-A., Cramer, A.-A., & Pele, D. T. The Link Between Energy Prices and Stock Markets in European Union Countries.
    • Andrei, A. Energy Price Modelling: A Comparative Evaluation of Four Generations of Forecasting Methods.
    • Grecu, R.-A. Review Paper on Energy Finance.
    • Mazzon, G., & Petukhina, A. Multivariate Distributional Copula Regression: Probabilistic Forecasting of Electricity Prices.
    • Zharova, A. Recommendation Systems for Energy Efficiency in Residential Buildings.
  5. 2024 Summer School “Data Science for Sustainable Finance and Economics” at Hochschule für Technik und Wirtschaft Berlin, 09-13 September 2024: Summer_School_2024-29.pdf (htw-berlin.de)
    • Pele, D. T. Overview of XAI Methods
    • Petukhina A. Classification models for financial applications
  6. Research Seminar at the University of Pavia, June 2025:
    • Petukhina A. Advancing Markowitz: Asset Allocation Forest – Link