Was ist die Webseite?

Forecasting MDPI

Startseite
Schweiz
Basel
Forecasting MDPI

Dr. Sonia Leva

Forecasting (ISSN 2571-9394) is an international and open access journal of all aspects of forecasting, published quarterly online by MDPI| IF: 2.3 Q2| Citescore: 5.8 Q1 | EiC: Prof.

08/09/2026

🌟 Highlights from Our Upcoming Forecasting Sessions 🌟

Get ready for inspiring discussions at IOCFC 2026, where leading experts from around the world will share their latest research and insights across a wide range of forecasting topics.

🔹 S1: Energy Forecasting & Analytics:
Prof. Dr. Anamika Yadav — Real-Time Power Load Forecasting Using AI and Data Analytics: Practical Studies from Indian SLDCs
Prof. Dr. Alberto Dolara — From Data to Battery Intelligence: Machine Learning for SoC and SoH Forecasting

🔹 S2: AI Forecasting & Large Language Models:
Prof. Dr. Mario Versaci — Energy Forecasting Beyond Prediction: Lie Algebras and the Geometry of Dynamic Interactions
Prof. Dr. Eren Baş — Decile Mean-Based Artificial Neural Network

🔹 S3: Forecasting and Econometric Models:
Prof. Dr. Fotios Petropoulos— The Wisdom of the Data: Getting the Most Out of Univariate Time Series Forecasting
Dr. Katja Heinisch — Advancing Sectoral Nowcasting: Large Language Models and Machine Learning Approaches

🔹 S4: Weather and Climate Forecasting:
Prof. Dr. Paul Williams — The Past, Present, and Future of Weather and Climate Forecasting
Dr. Jun Zhang — Bridging Science and Operations: New Frontiers in Tropical Cyclone Forecasting
Dr. Jun Du — Forecast Uncertainty: A Serious Deficiency in Today’s Ensemble Weather Prediction Models

We can’t wait to hear these outstanding contributions and exchange ideas with researchers from around the world. We hope to see you at IOCFC 2026! 🌐✨

07/09/2026

📣 Recommended Read | | OpenAccess

📖 Deep Learning Models for Bitcoin Prediction Using Hybrid Approaches with Gradient-Specific Optimization

✍️ by Amina Ladhari and Heni Boubaker

🔗 Read more at: https://www.mdpi.com/2571-9394/6/2/16

07/09/2026

📣 Recommended Read | | OpenAccess

📖 Developing Personalised Learning Support for the Business Forecasting Curriculum: The Forecasting Intelligent Tutoring System

✍️ by Devon Barrow, Antonija Mitrovic, Jay Holland, Mohammad Ali and Nikolaos Kourentzes

🔗 Read more at: https://www.mdpi.com/2571-9394/6/1/12

07/09/2026

🎉 The IOCFC 2026 Conference Program is Now Live!

The detailed conference program is officially available on our website. You will find all keynote and invited speeches, oral presentations, flash poster presentations, speakers’ exact presentation titles, and precise time slots!

📋View the full program and register here: https://sciforum.net/event/IOCFC2026/program-overview
Discover the presentations that match your research interests and start planning your schedule today.

🎟️ Register today:
Don't forget to complete your registration early to lock in your place and connect with the global research community. https://sciforum.net/registration/IOCFC2026
💡 Feel free to share this post with colleagues and peers who might be interested!

03/09/2026

📣 Recommended Read | |

📖 Probabilistic Demand Forecasting in the Southeast Region of the Mexican Power System Using Machine Learning Methods

✍️ by Ivan Itai Bernal Lara et al.

📈 Can hybrid machine learning handle electricity demand uncertainty in highly variable regions? This study integrates Bootstrap-based stochastic noise with XGBoost for forecasting in southeastern Mexico, achieving 1.644% MAPE for day-ahead predictions—while revealing that temperature data improves short-term but increases uncertainty over longer horizons.

🔗 Read more at: https://www.mdpi.com/2571-9394/7/3/39

03/09/2026

📣 Recommended Read | |

📖 Navigating AI-Driven Financial Forecasting: A Systematic Review of Current Status and Critical Research Gaps

✍️ by László Vancsura, Tibor Tatay and Tibor Bareith

This systematic literature review (PRISMA-based) examines AI/ML applications in financial market forecasting across equities, cryptocurrencies, commodities, and FX. While LSTM, GRU, XGBoost, and hybrid models outperform traditional methods, critical gaps remain: limited strategy integration, underexplored volatility sensitivity, and insufficient temporal robustness.

🔗 Read more at: https://www.mdpi.com/2571-9394/7/3/36

03/09/2026

⏰ Only 2 Weeks Left to Register: Join Us at IOCFC 2026! 📢

The 1st International Online Conference on Forecasting (IOCFC 2026) is approaching! Don’t miss the opportunity to join researchers, experts, and professionals from around the world for insightful discussions on the latest advances in forecasting.

The conference program overview is now available on the official website. Explore the scheduled sessions and exciting topics covered during the conference.

🔔 Please remember to complete your registration to receive the conference access link.
We warmly encourage all participants, including abstract authors, to register and attend the live sessions to engage in academic exchange and connect with the forecasting community.
📅 Conference Dates: 21–22 September 2026
🌐 Format: Online Conference

Register here:🔗 https://sciforum.net/registration/IOCFC2026
We look forward to welcoming you online at IOCFC 2026!

01/09/2026

📣 Recommended Read | |

📖 Applying Machine Learning and Statistical Forecasting Methods for Enhancing Pharmaceutical Sales Predictions

✍️ by Konstantinos P. Fourkiotis and Athanasios Tsadiras

Can machine learning improve pharmaceutical demand forecasting enough to optimize production and distribution? Analyzing 600,000 pharmacy sales records with ARIMA, LSTM, and XGBoost, this study finds that XGBoost consistently outperforms all other models—achieving MAPE scores as low as 16% across key drug categories—and reveals strong seasonality effects that can guide strategic planning.

🔗 Read more at: https://www.mdpi.com/2571-9394/6/1/10

01/09/2026

📣 Recommended Read | |

📖 Forecasting the Occurrence of Electricity Price Spikes: A Statistical-Economic Investigation Study

✍️ by Manuel Zamudio López, Hamidreza Zareipour and Mike Quashie

Can interpretable machine learning match black-box models for electricity price spike forecasting? This study compares tree-based classifiers with a statistical forecaster on Alberta market data, revealing that economic assessment matters as much as statistical accuracy—and that interpretability comes with a trade-off.

🔗 Read more at: https://www.mdpi.com/2571-9394/6/1/7

28/08/2026

📢 Recommended Read | |

📘 A Unified Transformer–BDI Architecture for Financial Fraud Detection: Distributed Knowledge Transfer Across Diverse Datasets

✍️ by Parul Dubey, Pushkar Dubey and Pitshou N. Bokoro

📈 Can AI detect sophisticated financial fraud while explaining its decisions? This study integrates transformer-based deep learning with symbolic BDI reasoning, achieving superior accuracy across three benchmark datasets while maintaining interpretability—a critical requirement for regulated financial environments.

🔗 Read more at: https://www.mdpi.com/2571-9394/7/2/31

Adresse

Basel

Webseite

https://www.mdpi.com/journal/forecasting

Benachrichtigungen

Lassen Sie sich von uns eine E-Mail senden und seien Sie der erste der Neuigkeiten und Aktionen von Forecasting MDPI erfährt. Ihre E-Mail-Adresse wird nicht für andere Zwecke verwendet und Sie können sich jederzeit abmelden.