Forecasting MDPI

03/12/2025

📢 Highly Cited Paper in !

📖 A Day-Ahead Photovoltaic Power Prediction via Transfer Learning and Deep Neural Networks

✍️ By: Seyed Mahdi Miraftabzadeh, Cristian Giovanni Colombo, Michela Longo & Federica Foiadelli

⚡ Boosts solar forecasting accuracy even with minimal data!

👉

Climate change and global warming drive many governments and scientists to investigate new renewable and green energy sources. Special attention is on solar panel technology, since solar energy is considered one of the primary renewable sources and solar panels can be installed in domestic neighborh...

03/12/2025

📢 New Publication in !

📘 The MECOVMA Framework: Implementing Machine Learning Under Macroeconomic Volatility for Marketing Predictions

✍️ By Manuel Muth

📊 Boosts marketing prediction accuracy in volatile economic conditions!

🔗

The methodological framework introduced in this paper, MECOVMA, is a novel framework that guides the application of Machine Learning specifically for marketing predictions within volatile macroeconomic environments. MECOVMA has been developed in response to the identified gaps displayed by existing ...

02/12/2025

📢 New publication in Forecasting!

📘 Mode Decomposition Bi-Directional Long Short-Term Memory (BiLSTM) Attention Mechanism and Transformer (AMT) Model for Ozone (O₃) Prediction in Johannesburg, South Africa

✍️ Israel Edem Agbehadji and Ibidun Christiana Obagbuwa

This study proposes a hybrid deep learning model—combining IMode decomposition, BiLSTM, attention mechanisms, and transformers—to improve the accuracy of ozone (O₃) concentration prediction in Johannesburg. The results highlight the model’s potential for supporting environmental monitoring and public health initiatives.

🔗 Read the full article here: https://brnw.ch/21wY0Fw

02/12/2025

📢 New publication in Forecasting!

📘 A Wavelet–Attention–Convolution Hybrid Deep Learning Model for Accurate Short-Term Photovoltaic Power Forecasting

✍️ Kaoutar Ait Chaoui, Hassan EL Fadil, Oumaima Choukai and Oumaima Ait Omar

This study presents an innovative hybrid deep learning framework that integrates improved wavelets, attention mechanisms, and convolutional layers to significantly enhance short-term photovoltaic power forecasting accuracy.

🔗 Read the full article here: https://brnw.ch/21wY0up

01/12/2025

📢 New publication in Forecasting

📘 Improving Dry-Bulb Air Temperature Prediction Using a Hybrid Model Integrating Genetic Algorithms with a Fourier–Bessel Series Expansion-Based LSTM Model

✍️ By: Hussein Alabdally, Mumtaz Ali, Mohammad Diykh, Ravinesh C. Deo, Anwar Ali Aldhafeeri, Shahab Abdulla, and Aitazaz Ahsan Farooque

This research presents an advanced hybrid forecasting approach that merges genetic algorithms with a Fourier–Bessel series expansion-based LSTM model to enhance dry-bulb air temperature prediction. A promising contribution to climate analytics, weather modeling, and environmental data science.

🔗 Read the full article:

The dry-bulb temperature is a critical parameter in weather forecasting, agriculture, energy management, and climate research. This work proposes a new hybrid prediction model (FBSE-GA-LSTM) that integrates the Fourier–Bessel series expansion (FBSE), genetic algorithm (GA), and long short-term mem...

01/12/2025

📢 New publication in Forecasting!

📘 An Extension of Laor Weight Initialization for Deep Time-Series Forecasting: Evidence from Thai Equity Risk Prediction

✍️ By: Katsamapol Petchpol and Laor Boongasame

This study introduces an enhanced weight initialization method designed to improve the stability and accuracy of deep time-series forecasting models, demonstrated through Thai equity risk prediction. A valuable contribution to deep learning and financial risk modeling.

🔗 Read the full article: https://brnw.ch/21wXYrW

28/11/2025

📢 New publication in Forecasting!

📘 Integration of LSTM Networks in Random Forest Algorithms for Stock Market Trading Predictions

✍️ Authored by: Juan C. King and José M. Amigó

This study introduces a hybrid approach combining LSTM neural networks with Random Forest algorithms to improve stock market trading predictions—an exciting step toward more robust and intelligent financial forecasting.

🔗 Read the full article:

The aim of this paper is the analysis and selection of stock trading systems that combine different models with data of a different nature, such as financial and microeconomic information. Specifically, based on previous work by the authors and with the application of advanced techniques of machine ...

28/11/2025

📢 New publication in Forecasting!

📘 TimeGPT’s Potential in Cryptocurrency Forecasting: Efficiency, Accuracy, and Economic Value

✍️ By: Minxing Wang, Pavel Braslavski, and Dmitry I. Ignatov

This study evaluates the capabilities of ITimeGPT in predicting cryptocurrency markets, focusing on its efficiency, accuracy, and economic value. A timely contribution to the fast-evolving intersection of AI and digital finance.

🔗 Read the full article:

Accurate and efficient cryptocurrency price prediction is vital for investors in the volatile crypto market. This study comprehensively evaluates nine models—including baseline, zero-shot, and deep learning architectures—on 21 major cryptocurrencies using daily and hourly data. Our multi-dimensi...

27/11/2025

📢 New Publication in !

We’re pleased to share our latest research article:

📘 ISGR-Net: A Synergistic Attention Network for Robust Stock Market Forecasting

This study introduces a novel attention-based deep learning architecture designed to enhance the accuracy and robustness of stock market prediction—pushing the boundaries of data-driven financial forecasting.

✍️ Authors: Rasmi Ranjan Khansama, Rojalina Priyadarshini, Surendra Kumar Nanda, Rabindra Kumar Barik & Manob Jyoti Saikia

🔗 Read the full article:

Owing to the high volatility, non-stationarity, and complexity of financial time-series data, stock market trend prediction remains a crucial but difficult endeavor. To address this, we present a novel Multi-Perspective Fused Attention model (SGR-Net) that amalgamates Random, Global, and Sparse Atte...

27/11/2025

📢 New Publication in Forecasting!

We’re excited to share our latest research article:

📘 Identification of Investment-Ready SMEs: A Machine Learning Framework to Enhance Equity Access and Economic Growth

This work presents a robust ML-based framework that helps identify SMEs with strong investment potential—supporting better access to equity financing and contributing to sustainable economic growth.

✍️ Authors: Periklis Gogas, Theophilos Papadimitriou, Panagiotis Goumenidis, Andreas Kontos and Nikolaos Giannakis

🔗 Read the full article:

Small and medium-sized enterprises (SMEs) are critical contributors to economic growth, innovation, and employment. However, they often struggle in securing external financing. This financial gap mainly arises from perceived risks and information asymmetries creating barriers between SMEs and potent...

26/11/2025

📢 New Special Issue in !

"Advanced Forecasting in an Era of Uncertainty and Its Impact on Strategic Investment Decisions"

Guest Editors: Dr. Marek Nagy and Dr. Katarina Valaskova

We are pleased to announce that this Special Issue in Forecasting is now open for submissions! 🔥🌍

This issue welcomes innovative contributions that explore how advanced forecasting methods support strategic investment choices in uncertain environments.

🔗 Learn more & submit your research: https://brnw.ch/21wXQxX

📆 Submission Deadline: 30 November 2026

26/11/2025

📢 New Publication in

📖 Short-Term Prediction in an Emergency Healthcare Unit: Comparison Between ARIMA, ANN, and Logistic Map Models

✍️ Authors: Andres Eberhard Friedl Ackermann, Virginia Fani, Romeo Bandinelli and Miguel Afonso Sellitto

We are pleased to announce the publication of this study comparing ARIMA, Artificial Neural Networks, and Logistic Map models for short-term prediction in emergency healthcare settings.

🔗

Emergency departments worldwide face challenges in managing fluctuating patient demand, which is often inadequately addressed by traditional forecasting methods due to the inherent nonlinearities of data. The purpose of this study is to propose a short-term prediction model for daily attendance in a...