A. K. Biswas et al., "A Dual Output Temporal Convolutional Network With Attention Architecture for Stock Price Prediction and Risk Assessment," in IEEE Access, vol. 13, pp. 53621-53639, 2025, doi: 10.1109/ACCESS.2025.3551307.
keywords: {Predictive models;Accuracy;Long short term memory;Data models;Forecasting;Risk management;Computational modeling;Attention mechanisms;Deep learning;Measurement;Stock price prediction;temporal convolutional network (TCN);attention mechanism;dual output model;financial time series;risk assessment;deep learning in finances},

M. N. H. Mir et al., "ABMF-Net: An Attentive Bayesian Multi-Stage Deep Learning Model for Robust Forecasting of Electricity Price and Demand" in IEEE Open Journal of the Computer Society, vol. 6, no. 01, pp. 896-907, null 2025, doi: 10.1109/OJCS.2025.3579522.
keywords: {Forecasting;Predictive models;Electricity;Computational modeling;Adaptation models;Bayes methods;Data models;Deep learning;Accuracy;Optimization}
Abstract: This article presents a novel deep learning model, the Attentive Bayesian Multi-Stage Forecasting Network (ABMF-Net), designed for robust forecasting of electricity price (USD/MWh) and demand (MW). The model incorporates an attention-based data selection mechanism, an encoder-decoder structure with masked time-series prediction, and a Bayesian neural network to generate both point and interval forecasts. Furthermore, a multi-objective Salp Swarm Algorithm (MSSA) is used to optimize forecasting accuracy and stability. Experimental evaluation on four real-world datasets from the Australian electricity market demonstrates that ABMF-Net achieves a MAPE as low as 1.89%, MAE of 0.67, RMSE of 0.98, and FICP of 0.98, outperforming LSTM, GRU, and Transformer models. Seasonal evaluations confirm the model’s robustness across high-variability conditions. These results position ABMF-Net as a high-performing and reliable forecasting model for modern electricity markets.
URL: https://doi.ieeecomputersociety.org/10.1109/OJCS.2025.3579522