This study investigates the predictive capabilities of three state-of-the-art neural network architectures—Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Transformer models—in forecasting stock prices for five leading technology companies: Apple Inc. (AAPL), Cisco Systems, Inc. (CSCO), Meta Platforms, Inc. (META), Microsoft Corporation (MSFT), and Tesla, Inc. (TSLA). The dataset spans from July 2019 to July 2023, with models evaluated using key performance metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared (R²) values. The results show that GRU models consistently achieve the lowest MAE, indicating superior precision in stock price prediction. In contrast, LSTM models, while showing slightly higher error rates, are particularly effective in capturing long-term trends and the variance in stock prices, as evidenced by higher R² values. Transformer models, which utilize self-attention mechanisms, showed promise in handling complex relationships but struggled with the volatility of certain stocks, such as TSLA, leading to higher errors and lower R². These findings provide valuable insights for financial analysts and investment professionals, offering guidance on selecting the most suitable deep learning models based on specific market conditions and forecasting needs. This study also lays the groundwork for further exploration into model optimization and hybrid approaches for more robust financial forecasting.
This study examines crude oil return dynamics in the context of the global energy transition, where decarbonization policies, technological innovation, and shifting energy demand increasingly influence market behavior. We propose a heavy-tailed distributional LSTM framework to jointly model the conditional mean, volatility, and tail risk of West Texas Intermediate (WTI) returns, incorporating key transition-related drivers: carbon allowance returns (ETS), artificial intelligence (AI) activity, electric vehicle (EV) market returns (SPKS), and geopolitical risk (GPR). Granger causality results show that ETS significantly predicts mean returns, reflecting the growing impact of climate policy signals, while AI and EV markets primarily affect volatility, indicating transmission through uncertainty channels. The model adopts a Student-t specification to capture heavy-tailed behavior and extreme price movements. Out-of-sample results reveal limited mean predictability but improved forecasting of return magnitude and tail risk. These findings highlight that, under energy transition dynamics, oil market predictability is increasingly concentrated in the risk dimension rather than in average returns.
This study examines the long-run and short-run elasticities of U.S. residential and commercial final energy consumption with respect to historical variations in heating and cooling degree days and compares these weather sensitivities across sectors. It also investigates whether joint exposure to heating and cooling conditions has an additive or attenuating effect on annual energy consumption. Using annual U.S. data from 1960 to 2025, we employ a Fourier-augmented bootstrap autoregressive distributed lag (Fourier ARDL) framework to estimate weather–energy relationships while accommodating smooth structural change. We also use a Fourier-augmented Toda–Yamamoto procedure to examine directional predictive relationships. The results confirm long-run equilibrium relationships in both sectors. Heating degree days have positive, significant long-run effects on residential and commercial energy consumption. Cooling degree days become significant when we include the heating–cooling interaction term. The interaction coefficient is negative and significant, indicating that joint heating and cooling exposure has an attenuating, non-additive association with annual energy consumption. Because we include the interaction term, we interpret the estimated HDD and CDD coefficients as conditional effects rather than unconditional elasticities. Residential energy demand adjusts to disequilibrium approximately three times faster than commercial demand. The causality results indicate directional predictive relationships from HDD to commercial consumption and from CHDD to residential consumption. Overall, the findings provide evidence on historical weather–energy relationships and offer implications for demand forecasting, grid planning, and energy-efficiency policy, but do not constitute a formal counterfactual attribution of energy changes to climate change.