An official website of the United States government
Accurate short-term load forecasting (STLF) plays a crucial role in optimizing grid operations and reducing operational costs for utility companies. Among various forecasting methods, Long Short-Term Memory (LSTM) networks are widely adopted due to their ability to capture temporal dependencies within load sequences. Although LSTM models have shown promising results, this paper further investigates their potential to enhance STLF accuracy for the next 24 hours. A multi-task learning framework inspired by Autoencoders is proposed to improve LSTM-based forecasting by jointly reconstructing historical data and predicting future loads. By transferring the encoder’s hidden and cell states to the forecasting decoder, the model captures richer temporal dependencies. Experimental results on a publicly available dataset show that the proposed framework improves forecasting performance over the next 24 forecasting steps, across multiple error metrics (MAPE, MAE, RMSE, and R2) compared with models widely used in STLF.
more »
« less
This content will become publicly available on September 1, 2027
GDP Forecasting for the United States (2025–2030) Using ARIMA, OLS, LSTM and Hybrid Models
Reliable GDP forecasting plays a critical role in macroeconomic management, particularly during periods of heightened uncertainty such as the 2008 financial crisis and the 2020 pandemic shock. During these episodes, timely GDP projections provided policymakers with essential guidance for assessing recession depth, calibrating emergency fiscal and monetary responses, and preventing further macroeconomic deterioration. To support policy evaluation and medium-term growth planning, this study applies a unified forecasting framework to annual U.S. GDP data from 1980 to 2024 using three representative base models—ARIMA, OLS, and LSTM—together with a linear hybrid ensemble that combines their predictions. Each base model is paired with preprocessing tailored to its statistical assumptions. For ARIMA, unit-root testing confirms non-stationarity, and second-order differencing produces a stationary series, leading to the selection of an ARIMA (0,2,2) specification via information criteria and autocorrelation diagnostics. For OLS, a log-linear specification stabilizes exponential growth, yielding an estimated long-run annual trend of approximately 4.98%. For LSTM, the log-transformed series is normalized and converted into four-year sliding window sequences to enable nonlinear temporal learning despite the limited sample size. The hybrid ensemble—implemented as a convex linear blend of the three base forecasts estimated by least squares—is designed to exploit complementary strengths across linear and nonlinear components. All models generate forecasts for 2025–2030 and are evaluated using MAE, RMSE, MAPE, MASE, and Theil’s U. The empirical results show that the hybrid ensemble (COLBA) model achieves the lowest MAE, RMSE, MASE, and Theil’s U, while the standalone ARIMA model attains the smallest MAPE. These findings indicate that combining statistically grounded econometric models with neural networks can modestly improve overall accuracy even when only annual data are available, while ARIMA remains particularly effective for preserving proportional accuracy in trend-dominated macroeconomic series.
more »
« less
- PAR ID:
- 10711414
- Publisher / Repository:
- Avestia Publishing, International ASET Inc.
- Date Published:
- Format(s):
- Medium: X
- Location:
- London, United Kingdom
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Wind energy technologies, including advanced turbine management and scheduling, rely on accurate wind power forecasting (WPF) for optimal operation. Enhancing forecast precision is crucial for reducing volatility in wind power integration and improving forecasting reliability. While time series forecasting methods estimate future values from historical data, traditional approaches often struggle with computational efficiency and model complexity. To address these challenges, we propose a hybrid forecasting model that integrates multi- variate estimation (MVE) and pure time series prediction (TSP) using a bidirectional long-short-term memory network (Bi-LSTM) optimized with Tree-structured Parzen Estimator (TPE)- based Bayesian optimization. The model incorporates numerical weather prediction (NWP) data for real-time forecasting, addressing a key limitation in existing methods. MVE utilizes meteorological features such as wind speed, direction, temperature, and pressure, while TSP captures historical power generation patterns. The TPE-optimized Bi-LSTM architecture effectively captures bidirectional temporal dependencies, improving accuracy in both short-term and long-term forecasting. The model is evaluated using a six-year historical wind energy dataset from NREL, with performance assessed through RMSE, MAE, and R2 score. It outperforms traditional LSTM variants (Vanilla LSTM, Stacked LSTM, Bi-LSTM) and state-of-the-art models such as Transformers and GRUs, achieving R2 scores of 0.976 for MVE and 0.932, 0.928, and 0.864 for TSP across short-term, day- ahead, and long-term forecasting, respectively. Additionally, TPE based Bayesian optimization reduces computational time around 8%–10%, enhancing hyperparameter tuning efficiency. The study further analyzes the model’s computational burden, scalability, and practical implementation, offering a robust and efficient approach for improving wind power forecasting accuracy. While the model achieves high accuracy on the NREL dataset, future work will validate its performance across diverse geographic regions (e.g., Europe, Asia) and turbine configurations.more » « less
-
This paper empirically evaluates the potentially non-linear nexus between financial indicators and the distribution of future GDP growth, using a rich set of macroeconomic and financial variables covering 13 advanced economies. We evaluate the out-of-sample forecast performance of financial variables for GDP growth, including a fully real-time exercise based on a flexible non-parametric model. We also use a parametric model to estimate the moments of the time-varying distribution of GDP and evaluate their in-sample estimation uncertainty. Our overall conclusion is pessimistic: Moments other than the conditional mean are poorly estimated, and no predictors we consider provide robust and precise advance warnings of tail risks or indeed about any features of the GDP growth distribution other than the mean. In particular, financial variables contribute little to such distributional forecasts, beyond the information contained in real indicators.more » « less
-
Forecasting time series data is an important subject in economics, business, and finance. Traditionally, there are several techniques to effectively forecast the next lag of time series data such as univariate Autoregressive (AR), univariate Moving Average (MA), Simple Exponential Smoothing (SES), and more notably Autoregressive Integrated Moving Average (ARIMA) with its many variations. In particular, ARIMA model has demonstrated its outperformance in precision and accuracy of predicting the next lags of time series. With the recent advancement in computational power of computers and more importantly development of more advanced machine learning algorithms and approaches such as deep learning, new algorithms are developed to analyze and forecast time series data. The research question investigated in this article is that whether and how the newly developed deep learning-based algorithms for forecasting time series data, such as “Long Short-Term Memory (LSTM)”, are superior to the traditional algorithms. The empirical studies conducted and reported in this article show that deep learning-based algorithms such as LSTM outperform traditional-based algorithms such as ARIMA model. More specifically, the average reduction in error rates obtained by LSTM was between 84 - 87 percent when compared to ARIMA indicating the superiority of LSTM to ARIMA. Furthermore, it was noticed that the number of training times, known as “epoch” in deep learning, had no effect on the performance of the trained forecast model and it exhibited a truly random behavior.more » « less
-
Chen, Li-Pang (Ed.)BackgroundMany disciplines, such as public health, rely on statistical time series models for real-time and retrospective forecasting efforts; however, effectively implementing related methods often requires extensive programming knowledge. Therefore, such tools remain largely inaccessible to those with limited programming experience, including students training in modeling, as well as professionals and policymakers seeking to forecast an epidemic’s trajectory. To address the need for accessible and intuitive forecasting applications, we presentStatModPredict, an R-Shiny dashboard for conducting robust forecasting analysis utilizing auto-regressive integrated moving average (ARIMA), generalized linear models (GLM), generalized additive models (GAM), and Meta’s Prophet model. MethodsStatModPredictsupports robust real-time forecasting and retrospective model analysis, including fitting, forecasting, evaluation, visualization, and comparison of results from four popular models. After loading an incident time series data set into the interface, users can easily customize model parameters and forecasting options to obtain the desired output. Additionally,StatModPredictoffers multiple editable figures for, but not limited to, the time series data, the forecasts, and model fit and forecast metrics. Users can also upload external forecasts produced elsewhere and evaluate their performance alongside the dashboard’s built-in models, thereby enabling direct comparisons. We provide a detailed demonstration of the dashboard’s features using publicly available annual HIV case data in the US. A video tutorial is available athttps://www.youtube.com/watch?v=zgZOvqhvqw8. ConclusionsBy eliminating programming barriers,StatModPredictfacilitates exploration and use by students training in forecasting, as well as professionals and policymakers aiming to forecast epidemic trajectories. Additionally, the flexibility in the required input data structure and parameter specification process extends the application ofStatModPredictto any discipline that employs time series data. By offering this open-source interface, we aim to broaden access to forecasting tools, promote hands-on learning, and foster contributions from users across disciplines.more » « less
