Neural network models with different input: An application on stock market forecasting

Mathematical Modeling and Computing, Год журнала: 2025, Номер 12(1), С. 176 - 186

Опубликована: Янв. 1, 2025

It is no doubt challenging to forecast the stock market accurately in reality due ever-changing market. Ever since Artificial Neural Networks (ANNs) have been recognized as universal approximators, they are extensively used forecasting albeit not having a systematic approach identifying optimal input. The appropriate number of significant lags time series corresponds input forecasting. Hence, this study aims compare effect several approaches determining lag for ANNs prior forecasting, based on autocorrelation function, partial Box–Jenkins model and forward selection. performances were compared with benchmark models, namely naïve terms error magnitudes trend change error. In study, all found outperform models such that neural network trained selected from selection 1 31 (ANN4) best it achieved highest accuracy lowest mean absolute percentage Contrary expectations, performed poorly series. different inputs viable quantitative yet more research required better understand other measurements improve performance

Язык: Английский

---

A hybrid Gaussian process-integrated deep learning model for retrofitted building energy optimization in smart city ecosystems

Applied Energy, Год журнала: 2025, Номер 388, С. 125643 - 125643

Опубликована: Март 19, 2025

Язык: Английский

---

An innovative machine learning approach for slope stability prediction by combining shap interpretability and stacking ensemble learning

Environmental Science and Pollution Research, Год журнала: 2025, Номер unknown

Опубликована: Май 7, 2025

Язык: Английский

---

FastLSM-AutoML: Fast, reliable, and robust end-to-end AutoML tool for producing a landslide susceptibility map

Stochastic Environmental Research and Risk Assessment, Год журнала: 2024, Номер unknown

Опубликована: Дек. 11, 2024

Язык: Английский

---

A study of data-driven fault diagnosis and early warning systems for power batteries in new energy vehicles

Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering, Год журнала: 2024, Номер unknown, С. 1260 - 1266

Опубликована: Окт. 18, 2024

Язык: Английский

---