Application of adaptive harmony search and machine learning on optimization problems about strength of materials

Elsevier eBooks, Год журнала: 2025, Номер unknown, С. 273 - 295

Опубликована: Янв. 1, 2025

Язык: Английский

OCENA SKUTECZNOŚCI PROGNOZOWANIA CEN BITCOINÓW PRZY UŻYCIU TECHNIK UCZENIA MASZYNOWEGO NA DANYCH HISTORYCZNYCH

Informatyka Automatyka Pomiary w Gospodarce i Ochronie Środowiska, Год журнала: 2024, Номер 14(2), С. 101 - 108

Опубликована: Июнь 30, 2024

Since entering the market in 2009, Bitcoin has had a price that is extremely erratic. Its influenced by factors such as adoption rates, regulatory changes, geopolitical occurrences, and macroeconomic developments. Experts believe Bitcoin's will rise long run due to limited supply rising demand. Therefore, aim of this study propose an ensemble feature selection machine learning-based approach predict bitcoin price. For research purpose, cryptocurrency-based dataset been used, visualized, preprocessed. Five different approaches (Pearson, RFE, Embedded Random Forest, Tree-based Light GBM) are followed methodology, with maximum voting extract most significant features generate reduced attributes. Then or without used for prediction applying ten learning regressing models, which includes six traditional, four bagging boosting techniques. The comparative result analysis through multiple performance parameters reveals decreased number improves each models outperform other types models. Forest regression ML model can get best accuracy 0.036018 RMSE, 0.029470 MAE 0.934512 R2 employing estimating value bitcoin.

Язык: Английский

Bitcoin Price Predictive Dynamics Using Machine Learning Models

2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT), Год журнала: 2024, Номер unknown, С. 1 - 6

Опубликована: Июнь 24, 2024

Язык: Английский