Exploration of Stacked Ensemble Models for Bitcoin Price Prediction Using Diverse Look-Back Windows

Abstract

This research paper presents a stacked ensemble model for next day Bitcoin price prediction, incorporating diverse look-back windows and evaluating the performance of various models within the ensemble framework using metrics like Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). The base layer, layer-0, comprises LSTM and GRU models with different look-back windows. The layer-1 models, including CNN, SVR, Linear Regression, Random Forest Regressor, LSTM, and KNN, are tested individually in conjunction with the base layer models. Extensive experiments demonstrate the effectiveness of the stacked ensemble approach, improving prediction accuracy. The comparative analysis provides insights into the strengths and weaknesses of each model, aiding in the identification of optimized combinations for Bitcoin price prediction. This research contributes to the field by showcasing the value of diverse look-back windows and evaluating models in a stacked ensemble framework, enhancing the accuracy of Bitcoin price forecasting.