Comparative Analysis of Bitcoin Price Prediction Models: A Systematic literature review

This paper presents a systematic literature review of machine learning models used for predicting Bitcoin prices. We identified and analyzed 26 different machine learning models notable for their effectiveness in predictive tasks. Out of these, 6 models are discussed in detail, focusing on their advantages, disadvantages, and potential hybrid approaches. Additionally, we collected 21 evaluation metrics, identifying 8 as the most relevant for cryptocurrency price prediction. In terms of datasets, we found a reliance on public sources such as Kaggle and Yahoo Finance; however, challenges related to the inconsistency in data availability remain. Lastly, we noted a lack of standardized procedures for comparing models, highlighting the need for the development of systematic methodologies to standardize evaluations in this field. Smart citations: https://scite.ai/reports/10.61467/2007.1558.2026.v17i2.1166Dimensions.Open Alex.