Comparison of Machine Learning Algorithms for Creation of a Bitcoin Price Prediction Model

With theadvancement ofmachine learning tools, anincreasing number ofalgorithms are being utilized for predicting not only traditional time series data related tofinancial markets but also those connected tocryptocurrencies. This paper aims tocompare various machine learning algorithms used for prediction, inorder toidentify theone with thegreatest practical potential for creating aprediction model ofBitcoin’s price asaninvestment asset. Theanalysis focuses onsupervised learning algorithms, taking into account thenature ofthetask involving long time series datasets. Thepaper also describes theexact process ofcreating and setting up individual models and their parameters, explaining procedures for obtaining and editing datasets, and shows how toevaluate performance ofthese models. Inaddition totheanalysis ofthemain subject ofresearch, which is Bitcoin, thepaper also uses ananalysis ofreference cryptocurrencies such asEthereum, Litecoin and NEO tocompare theresulting performances. Theprocesses consisting ofediting theanalysed datasets, creating individual prediction models, training and testing theperformance ofmodels onhistorical data, and creating, debugging and implementing individual machine learning models were realised through coding inthePython program

Economics · Machine learning · Artificial Intelligence · Computer Science · Forecasting Techniques and Applications · Statistical and Computational Modeling · Stock Market Forecasting Methods