Crypto Prophets: Machine Learning Oracles for Price Forecasting

Cryptocurrency has emerged as a revolutionary financial asset, captivating investors and researchers alike with its volatile nature and potential for high returns. As the market continues to evolve, there is an increasing need for sophisticated tools to predict price movements and inform investment decisions. This research work delves into a predictive assessment of cryptocurrency price fluctuations, using thorough machine learning techniques to project future prices for Monero, Ethereum, Wrapped Bitcoin, and Bitcoin—the four leading cryptocurrencies. Using historical price data, our methodology includes data preprocessing, feature selection, and the application of various machine learning models such as Linear Regression, Extreme Gradient Boosting (XGBoost), K-Nearest Neighbors (KNN), Random Forest, and Support Vector Regression (SVR). The models’ predictive performance was meticulously evaluated using Mean Squared Error (MSE), R-squared (R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>), and Mean Absolute Percentage Error (MAPE). Linear Regression achieved superior performance for Bitcoin with an R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> score of 0.9823 and Wrapped Bitcoin with an R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> score of 0.9780, while XG-Boost excelled in Monero predictions with the lowest MSE of 325.33. This research offers critical insights for investors, market strategists, and financial analysts, underscoring the prominent impact of machine learning in enhancing the market analysis of cryptocurrencies and informing decision-making processes. The work immensely contributes to the flourishing area of financial technology, suggesting various ways to move forward with integrated advanced predictive models and sentiment analysis of markets and economic indicators to redefine investment strategies in the highly volatile cryptocurrency domain.

Authors

Institutions

Publication Details

Published
2024-09-13
DOI
https://doi.org/10.1109/icietdw61607.2024.10941381
Primary Topic
Stock Market Forecasting Methods
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Crypto Prophets: Machine Learning Oracles for Price Forecasting

S Baghavathi Priya, S. Priyanga, Veda Chatiyode, Janani Srinivasan Anusha
Stock Market Forecasting Methods
article

Crypto Prophets: Machine Learning Oracles for Price Forecasting

S Baghavathi Priya, S. Priyanga, Veda Chatiyode, Janani Srinivasan Anusha
article en

Abstract

Cryptocurrency has emerged as a revolutionary financial asset, captivating investors and researchers alike with its volatile nature and potential for high returns. As the market continues to evolve, there is an increasing need for sophisticated tools to predict price movements and inform investment decisions. This research work delves into a predictive assessment of cryptocurrency price fluctuations, using thorough machine learning techniques to project future prices for Monero, Ethereum, Wrapped Bitcoin, and Bitcoin—the four leading cryptocurrencies. Using historical price data, our methodology includes data preprocessing, feature selection, and the application of various machine learning models such as Linear Regression, Extreme Gradient Boosting (XGBoost), K-Nearest Neighbors (KNN), Random Forest, and Support Vector Regression (SVR). The models’ predictive performance was meticulously evaluated using Mean Squared Error (MSE), R-squared (R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>), and Mean Absolute Percentage Error (MAPE). Linear Regression achieved superior performance for Bitcoin with an R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> score of 0.9823 and Wrapped Bitcoin with an R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> score of 0.9780, while XG-Boost excelled in Monero predictions with the lowest MSE of 325.33. This research offers critical insights for investors, market strategists, and financial analysts, underscoring the prominent impact of machine learning in enhancing the market analysis of cryptocurrencies and informing decision-making processes. The work immensely contributes to the flourishing area of financial technology, suggesting various ways to move forward with integrated advanced predictive models and sentiment analysis of markets and economic indicators to redefine investment strategies in the highly volatile cryptocurrency domain.

Amrita Vishwa Vidyapeetham (IN)
Openalex Percentile: Top 66%
Stock Market Forecasting Methods
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.