Paper Title: Performance Evaluation of Ethereum Price Prediction Utilizing Support Vector Regression
Author's name: Ramya Sree KN, Vidhya A, Jotheeswaran G, Depak kumarasan C
In recent years, the popularity and usage of cryptocurrencies have surged along with their values, and Ethereum has emerged as the second most renowned cryptocurrency, following Bitcoin. Cryptocurrencies are built on block chain technology, which is decentralized and has the potential to revolutionize traditional banking systems. This Python program utilizes the finance library to gather historical price data for the cryptocurrency Ethereum (ETH) from Yahoo Finance. The collected data is then employed to train a Support Vector Regression (SVR) model, which aims to predict the future price of ETH. This paper presents a comparative analysis of the prediction accuracy between the (SVR) model and the (LR) model. The program initially downloads and saves the data to a CSV file. Subsequently, the data is preprocessed by adding a column to the Data Frame containing the future price of ETH, projected for a specified number of days ahead. Using the train and test split function from the sci-kit-learn library, the programme then divides the data into training and testing sets. An SVR model with a radial basis function kernel is fitted to the training set. Finally, the model's performance is evaluated using the R-squared score, and the program generates forecasts for the price of ETH using the testing set. The actual and forecasted ETH price values are visualized using the matplotlib library, enabling a comprehensive comparison of the model's predictions.