Machine Learning-Based Time Series Analysis for Cryptocurrency Price Prediction using Synthetic Data
- Version
- Download 4
- File Size 275.29 KB
- File Count 1
- Create Date 24 March 2026
- Last Updated 24 March 2026
Machine Learning-Based Time Series Analysis for Cryptocurrency Price Prediction using Synthetic Data
Dr. K. Satyam1, Desman Likhitha2
1Associate Professor, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati, AndhraPradesh, India.
2 Post Graduate, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati, AndhraPradesh, India.
ABSTRACT:Because of the tremendous volatility and erratic behaviour of cryptocurrency markets, it is difficult to estimate prices accurately. This research uses a synthetic time-series dataset to provide a machine learning-based method for predicting bitcoin prices. Open price, peak price, low price, close price, and trading volume are among the daily trading features in the dataset that mimic actual market conditions. The suggested approach analyses past trends and forecasts future closing prices using a variety of regression-based machine learning models. To increase the accuracy and efficiency of the model, data preprocessing methods including feature selection and normalisation are used. Standard measures like Mean Absolute Error (MAE), Mean Squared Error (MSE), and R-squared score are used in the study to assess model performance. Even when trained on artificial data, experimental results show that machine learning algorithms may successfully identify underlying patterns in bitcoin price movements. The results show the promise of predictive modelling in financial forecasting and lay the groundwork for future studies utilising cutting-edge deep learning techniques and real-world datasets.
KEYWORDS:Cryptocurrency, Machine Learning, Price Prediction, Time Series Analysis, Synthetic Dataset, Regression Models, Financial Forecasting, Data Preprocessing
Download