Predictive Modeling of Cryptocurrency Price Movements Using Autoregressive and Neural Network Models

Sandeep Yadav

doi:10.5281/zenodo.14288541

Predictive Modeling of Cryptocurrency Price Movements Using Autoregressive and Neural Network Models

Author(s)	Sandeep Yadav
Country	United States
Abstract	Cryptocurrency markets are highly volatile and driven by complex, non-linear dynamics, posing significant challenges for price prediction. This research explores the predictive modeling of cryptocurrency price movements by integrating traditional statistical techniques, such as Autoregressive (AR) models, with advanced Neural Network (NN) architectures. The study evaluates the performance of these models in forecasting short-term price trends for major cryptocurrencies like Bitcoin, Ethereum, and Binance Coin. The dataset consists of historical price data and technical indicators, preprocessed to address missing values, outliers, and non-stationarity. Autoregressive models provide interpretable baseline predictions by capturing temporal dependencies in price series, while Neural Networks leverage their capability to learn complex patterns and relationships within the data. Experimental results demonstrate that Neural Network models, particularly Long Short-Term Memory (LSTM) networks, outperform AR models in terms of accuracy, root mean squared error (RMSE), and directional accuracy. However, AR models exhibit competitive performance in periods of low market volatility due to their simplicity and robustness. This research highlights the strengths and limitations of both approaches, providing insights into their applicability for cryptocurrency price prediction. The findings underscore the potential of hybrid models, combining the interpretability of AR models with the predictive power of NNs, to enhance decision-making in cryptocurrency trading and risk management. Future work could explore the integration of alternative data sources, such as social media sentiment and blockchain activity, to further improve prediction accuracy.
Keywords	Cryptocurrency Price Prediction, Autoregressive Models, Neural Networks, Long Short-Term Memory (LSTM), Time Series Analysis, Price Forecasting, Machine Learning in Finance, Cryptocurrency Volatility, Predictive Modeling, Hybrid Prediction Models
Published In	Volume 14, Issue 1, January-March 2023
Published On	2023-01-09
Cite This	Predictive Modeling of Cryptocurrency Price Movements Using Autoregressive and Neural Network Models - Sandeep Yadav - IJSAT Volume 14, Issue 1, January-March 2023. DOI 10.5281/zenodo.14288541
DOI	https://doi.org/10.5281/zenodo.14288541
Short DOI	https://doi.org/g8txvq

View / Download PDF File

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 15 Isu 4 Cover Page Vol 15 Isu 3 Cover Page Vol 15 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Predictive Modeling of Cryptocurrency Price Movements Using Autoregressive and Neural Network Models

Share this