Abstract :

Cryptocurrency Trading Has Emerged As A Global Phenomenon,characterized By High Volatility And Unpredictability.Accurate Forecasting Of Cryptocurrency Prices Is Critical For Traders, Investors, And Financial Institutions To Make Informed Decisions, Mitigate Risks And Maximize Returns.However, Traditional Forecasting Systems Often Fail To Capture The Complex And Non Linear Patterns Inherent In Cryptocurrency Markets.These Systems Struggle With Dynamic Factors Such As Market Sentiment, Global Events, And Regulatory Changes, Leading To Unreliable Predictions.This Project Proposes A Solution By Employing Long Short-Term Memory (LSTM) Neural Networks, A Type Of Deep Learning Model Optimized For Sequential Data, To Predict Prices.By Leveraging Historical Price Data And Advanced Data Preprocessing Techniques, The Model Demonstrates Improved Performance In Capturing Market Trends And Making Accurate Predictions.The Evaluation Metrics, Including Mean Absolute Error (MAE), Mean Squared Error (MSE), And Accuracy, Highlight The Model’s Effectiveness In Addressing The Limitations Of Traditional Approaches.Additionally, The Adoption Of LSTM Models Allows For The Incorporation Of Timedependent Features,improving The Reliability Of Forecasts Even In Volatile Environment.This Project Not Only Addresses The Challenges Posed By Traditional Forecasting Systems But Also Introduces A Scalable Framework That Can Adapt To The Evolving Dynamics Of Cryptocurrency Markets.By Automating Feature Extraction And Leveraging Deep Learning Capabilities, The Model Reduces The Dependency On Manual Interventions And Domain-specific Expertise

Published:

25-8-2025

Issue:

Vol. 25 No. 8 (2025)

Page Nos:

387-396

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite