Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Utilizing RNN for Real-time Cryptocurrency Price Prediction and Trading Strategy Optimization

Shamima Nasrin Tumpa, Kehelwala Dewage Gayan Maduranga

TL;DR

This research aims to improve accuracy in price prediction and develop effective trading strategies that address the challenges of cryptocurrency trading by leveraging RNNs' capability to capture long-term patterns in time-series data.

Abstract

This study explores the use of Recurrent Neural Networks (RNN) for real-time cryptocurrency price prediction and optimized trading strategies. Given the high volatility of the cryptocurrency market, traditional forecasting models often fall short. By leveraging RNNs' capability to capture long-term patterns in time-series data, this research aims to improve accuracy in price prediction and develop effective trading strategies. The project follows a structured approach involving data collection, preprocessing, and model refinement, followed by rigorous backtesting for profitability and risk assessment. This work contributes to both the academic and practical fields by providing a robust predictive model and optimized trading strategies that address the challenges of cryptocurrency trading.

Utilizing RNN for Real-time Cryptocurrency Price Prediction and Trading Strategy Optimization

TL;DR

This research aims to improve accuracy in price prediction and develop effective trading strategies that address the challenges of cryptocurrency trading by leveraging RNNs' capability to capture long-term patterns in time-series data.

Abstract

This study explores the use of Recurrent Neural Networks (RNN) for real-time cryptocurrency price prediction and optimized trading strategies. Given the high volatility of the cryptocurrency market, traditional forecasting models often fall short. By leveraging RNNs' capability to capture long-term patterns in time-series data, this research aims to improve accuracy in price prediction and develop effective trading strategies. The project follows a structured approach involving data collection, preprocessing, and model refinement, followed by rigorous backtesting for profitability and risk assessment. This work contributes to both the academic and practical fields by providing a robust predictive model and optimized trading strategies that address the challenges of cryptocurrency trading.

Paper Structure

This paper contains 26 sections, 12 equations, 16 figures, 1 table.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Materials and Method
  4. Data Collection and Preprocessing
  5. Exploratory Data Analysis
  6. Dataset Splitting
  7. Model Development
  8. Model Training and Testing
  9. Performance Evaluation
  10. Dataset
  11. Data Imputation and Reshaping
  12. Normalization
  13. Data Splitting
  14. Experimental Setup
  15. Recurrent Neural Network (RNN) Models
  16. ...and 11 more sections

Figures (16)

  • Figure 1: Flowchart of the methodology used for cryptocurrency price prediction (adapted from Seabe2022).
  • Figure 2: LSTM architecture showing the flow of information through the input, forget, and output gates (adapted from Seabe2022).
  • Figure 3: GRU architecture showing the flow of information through the update and reset gates (adapted from Seabe2022).
  • Figure 4: Bi-LSTM architecture showing forward and backward data flow for improved sequence understanding (adapted from Baeldung2023_LSTM).
  • Figure 5: Training and validation loss for BTC
  • ...and 11 more figures