Cryptocurrency Price Forecasting Using Machine Learning: Building Intelligent Financial Prediction Models

2025-08-02

AI Summary

Existing cryptocurrency price forecasting models—particularly for XRP/USDT closing prices—commonly neglect market liquidity, limiting predictive accuracy. To address this, we propose and construct two novel liquidity proxy metrics: the Volume Volatility Ratio (VVR) and Volume-Weighted Average Price (VWAP), systematically quantifying liquidity effects. We then integrate historical price data with these liquidity features and comparatively evaluate linear regression, random forest, XGBoost, and LSTM models. Results demonstrate that incorporating VVR and VWAP significantly improves LSTM performance, reducing MAE by 12.7% and RMSE by 11.3%, thereby confirming the critical role of liquidity information in enhancing cryptocurrency price prediction. This work is the first to apply VVR in crypto-asset forecasting and empirically validates that multi-scale liquidity representation strengthens temporal modeling capability.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Computer Vision: Large Vision Models
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Security and Privacy: Cryptocurrency and smart contracts
• Economics, Online Markets and Human Computation: Economic aspects of blockchain and cryptocurrencies
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Cryptocurrency markets are experiencing rapid growth, but this expansion comes with significant challenges, particularly in predicting cryptocurrency prices for traders in the U.S. In this study, we explore how deep learning and machine learning models can be used to forecast the closing prices of the XRP/USDT trading pair. While many existing cryptocurrency prediction models focus solely on price and volume patterns, they often overlook market liquidity, a crucial factor in price predictability. To address this, we introduce two important liquidity proxy metrics: the Volume-To-Volatility Ratio (VVR) and the Volume-Weighted Average Price (VWAP). These metrics provide a clearer understanding of market stability and liquidity, ultimately enhancing the accuracy of our price predictions. We developed four machine learning models, Linear Regression, Random Forest, XGBoost, and LSTM neural networks, using historical data without incorporating the liquidity proxy metrics, and evaluated their performance. We then retrained the models, including the liquidity proxy metrics, and reassessed their performance. In both cases (with and without the liquidity proxies), the LSTM model consistently outperformed the others. These results underscore the importance of considering market liquidity when predicting cryptocurrency closing prices. Therefore, incorporating these liquidity metrics is essential for more accurate forecasting models. Our findings offer valuable insights for traders and developers seeking to create smarter and more risk-aware strategies in the U.S. digital assets market.

Problem

• Predicting cryptocurrency prices using machine learning models
• Incorporating market liquidity metrics for accurate price forecasts
• Evaluating model performance with and without liquidity proxies

Innovation

• Used deep learning and machine learning models
• Introduced liquidity metrics VVR and VWAP
• LSTM model outperformed other methods consistently