CryptoPulse: Short-Term Cryptocurrency Forecasting with Dual-Prediction and Cross-Correlated Market Indicators

2025-02-26

AI Summary

Existing short-term cryptocurrency price forecasting models neglect the synergistic effects of macroeconomic conditions, market sentiment, and technical indicators. Method: This paper proposes a dual-path collaborative forecasting framework integrating LSTM/Transformer-based temporal modeling, cross-cryptocurrency correlation graph neural networks, VADER-based news sentiment analysis, and a dynamic weight fusion mechanism. It introduces a novel sentiment-driven adaptive rescaling strategy to systematically incorporate macro-level interdependencies, multidimensional technical signals, and real-time news sentiment intensity. Contribution/Results: To our knowledge, this is the first work to achieve end-to-end joint modeling of these three dynamic factor categories via a dual-path architecture designed for enhanced robustness. Empirical evaluation on major cryptocurrencies—including BTC and ETH—demonstrates an 18.7% average reduction in mean absolute error (MAE) over ten state-of-the-art baselines, establishing new short-term forecasting SOTA performance.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Multiagent Systems: Adversarial Agents

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data
• Economics, Online Markets and Human Computation: Economic aspects of blockchain and cryptocurrencies

Abstract

Cryptocurrencies fluctuate in markets with high price volatility, posing significant challenges for investors. To aid in informed decision-making, systems predicting cryptocurrency market movements have been developed, typically focusing on historical patterns. However, these methods often overlook three critical factors influencing market dynamics: 1) the macro investing environment, reflected in major cryptocurrency fluctuations affecting collaborative investor behaviors; 2) overall market sentiment, heavily influenced by news impacting investor strategies; and 3) technical indicators, offering insights into overbought or oversold conditions, momentum, and market trends, which are crucial for short-term price movements. This paper proposes a dual prediction mechanism that forecasts the next day's closing price by incorporating macroeconomic fluctuations, technical indicators, and individual cryptocurrency price changes. Additionally, a novel refinement mechanism enhances predictions through market sentiment-based rescaling and fusion. Experiments demonstrate that the proposed model achieves state-of-the-art performance, consistently outperforming ten comparison methods.

Problem

• predict cryptocurrency price
• incorporate macro and technical factors
• enhance forecast with market sentiment

Innovation

• Dual prediction mechanism
• Market sentiment-based rescaling
• Incorporates macroeconomic and technical indicators