ASTIF: Adaptive Semantic-Temporal Integration for Cryptocurrency Price Forecasting

TL;DR

The paper introduces ASTIF, a hybrid system that adaptively combines semantic insights and temporal data for more accurate cryptocurrency price forecasting, especially during market shifts.

Contribution

It presents a novel adaptive framework integrating semantic and temporal models with confidence-based meta-learning for real-time financial prediction.

Findings

ASTIF outperforms existing deep learning models like Informer and TFT.

The adaptive meta-learning mechanism improves robustness during market turbulence.

Semantic and temporal integration enhances forecasting accuracy.

Abstract

Financial time series forecasting is fundamentally an information fusion challenge, yet most existing models rely on static architectures that struggle to integrate heterogeneous knowledge sources or adjust to rapid regime shifts. Conventional approaches, relying exclusively on historical price sequences, often neglect the semantic drivers of volatility such as policy uncertainty and market narratives. To address these limitations, we propose the ASTIF (Adaptive Semantic-Temporal Integration for Cryptocurrency Price Forecasting), a hybrid intelligent system that adapts its forecasting strategy in real time through confidence-based meta-learning. The framework integrates three complementary components. A dual-channel Small Language Model using MirrorPrompt extracts semantic market cues alongside numerical trends. A hybrid LSTM Random Forest model captures sequential temporal dependencies. A confidence-aware meta-learner functions as an adaptive inference layer, modulating each predictor's contribution based on its real-time uncertainty. Experimental evaluation on a diverse dataset of AI-focused cryptocurrencies and major technology stocks from 2020 to 2024 shows that ASTIF outperforms leading deep learning and Transformer baselines (e.g., Informer, TFT). The ablation studies further confirm the critical role of the adaptive meta-learning mechanism, which successfully mitigates risk by shifting reliance between semantic and temporal channels during market turbulence. The research contributes a scalable, knowledge-based solution for fusing quantitative and qualitative data in non-stationary environments.