Skip to content
Open access

MSPCIFormer: A Multi‐Scale Patching Channel‐Independent Transformer for Cryptocurrency Price Forecasting

Jul 2026 · Expert systems · Vol 43 · 0 citations · 66 references

TL;DR

MSPCIFormer is proposed, a novel Transformer‐based architecture that integrates multi‐scale patching with channel‐independent (CI) modelling to capture heterogeneous temporal dynamics while mitigating noise from time‐varying inter‐asset correlations.

Abstract

Forecasting cryptocurrency prices remains challenging due to extreme volatility, regime‐dependent dynamics, and unstable cross‐asset correlations. Statistical methods such as ARIMA and GARCH assume stationarity and linear dependence structures, making them inadequate for capturing non‐linear temporal patterns in high volatile cryptocurrency data. Conventional machine learning methods often require hand‐crafted features and fail to capture the sequential temporal dependencies inherent in price series. Recurrent deep learning approaches such as recurrent neural networks (RNNs) and LSTMs address the issues but suffer from limited parallelization, vanishing gradients, and difficulty in learning multi‐scale temporal patterns. The advances in Transformer have demonstrated strong capability in capturing long‐range temporal dependencies through self‐attention while enabling parallel computation. However, canonical Transformer still struggle with noisy, volatile financial time series due to computational complexity and sensitivity to irrelevant temporal patterns. These limitations motivate the exploration of Transformer‐based architectures. Our study makes three key contributions. First, we propose MSPCIFormer, a novel Transformer‐based architecture that integrates multi‐scale patching with channel‐independent (CI) modelling to capture heterogeneous temporal dynamics while mitigating noise from time‐varying inter‐asset correlations. Second, we conduct comprehensive experiments comparing MSPCIFormer with state‐of‐the‐art Transformer models and strong time‐series forecasting baselines, evaluated using both statistical and economic metrics across multiple forecasting horizons. Third, we establish a unified evaluation framework incorporating both Hold‐out and Walk‐forward evaluation framework with economical metrics for regime‐robustness testing. Empirical results demonstrate that MSPCIFormer achieves the best or tied‐best predictive accuracy among all Transformer‐based baselines across three cryptocurrency assets, while maintaining competitive and stable performance across diverse market regimes.

Read PDF

Similar papers

Open access Aug 2026

A frequency-guided multi-scale decomposition and patch transformer for multivariate cryptocurrency time-series forecasting

Multivariate cryptocurrency forecasting is challenging because market series exhibit non-stationarity, cross-variable dependence, heterogeneous temporal scales, and abrupt short-term fluctuations. Although Transformer-based forecasting models can capture long-range temporal relationships, directly modeling raw high-frequency sequences may obscure dominant periodic structures and increase computational cost. This study proposes a frequency-guided multi-scale decomposition and patch Transformer, termed FMDP-Transformer, for multivariate cryptocurrency time-series forecasting. First, a frequency-guided multi-scale representation module estimates dominant temporal periods from the Fourier amplitude spectrum and constructs scale-specific representations through period-dependent average pooling. This module is designed to extract multi-scale periodic information and attenuate short-term disturbances rather than to perform explicit anomaly detection. Second, the resulting representation is decomposed into trend and residual components. A lightweight linear projection is used for parsimonious trend extrapolation, while the residual component is divided into overlapping patches and processed by a Transformer encoder to model local and long-range temporal dependencies. The forecasts produced by the two branches are subsequently combined. Experiments on Bitcoin, Dogecoin, and Binance Coin data derived from the G-Research Crypto Forecasting dataset evaluate the model under multiple forecasting horizons. Comparisons with recurrent, decomposition-based, patch-based, inverted-Transformer, and multi-scale forecasting models, together with component ablations and computational-complexity analysis, are used to assess its effectiveness. The results indicate that frequency-guided multi-scale representation, decomposition, and patch tokenization provide complementary benefits for multivariate cryptocurrency forecasting. Nevertheless, the proposed frequency-guided smoothing operation does not explicitly identify statistical anomalies, and abrupt market movements may contain predictive information rather than noise.

Jin Liu, M. Yahya, Saidatunur Fauzi Saidin et al. · 0 citations
Review Open access Jul 2026

Deep Temporal Convolutional Networks for High Frequency Cryptocurrency Price Forecasting

Findings from the application of Deep Temporal Convolutional Networks in high-frequency cryptocurrency price forecasting are synthesized, highlighting TCNs' advantages in computational efficiency, robustness, and adaptability to rapidly shifting trading environments.

Xue Cheng · 0 citations
Conference 2026

DeRNN: Decomposed Recurrent Neural Network for Long-Term Time Series Forecasting

The Decomposed Recurrent Neural Network (DeRNN) is proposed, which decouples global trend modeling from local fluctuation extraction via an asymmetric dual-track architecture and exhibits superior robustness against noise and distribution shifts.

Shanyun Qian · 0 citations
Open access Jul 2026

Causal-Structure-Based Cryptocurrency Price Direction Prediction Model

Analysis of the inferred causal structures showed that the returns improved when trades were executed only during rolling-window trials in which specific directed edges to the target variable were detected, and proposed a causal filter strategy that restricts trading to periods in which specific directed edges to the target variable are detected.

Yuantai Cui, Hiroaki Fukunishi · 0 citations
Open access Aug 2026

Short-Term Price Prediction in Cryptocurrency Ecosystems Using a Hybrid CNN–LSTM Model

This study investigates short-term predictive relationships between major cryptocurrencies—specifically Ethereum (ETH) and Solana (SOL)—and their respective sub-tokens (DYDX, UNI, GRT, JUP, RAY, PYTH) by employing a hybrid deep learning framework that integrates Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models. Using high-frequency data across different time intervals (15 minutes, 1 hour, and 4 hours), the study examines whether price movements in major tokens are associated with enhanced short- and medium-term predictability of ecosystem-based sub-tokens. The empirical results indicate that the hybrid CNN-LSTM model achieves strong forecasting performance at shorter time horizons, while prediction accuracy declines as the time interval increases, reflecting the limiting role of market volatility. The results indicate statistically significant short-term predictive relationships and pronounced co-movement patterns between major token movements and sub-token pricing behavior, particularly at higher-frequency intervals, suggesting that Ethereum and Solana provide informative signals related to ecosystem-wide liquidity and trading activity.

Mehmet Çınar, Muhammed Apak · 0 citations
Open access 2026

A Generative Adaptive Decomposition Hierarchical Transformer for Stock Price Forecasting

Forecasting stock prices is challenging due to the non-stationarity and volatility of financial time series. We propose the Generative Adaptive Decomposition Hierarchical Transformer (GADHT), a hybrid framework that combines adaptive decomposition, masked self-supervised pretraining, and hierarchical attention. GADHT applies Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) to decompose financial signals into intrinsic mode functions (IMFs) that capture multi-scale temporal dynamics. A masked self-supervised pretraining task based on IMF reconstruction is used to learn spectral–temporal representations without labeled data, while a hierarchical transformer with energy-weighted attention emphasizes informative IMFs during forecasting. Experiments on large-cap equities across multiple forecasting horizons show that GADHT achieves competitive and stable forecasting performance. The model maintains stable predictive behavior during stress periods such as the 2008 financial crisis and the 2020 COVID-19 crash, and shows positive economic performance under the adopted backtesting assumptions. Zero-shot and cross-market experiments further suggest that the learned representations can transfer to unseen large-cap equities and selected international markets. Interpretability analysis shows that spectral attention patterns are associated with financial characteristics such as momentum, volatility, and liquidity. Overall, the results suggest that GADHT provides a coherent and interpretable framework for multi-horizon stock forecasting.

Khalid Bentaleb, Mohamed Ben Houad, Mohammed Mestari · 0 citations