Partial multivariate transformer as a tool for cryptocurrencies time series prediction

TL;DR

This paper introduces a partial-multivariate transformer approach for cryptocurrency price prediction, balancing feature selection to improve accuracy and examining its practical trading utility, revealing a disconnect between statistical performance and financial gains.

Contribution

It proposes a novel partial-multivariate transformer model for cryptocurrency forecasting and evaluates its effectiveness compared to classical and deep learning models.

Findings

Partial-multivariate approach improves statistical accuracy.

Lower prediction error does not always lead to higher trading returns.

Highlights need for evaluation metrics aligned with financial objectives.

Abstract

Forecasting cryptocurrency prices is hindered by extreme volatility and a methodological dilemma between information-scarce univariate models and noise-prone full-multivariate models. This paper investigates a partial-multivariate approach to balance this trade-off, hypothesizing that a strategic subset of features offers superior predictive power. We apply the Partial-Multivariate Transformer (PMformer) to forecast daily returns for BTCUSDT and ETHUSDT, benchmarking it against eleven classical and deep learning models. Our empirical results yield two primary contributions. First, we demonstrate that the partial-multivariate strategy achieves significant statistical accuracy, effectively balancing informative signals with noise. Second, we experiment and discuss an observable disconnect between this statistical performance and practical trading utility; lower prediction error did not consistently translate to higher financial returns in simulations. This finding challenges the reliance on traditional error metrics and highlights the need to develop evaluation criteria more aligned with real-world financial objectives.