Partial multivariate transformer as a tool for cryptocurrencies time series prediction
This addresses the problem of forecasting volatile cryptocurrency prices for traders and researchers, but it is incremental as it builds on existing transformer methods with a partial-multivariate strategy.
The paper tackled cryptocurrency price forecasting by proposing a partial-multivariate transformer (PMformer) to balance information and noise, achieving significant statistical accuracy in predicting daily returns for BTCUSDT and ETHUSDT, but found that lower prediction error did not consistently lead to higher financial returns in simulations.
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.