Partial multivariate transformer as a tool for cryptocurrencies time series prediction

• URL: http://arxiv.org/abs/2512.04099v1
• Date: Sat, 22 Nov 2025 21:59:32 GMT
• Title: Partial multivariate transformer as a tool for cryptocurrencies time series prediction
• Authors: Andrzej Tokajuk, Jarosław A. Chudziak,
• Abstract summary: We show that a partial-multivariate strategy achieves significant statistical accuracy, effectively balancing informative signals with noise.<n>Lower prediction error did not consistently translate to higher financial returns in simulations.<n>This finding challenges the reliance on traditional error metrics and highlights the need to develop evaluation criteria more aligned with real-world financial objectives.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• On the Effect of Regularization on Nonparametric Mean-Variance Regression [22.758981850171548]
  We develop a statistical field theory framework, which captures the observed phase transition in alignment with experimental results.<n>Experiments on UCI datasets and the large-scale ClimSim dataset demonstrate robust calibration performance, effectively quantifying predictive uncertainty.
  arXiv  Detail & Related papers  (2025-11-27T01:09:28Z)
• Multivariate Forecasting of Bitcoin Volatility with Gradient Boosting: Deterministic, Probabilistic, and Feature Importance Perspectives [1.8352113484137627]
  This study investigates the application of the Light Gradient Boosting Machine (LGBM) model for both deterministic and probabilistic forecasting of Bitcoin realized volatility.<n>We evaluate the performance of LGBM-based models and compare them with both econometric and machine learning baselines.
  arXiv  Detail & Related papers  (2025-11-25T09:26:13Z)
• Auditing Algorithmic Bias in Transformer-Based Trading [10.235738752130803]
  We employ a transformer model for prediction, and introduce a metric based on Partial Information Decomposition (PID) to measure the influence of each asset on the model's decision making.<n>Our analysis reveals two key observations: first, the model disregards data volatility entirely, and second, it is biased toward data with lower-frequency price movements.
  arXiv  Detail & Related papers  (2025-10-01T21:20:26Z)
• Probabilistic Forecasting Cryptocurrencies Volatility: From Point to Quantile Forecasts [1.8352113484137627]
  This paper introduces probabilistic forecasting methods that leverage point forecasts from a wide range of base models.<n>To the best of our knowledge, this is the first study in the literature to propose and systematically evaluate probabilistic forecasts of variance in cryptocurrency markets.<n>Our empirical results for Bitcoin demonstrate that the Quantile Estimation through Residual Simulation (QRS) method consistently outperforms more sophisticated alternatives.
  arXiv  Detail & Related papers  (2025-08-21T18:42:11Z)
• AMA-LSTM: Pioneering Robust and Fair Financial Audio Analysis for Stock Volatility Prediction [25.711345527738068]
  multimodal methods have faced two drawbacks. They often fail to yield reliable models and overfit the data due to their absorption of information from the stock market. Using multimodal models to predict stock volatility suffers from gender bias and lacks an efficient way to eliminate such bias. Our comprehensive experiments on robustness-world financial audio datasets reveal that this method exceeds the performance of current state-of-the-art solution.
  arXiv  Detail & Related papers  (2024-07-03T18:40:53Z)
• Structured Radial Basis Function Network: Modelling Diversity for Multiple Hypotheses Prediction [51.82628081279621]
  Multi-modal regression is important in forecasting nonstationary processes or with a complex mixture of distributions. A Structured Radial Basis Function Network is presented as an ensemble of multiple hypotheses predictors for regression problems. It is proved that this structured model can efficiently interpolate this tessellation and approximate the multiple hypotheses target distribution.
  arXiv  Detail & Related papers  (2023-09-02T01:27:53Z)
• Diffusion Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock Price Prediction [54.21695754082441]
  Multi-step stock price prediction over a long-term horizon is crucial for forecasting its volatility. Current solutions to multi-step stock price prediction are mostly designed for single-step, classification-based predictions. We combine a deep hierarchical variational-autoencoder (VAE) and diffusion probabilistic techniques to do seq2seq stock prediction. Our model is shown to outperform state-of-the-art solutions in terms of its prediction accuracy and variance.
  arXiv  Detail & Related papers  (2023-08-18T16:21:15Z)
• DeepVol: Volatility Forecasting from High-Frequency Data with Dilated Causal Convolutions [53.37679435230207]
  We propose DeepVol, a model based on Dilated Causal Convolutions that uses high-frequency data to forecast day-ahead volatility. Our empirical results suggest that the proposed deep learning-based approach effectively learns global features from high-frequency data.
  arXiv  Detail & Related papers  (2022-09-23T16:13:47Z)
• Bayesian Bilinear Neural Network for Predicting the Mid-price Dynamics in Limit-Order Book Markets [84.90242084523565]
  Traditional time-series econometric methods often appear incapable of capturing the true complexity of the multi-level interactions driving the price dynamics. By adopting a state-of-the-art second-order optimization algorithm, we train a Bayesian bilinear neural network with temporal attention. By addressing the use of predictive distributions to analyze errors and uncertainties associated with the estimated parameters and model forecasts, we thoroughly compare our Bayesian model with traditional ML alternatives.
  arXiv  Detail & Related papers  (2022-03-07T18:59:54Z)
• Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions [91.63716984911278]
  We introduce a novel Mixture of Normal-Inverse Gamma distributions (MoNIG) algorithm, which efficiently estimates uncertainty in principle for adaptive integration of different modalities and produces a trustworthy regression result. Experimental results on both synthetic and different real-world data demonstrate the effectiveness and trustworthiness of our method on various multimodal regression tasks.
  arXiv  Detail & Related papers  (2021-11-11T14:28:12Z)
• Bias-Variance Tradeoffs in Single-Sample Binary Gradient Estimators [100.58924375509659]
  Straight-through (ST) estimator gained popularity due to its simplicity and efficiency. Several techniques were proposed to improve over ST while keeping the same low computational complexity. We conduct a theoretical analysis of Bias and Variance of these methods in order to understand tradeoffs and verify originally claimed properties.
  arXiv  Detail & Related papers  (2021-10-07T15:16:07Z)
• Gaussian process imputation of multiple financial series [71.08576457371433]
  Multiple time series such as financial indicators, stock prices and exchange rates are strongly coupled due to their dependence on the latent state of the market. We focus on learning the relationships among financial time series by modelling them through a multi-output Gaussian process.
  arXiv  Detail & Related papers  (2020-02-11T19:18:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.