Flowz: When Does Learning Forecast Errors Add Value? Conditional Flow Matching for Financial Price Forecasts
Abstract
Learning a forecasting model's errors offers a modular way to improve its predictive distribution while retaining its underlying dynamics. We study this approach with Flowz, a conditional flow model of direct multi-step price-level residuals fitted using random features and ridge regression. Each EWMA, ARIMA, ARFIMA, and structural baseline is compared with a Gaussian residual location-scale control and a conditional Flowz extension. The experiment uses 24 US stocks selected across four liquidity-volatility strata, 104 common forecast origins, horizons of 5, 10, 20, 40, 80, and 160 trading observations, and three fit seeds. Marginal CRPS is the primary score. At farther horizons, Flowz reduces mean CRPS by 30.7% against EWMA and 24.0% against its Gaussian residual control. The EWMA improvement holds at each fit seed and exceeds the Gaussian control for all 24 stocks in the far band. The ARIMA, ARFIMA, and structural extensions worsen both comparators. Conditional residual learning is therefore useful for the drifting EWMA specification in this experiment, with gains concentrated at longer horizons.
Related
- Target alignment, dilution and forecast selection when cross-sectional forecasts share a common target
- Market-Informed Networks for Modeling and Forecast Evaluation of Financial Extremes
- Aggregate Calibration Can Mask Stress-State Undercoverage: Bounded-Memory Forecast Intervals under Recurrent Financial Stress
- Mathematical Characterization of Dynamic Risk Spillovers in Carbon-Energy Financial Networks with Multi-Dimensional Uncertainty: A TVP-VAR-DY Connectedness Approach via Generalized Forecast-Error Variance Decomposition
- Towards Calibrated Probabilistic Forecasts for Events of Interest via Outcome-Conditional Recalibration
BibTeX
@misc{vercellino2026flowz,
title = {{Flowz: When Does Learning Forecast Errors Add Value? Conditional Flow Matching for Financial Price Forecasts}},
author = {Giancarlo Vercellino},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.29991},
eprint = {2610.29991},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.29991},
}
RIS
TY - UNPB
TI - Flowz: When Does Learning Forecast Errors Add Value? Conditional Flow Matching for Financial Price Forecasts
AU - Giancarlo Vercellino
PY - 2026
DA - 2026/10/21
PB - arXiv
DO - 10.48550/arxiv.2610.29991
UR - https://arxiv.org/abs/2610.29991
AB - Learning a forecasting model's errors offers a modular way to improve its predictive distribution while retaining its underlying dynamics. We study this approach with Flowz, a conditional flow model of direct multi-step price-level residuals fitted using random features and ridge regression. Each EWMA, ARIMA, ARFIMA, and structural baseline is compared with a Gaussian residual location-scale control and a conditional Flowz extension. The experiment uses 24 US stocks selected across four liquidity-volatility strata, 104 common forecast origins, horizons of 5, 10, 20, 40, 80, and 160 trading observations, and three fit seeds. Marginal CRPS is the primary score. At farther horizons, Flowz reduces mean CRPS by 30.7% against EWMA and 24.0% against its Gaussian residual control. The EWMA improvement holds at each fit seed and exceeds the Gaussian control for all 24 stocks in the far band. The ARIMA, ARFIMA, and structural extensions worsen both comparators. Conditional residual learning is therefore useful for the drifting EWMA specification in this experiment, with gains concentrated at longer horizons.
ER -