IVE: Enhanced Probabilistic Forecasting of Intraday Volume Ratio with Transformers

TL;DR

This paper introduces a Transformer-based probabilistic model for intraday volume ratio forecasting in financial markets, improving prediction accuracy and enabling practical trading applications for VWAP strategies.

Contribution

The study develops a novel Transformer architecture for probabilistic volume ratio prediction, incorporating external features and outperforming benchmarks in live trading tests.

Findings

Transformer model achieves high prediction accuracy.

Probabilistic forecasts capture volume spikes effectively.

Model outperforms VWAP benchmarks in live trading.

Abstract

This paper presents a new approach to volume ratio prediction in financial markets, specifically targeting the execution of Volume-Weighted Average Price (VWAP) strategies. Recognizing the importance of accurate volume profile forecasting, our research leverages the Transformer architecture to predict intraday volume ratio at a one-minute scale. We diverge from prior models that use log-transformed volume or turnover rates, instead opting for a prediction model that accounts for the intraday volume ratio's high variability, stabilized via log-normal transformation. Our input data incorporates not only the statistical properties of volume but also external volume-related features, absolute time information, and stock-specific characteristics to enhance prediction accuracy. The model structure includes an encoder-decoder Transformer architecture with a distribution head for greedy sampling, optimizing performance on high-liquidity stocks across both Korean and American markets. We extend the capabilities of our model beyond point prediction by introducing probabilistic forecasting that captures the mean and standard deviation of volume ratios, enabling the anticipation of significant intraday volume spikes. Furthermore, an agent with a simple trading logic demonstrates the practical application of our model through live trading tests in the Korean market, outperforming VWAP benchmarks over a period of two and a half months. Our findings underscore the potential of Transformer-based probabilistic models for volume ratio prediction and pave the way for future research advancements in this domain.