Unraveling the Dynamics of SPY Trading Volumes: A Comprehensive Analysis of Daily and Intraday Liquidity Trends

TL;DR

This study evaluates methods for accurately forecasting SPY trading volumes, demonstrating that ARIMA models with exogenous variables and seasonal adjustments outperform naive baselines in predicting intraday and daily liquidity trends.

Contribution

It introduces a comprehensive analysis comparing ARIMA, ARIMAX, and frequency domain models for SPY volume forecasting, highlighting the effectiveness of ARIMA with exogenous variables and seasonality.

Findings

ARIMA with exogenous variables yields the most accurate volume forecasts.

Seasonality improves intraday volume prediction accuracy.

Models outperform naive baseline methodologies in VWAP tracking.

Abstract

In this project, we investigate the accuracy of forecasting intraday and daily trading volume of the exchange-traded fund SPY. The ability to forecast volume over varying time intervals with high accuracy is a critical element to many trading strategies. After performing exploratory data analysis on intraday and daily SPY data we identify three methods for our analysis: ARIMA and ARIMAX models, with or without seasonality, as well as a Frequency Domain Process Representation. To evaluate predictive power of our models, we use mean squared error, mean absolute percentage error, and volume weighted average price (VWAP) tracking error. All models for both intraday and daily data output strong VWAP predictions in comparison to the VWAP estimates produced by naive baseline methodologies. In both cases volume is most accurately forecasted using ARIMA models with exogenous variables in the form of technical indicators, with intraday incorporating a seasonal component and daily not.