Forecasting Intra-daily Volume in Large Panels of Assets

Brownlees Christian, Crespo Ignacio, Darolles Serge and Fol Gaëlle Le
Additional contact information
Darolles Serge: DRM - Dauphine Recherches en Management - Université Paris Dauphine-PSL - PSL - Université Paris Sciences et Lettres - CNRS - Centre National de la Recherche Scientifique
Fol Gaëlle Le: DRM - Dauphine Recherches en Management - Université Paris Dauphine-PSL - PSL - Université Paris Sciences et Lettres - CNRS - Centre National de la Recherche Scientifique

Working Papers from HAL

Abstract: Intra-daily trading volume forecasts are a key input for several trade execution algorithms. In this study we introduce an intra-daily trading volume forecasting methodology for large panels of assets that combines factor models with sparse vector autoregressions. The highlight of the approach is that it allows to capture both the common market-wide factors driving trading activity as well as the sparse network of spillover effects among individual assets. We apply the methodology to predict the intra-daily trading volume of a panel of constituents of the STOXX 600 index for a range of intra-daily frequencies ranging from 5 minutes to 30 minutes. We assess both the statistical accuracy as well as the economic value of the predictions relative to a number of benchmarks. In particular, we assess the economic value of the prediction through a VWAP trade execution exercise. Results show that our proposed methodology delivers both statistical and economic gains, with the largest improvements being associated with the most interconnected stocks.

Keywords: Intra-daily Volume; Factor Models; Networks; Machine Learning (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:wpaper:hal-05440876

Access Statistics for this paper

More papers in Working Papers from HAL
Bibliographic data for series maintained by CCSD ().