Universal features of price formation in financial markets: perspectives from deep learning

Justin Sirignano, Rama Cont

Research output: Contribution to journalArticlepeer-review

Abstract

Using a large-scale Deep Learning approach applied to a high-frequency database containing billions of market quotes and transactions for US equities, we uncover nonparametric evidence for the existence of a universal and stationary relation between order flow history and the direction of price moves. The universal price formation model exhibits a remarkably stable out-of-sample accuracy across a wide range of stocks and time periods. Interestingly, these results also hold for stocks which are not part of the training sample, showing that the relations captured by the model are universal and not asset-specific. The universal model—trained on data from all stocks—outperforms asset-specific models trained on time series of any given stock. This weighs in favor of pooling together financial data from various stocks, rather than designing asset- or sector-specific models, as is currently commonly done. Standard data normalizations based on volatility, price level or average spread, or partitioning the training data into sectors or categories such as large/small tick stocks, do not improve training results. On the other hand, inclusion of price and order flow history over many past observations improves forecast accuracy, indicating that there is path-dependence in price dynamics.

Original languageEnglish (US)
Pages (from-to)1449-1459
Number of pages11
JournalQuantitative Finance
Volume19
Issue number9
DOIs
StatePublished - 2019

Keywords

  • Deep learning
  • Financial econometrics
  • High-frequency data
  • Intraday data
  • Limit order book
  • Machine learning
  • Market microstructure
  • Price formation

ASJC Scopus subject areas

  • Finance
  • Economics, Econometrics and Finance(all)

Fingerprint Dive into the research topics of 'Universal features of price formation in financial markets: perspectives from deep learning'. Together they form a unique fingerprint.

Cite this