Equity2Vec: End-to-end Deep Learning Framework for Cross-sectional Asset Pricing

Qiong Wu, Christopher G. Brinton, Zheng Zhang, Andrea Pizzoferrato, Zhenming Liu, Mihai Cucuringu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

Pricing assets has attracted significant attention from the financial technology community. We observe that the existing solutions overlook the cross-sectional effects and not fully leveraged the heterogeneous data sets, leading to sub-optimal performance. To this end, we propose an end-to-end deep learning framework to price the assets. Our framework possesses two main properties: 1) We propose Eqity2Vec, a graph-based component that effectively captures both long-term and evolving cross-sectional interactions. 2) The framework simultaneously leverages all the available heterogeneous alpha sources including technical indicators, financial news signals, and cross-sectional signals. Experimental results on datasets from the real-world stock market show that our approach outperforms the existing state-of-the-art approaches. Furthermore, market trading simulations demonstrate that our framework monetizes the signals effectively.

Original languageEnglish (US)
Title of host publicationICAIF 2021 - 2nd ACM International Conference on AI in Finance
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450391481
DOIs
StatePublished - Nov 3 2021
Externally publishedYes
Event2nd ACM International Conference on AI in Finance, ICAIF 2021 - Virtual, Online
Duration: Nov 3 2021Nov 5 2021

Publication series

NameICAIF 2021 - 2nd ACM International Conference on AI in Finance

Conference

Conference2nd ACM International Conference on AI in Finance, ICAIF 2021
CityVirtual, Online
Period11/3/2111/5/21

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Finance

Fingerprint

Dive into the research topics of 'Equity2Vec: End-to-end Deep Learning Framework for Cross-sectional Asset Pricing'. Together they form a unique fingerprint.

Cite this