TY - GEN
T1 - Equity2Vec
T2 - 2nd ACM International Conference on AI in Finance, ICAIF 2021
AU - Wu, Qiong
AU - Brinton, Christopher G.
AU - Zhang, Zheng
AU - Pizzoferrato, Andrea
AU - Liu, Zhenming
AU - Cucuringu, Mihai
N1 - Funding Information:
We thank anonymous reviewers for helpful comments and suggestions. Christopher G. Brinton was supported in part by the Charles Koch Foundation. Qiong Wu, Zheng Zhang and Zhenming Liu are supported by NSF grants NSF-2008557, NSF-1835821, and NSF-1755769. Mihai Cucuringu and Andrea Pizzoferrato acknowledge support from The Alan Turing Institute EPSRC grant EP/N510129/1. Andrea Pizzoferrato also acknowledges support from the National Group of Mathematical Physics (GNFM-INdAM), and by the EPSRC grant EP/P002625/1. The authors acknowledge William & Mary Research Computing for providing computational resources and technical support that have contributed to the results reported within this paper.
Publisher Copyright:
© 2021 ACM.
PY - 2021/11/3
Y1 - 2021/11/3
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85127733118&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85127733118&partnerID=8YFLogxK
U2 - 10.1145/3490354.3494409
DO - 10.1145/3490354.3494409
M3 - Conference contribution
AN - SCOPUS:85127733118
T3 - ICAIF 2021 - 2nd ACM International Conference on AI in Finance
BT - ICAIF 2021 - 2nd ACM International Conference on AI in Finance
PB - Association for Computing Machinery, Inc
Y2 - 3 November 2021 through 5 November 2021
ER -