From Word to Financial Time Series Embedding

8 Pages Posted: 10 Jun 2018

See all articles by Maxime De Bruyn

Maxime De Bruyn

Degroof Petercam Asset Management

Date Written: May 23, 2018

Abstract

Pre-trained word vectors contributed to state of the art results in many Natural Language Processing tasks. In this work, we show that the same algorithms can be applied to the embedding of financial time series. Pre-trained vectors for financial time series are useful for visualizing an investable universe, embedding a portfolio of financial instruments, and can be used as context vectors in larger NLP networks.

Keywords: Time Series, Embedding, Word2Vec, Glove, Finance, Stock2Vec

Suggested Citation

De Bruyn, Maxime, From Word to Financial Time Series Embedding (May 23, 2018). Available at SSRN: https://ssrn.com/abstract=3184513 or http://dx.doi.org/10.2139/ssrn.3184513

Maxime De Bruyn (Contact Author)

Degroof Petercam Asset Management ( email )

Rue Guimard 18
Brussels, 1040
Belgium

Register to save articles to
your library

Register

Paper statistics

Downloads
340
Abstract Views
1,032
rank
90,736
PlumX Metrics