News-Driven Stock Prediction Using Noisy Equity State Representation

Xiao Liu, Heyan Huang, Yue Zhang

Keywords: news-driven stock prediction, equity state representation, recurrent state transition

Abstract:

News-driven stock prediction investigates the correlation between news events and stock price movements.
Previous work has considered effective ways for representing news events and their sequences, but rarely exploited the representation of underlying equity states.
We address this issue by making use of a recurrent neural network to represent an equity state transition sequence, integrating news representation using contextualized embeddings as inputs to the state transition mechanism.
Thanks to the separation of news and equity representations, our model can accommodate additional input factors.
We design a novel random noise factor for modeling influencing factors beyond news events, and a future event factor to address the delay of news information (e.g., insider trading).
Results show that the proposed model outperforms strong baselines in the literature.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: We investigate explicit modeling of equity state representations in news-driven stock prediction by using an LSTM state to model the fundamentals, adding news impact and noise impact by using attention and noise sampling, respectively.

Reviewed Version (pdf): https://openreview.net/references/pdf?id=ACB1_v9e24