Incorporating Fine-grained Events in Stock Movement Prediction

Chen, Deli; Zou, Yanyan; Harimoto, Keiko; Bao, Ruihan; Ren, Xuancheng; Sun, Xu

doi:10.48550/arxiv.1910.05078

Cited by 5 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stock prices often depend on various news that affect the economy. [4], [5] show that adding news information or tweet features leads to better prediction performance compared with using only LSTM. This model uses VADER [24] to extract sentiment scores based on the news.…”

Section: Related Workmentioning

confidence: 99%

“…The hidden state hl with layer normalization [36] applied is transformed into matrices query, key, and value by multiplying each weight. In (5), the similarities between each query and key are computed by using a dot product. To prevent the gradient from becoming almost zero in the Softmax function, √ d k , where d k denotes the dimension of key, is divided for scaling.…”

Section: Transformersmentioning

confidence: 99%

See 1 more Smart Citation

Offline Reinforcement Learning for Automated Stock Trading

Lee,

Moon

2023

IEEE Access

View full text Add to dashboard Cite

Recently, with the increasing interest in investments in financial stock markets, several methods have been proposed to automatically trade stocks and/or predict future stock prices using machine learning techniques, such as reinforcement learning (RL), LSTM, and transformers. Among them, RL has been applied to manage portfolio assets with a sequence of optimal actions. The most important factor in investing in stocks is the utilization of past stock price data. However, existing RL algorithms applied to stock markets do not consider past stock data when taking optimal actions, as RL is formulated based on the Markov property. In other words, it means that the existing RL algorithm infers action based on the current state only.To resolve this limitation, we propose Transformer Actor-Critic with Regularization (TACR) using decision transformer to train the model with the correlation of past MDP (Markov Decision Process) elements using an attention network. In addition, a critic network is added to improve the performance by updating the parameters based on the evaluation of an action. For an efficient learning method, we train our model using an offline RL algorithm through suboptimal trajectories. To prevent overestimating the value of actions and reduce learning time, we train TACR through a regularization technique with an added behavior cloning. The experimental results using various stock market datasets show that TACR performs better than other state-of-the-art methods in terms of the Sharpe ratio and profit.INDEX TERMS portfolio allocation, reinforcement learning, sequence modeling, sharpe ratio, transformer, stock market.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Transformersmentioning

confidence: 99%

Offline Reinforcement Learning for Automated Stock Trading

Lee,

Moon

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…On the other hand, the study [4] criticized that the coarse-grained event structure such as (S, P, O) [7,78] may omit specific semantic information of different types of events, thus proposing the Japanese financial event dictionary (TFED) to extract the fine-grained events automatically from financial news. Generally, the TFED specified the type of financial events and their corresponding trigger words and event structures.…”

Section: Event Extraction-based Stock Forecasting Approachmentioning

confidence: 99%

“…In the existing literature, extensive studies [3][4][5][6][7] continuously realized excess return in the stock market. Those findings contradicted EMH and raised the fundamental question: "Where does the abnormal return come from?"…”

Section: Introductionmentioning

confidence: 99%

A Review of Sentiment, Semantic and Event-Extraction-Based Approaches in Stock Forecasting

et al. 2022

View full text Add to dashboard Cite

Stock forecasting is a significant and challenging task. The recent development of web technologies has transformed the communication channel to allow the public to share information over the web such as news, social media contents, etc., thus causing exponential growth of web data. The massively available information might be the key to revealing the financial market’s unexplained variability and facilitating forecasting accuracy. However, this information is usually in unstructured natural language and consists of different inherent meanings. Although a human can easily interpret the inherent messages, it is still complicated to manually process such a massive amount of textual data due to the constraint of time, ability, energy, etc. Due to the different properties of text sources, it is crucial to understand various text processing approaches to optimize forecasting performance. This study attempted to summarize and discuss the current text-based financial forecasting approaches in the aspect of semantic-based, sentiment-based, event-extraction-based, and hybrid approaches. Afterward, the study discussed the strength and weakness of each approach, followed with their comparison and suitable application scenarios. Moreover, this study also highlighted the future research direction in text-based stock forecasting, where the overall discussion is expected to provide insightful analysis for future reference.

show abstract

“…Alternative methods predict stock returns based on diversified alternative data, such as news texts (Hu et al 2018), social media information (Xu and Cohen 2018) and knowledge graphs (Cheng et al 2020). (Chen et al 2019) incorporates the fine-grained new events into stock movement prediction, and (Chen, Wei, and Huang 2018) constructs a financial knowledge graph based on raw news texts for stock price prediction. Unlike alternative methods, technical methods only focus on the market data (mainly stock price and volume and derived features).…”

Section: Stock Prediction With Machine Learningmentioning

confidence: 99%

FactorVAE: A Probabilistic Dynamic Factor Model Based on Variational Autoencoder for Predicting Cross-Sectional Stock Returns

Duan

Wang

Zhang

et al. 2022

AAAI

View full text Add to dashboard Cite

As an asset pricing model in economics and finance, factor model has been widely used in quantitative investment. Towards building more effective factor models, recent years have witnessed the paradigm shift from linear models to more flexible nonlinear data-driven machine learning models. However, due to low signal-to-noise ratio of the financial data, it is quite challenging to learn effective factor models. In this paper, we propose a novel factor model, FactorVAE, as a probabilistic model with inherent randomness for noise modeling. Essentially, our model integrates the dynamic factor model (DFM) with the variational autoencoder (VAE) in machine learning, and we propose a prior-posterior learning method based on VAE, which can effectively guide the learning of model by approximating an optimal posterior factor model with future information. Particularly, considering that risk modeling is important for the noisy stock data, FactorVAE can estimate the variances from the distribution over the latent space of VAE, in addition to predicting returns. The experiments on the real stock market data demonstrate the effectiveness of FactorVAE, which outperforms various baseline methods.

show abstract

Incorporating Fine-grained Events in Stock Movement Prediction

Cited by 5 publications

References 24 publications

Offline Reinforcement Learning for Automated Stock Trading

Offline Reinforcement Learning for Automated Stock Trading

A Review of Sentiment, Semantic and Event-Extraction-Based Approaches in Stock Forecasting

FactorVAE: A Probabilistic Dynamic Factor Model Based on Variational Autoencoder for Predicting Cross-Sectional Stock Returns

Contact Info

Product

Resources

About