Stock Movement Prediction from Tweets and Historical Prices

Xu, Yumo; Cohen, Shay B.

doi:10.18653/v1/p18-1183

Cited by 245 publications

(240 citation statements)

References 20 publications

Supporting

Mentioning

220

Contrasting

Order By: Relevance

“…Different from works of (Xu and Cohen, 2018;Zhang et al, 2018b) who use limited daily-level stock trade data (stock close price and daily trade volume, for example), we adopt the minute-level stock data to describe the stock movement in a more detailed way. For each minute when at least one trade happens, we collect the following items: (1) First/last/highest/lowest trade price of the minute; (2) Total trade volume/value of the minute; (3) Volume-weighted average trade price.…”

Section: Trade Data Embeddingmentioning

confidence: 99%

“…We do not study the multi-news for days on end, which are studied in (Xu and Cohen, 2018;Hu et al, 2018) because we find the situation that news about same stock happens in several continuous days is very sparse in real data. Mcc Figure 4: The percentage (all dataset) and performance (SSPM on test set) of different times' news.…”

Section: Experiments Detailsmentioning

confidence: 99%

“…In these text-based stock prediction works, various methods are proposed to extract semantic information from stock related text to help the prediction of stock movement. There are mainly two methods of applying text: employing raw text (Hu et al, 2018;Xu and Cohen, 2018) or coarse-grained <S,P,O> structure (subject, predicate and object) extracted from * This work is done when Deli Chen is a intern at Mizuho Securities.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Incorporating Fine-grained Events in Stock Movement Prediction

Chen¹,

Zou²,

Harimoto³

et al. 2019

Proceedings of the Second Workshop on Economics and Natural Language Processing

View full text Add to dashboard Cite

Considering event structure information has proven helpful in text-based stock movement prediction. However, existing works mainly adopt the coarse-grained events, which loses the specific semantic information of diverse event types. In this work, we propose to incorporate the fine-grained events in stock movement prediction. Firstly, we propose a professional finance event dictionary built by domain experts and use it to extract fine-grained events automatically from finance news. Then we design a neural model to combine finance news with fine-grained event structure and stock trade data to predict the stock movement. Besides, in order to improve the generalizability of the proposed method, we design an advanced model that uses the extracted finegrained events as the distant supervised label to train a multi-task framework of event extraction and stock prediction. The experimental results show that our method outperforms all the baselines and has good generalizability.

show abstract

Section: Trade Data Embeddingmentioning

confidence: 99%

Section: Experiments Detailsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Incorporating Fine-grained Events in Stock Movement Prediction

Chen¹,

Zou²,

Harimoto³

et al. 2019

Proceedings of the Second Workshop on Economics and Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…It is worth mentioning that LSTM-HA is also an open framework. The representations learned from other types of information sources, such as news, events and social media [4,12,27], could also be concatenated or attended with r (i) t .…”

Section: Stock Representations Extractionmentioning

confidence: 99%

AlphaStock

Wang

Zhang

Tang

et al. 2019

Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Recent years have witnessed the successful marriage of finance innovations and AI techniques in various finance applications including quantitative trading (QT). Despite great research efforts devoted to leveraging deep learning (DL) methods for building better QT strategies, existing studies still face serious challenges especially from the side of finance, such as the balance of risk and return, the resistance to extreme loss, and the interpretability of strategies, which limit the application of DL-based strategies in reallife financial markets. In this work, we propose AlphaStock, a novel reinforcement learning (RL) based investment strategy enhanced by interpretable deep attention networks, to address the above challenges. Our main contributions are summarized as follows: i) We integrate deep attention networks with a Sharpe ratio-oriented reinforcement learning framework to achieve a risk-return balanced investment strategy; ii) We suggest modeling interrelationships among assets to avoid selection bias and develop a cross-asset attention mechanism; iii) To our best knowledge, this work is among the first to offer an interpretable investment strategy using deep reinforcement learning models. The experiments on long-periodic U.S. and Chinese markets demonstrate the effectiveness and robustness of AlphaStock over diverse market states. It turns out that AlphaStock tends to select the stocks as winners with high long-term growth, low volatility, high intrinsic value, and being undervalued recently.

show abstract

“…[24]- [26] extracted sentiment and event features from Twitter and news for stock market prediction. Some recent work attempted to exploit heterogeneous historical price and social media data via feature concatenation [27] or joint feature learning [28] for stock prediction. When such feature fusion methods are applied to the problem of forecasting volatility with the assistance of order book data in this paper, they overlook the time-varying environment of the market [6]- [8] as well as weakening the interpretability of order book features [29].…”

Section: Related Workmentioning

confidence: 99%

Bitcoin Volatility Forecasting with a Glimpse into Buy and Sell Orders

Guo

Bifet

Antulov-Fantulin

2018

2018 IEEE International Conference on Data Mining (ICDM)

View full text Add to dashboard Cite

Bitcoin is one of the most prominent decentralized digital cryptocurrencies, currently having the largest market capitalization among cryptocurrencies. Ability to understand which factors drive the fluctuations of the Bitcoin price and to what extent they are predictable is interesting both from theoretical and practical perspective. In this paper, we study the problem of the Bitcoin short-term volatility forecasting by exploiting volatility history and order book data. Order book, consisting of buy and sell orders over time, reflects the intention of the market and is closely related to the evolution of volatility. We propose temporal mixture models capable of adaptively exploiting both volatility history and order book features for short-term volatility forecasting. By leveraging rolling and incremental learning and evaluation procedures, we demonstrate the prediction performance of our model as well as studying the robustness, in comparison to a variety of statistical and machine learning baselines. Meanwhile, our temporal mixture model enables to decipher time-varying effect of order book features on the volatility. It demonstrates the prospect of our temporal mixture model as an interpretable forecasting framework over heterogeneous Bitcoin data.

show abstract

Stock Movement Prediction from Tweets and Historical Prices

Cited by 245 publications

References 20 publications

Incorporating Fine-grained Events in Stock Movement Prediction

Incorporating Fine-grained Events in Stock Movement Prediction

AlphaStock

Bitcoin Volatility Forecasting with a Glimpse into Buy and Sell Orders

Contact Info

Product

Resources

About