A News-Driven Recurrent Neural Network for Market Volatility Prediction

Lin, Peikang; Mo, X. H.; Lin, Guidong; Ling, Liwen; Wei, Tingting; Luo, Wei

doi:10.1109/acpr.2017.35

Cited by 7 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A possible future research direction is to improve the prediction speed of the model further while maintaining the prediction accuracy. Furthermore, it demonstrates that the hot events in the news, such as economic stimulus policies, regional conflicts and local wars, natural disasters and epidemics, will have an impact on financial markets, and some researchers have already begun research in this area 20‐22 . Therefore, building an event‐driven fund correlation analysis system is also one of our future research directions.…”

Section: Discussionmentioning

confidence: 97%

“…Since Lightgbm uses the GOSS (Gradient‐based One‐Side Sampling) strategy to select samples with more considerable gradient descent, the training data volume is reduced, and the training speed is rapid. At the same time, Lightgbm uses the EFB (Exclusive Feature Bundling) strategy to bundle mutually exclusive features, reducing the number of features and preventing overfitting 20,21 . Therefore, Lightgbm is also an ideal reference model for fund analysis.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

DLIFT: A deep‐learning‐based intelligent fund transaction system for financial Internet of Things

Xiang

Yin

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

Summary Analyzing the correlation between two funds can help investors control investment risks and optimize investment portfolios, which has a strong guiding significance for fund investment in reality. Constructing an intelligent investment system with fund correlation analysis capabilities can help investors automatically make profits from financial markets. In previous research, many researchers have built intelligent investment systems using Bayesian networks, support vector machines (SVM), and LSTM models. However, the strong historical dependence between fund data and the high‐dimensional and high‐noise characteristics of fund data prevent traditional methods from obtaining excellent performance in fund analysis. This paper designs a deep learning‐based fund intelligent trading system‐DLIFT which has functions such as investment push, income prediction, and risk control. The systems data analysis module is implemented using the Improved RNN model. This model employed encoder‐decoder architecture. The encoder is responsible for analyzing the fund's feature, and the decoder is responsible for analyzing the dependency relationship between the historical correlation and the current correlation. LSTM and an attention mechanism are simultaneously applied to the encoder and decoder, which enabled the discovery of the implicit dependence of time series data. This article places the designed system on a historical dataset containing multiple public funds for verification. In specific experiments, the experimental results of the comparative experiments show the superiority of our model. At the same time, the results of the ablation experiment results show that LSTM and attention mechanism play critical role in the proposed system.

show abstract

Section: Discussionmentioning

confidence: 97%

Section: Methodsmentioning

confidence: 99%

DLIFT: A deep‐learning‐based intelligent fund transaction system for financial Internet of Things

Xiang

Yin

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…By comparing with [6] and [10], despite that modeling the correlations between trading days can bring better results, we also find that modeling the noise by using a state-related random factor may be effective because of the high market stochasticity.…”

Section: Predicting Sandp 500 Indexmentioning

confidence: 97%

“…We compare our approach with the following strong baselines on predicting the S&P 500 index, which also only use financial news: Accuracy MCC [11] 56.38% 0.0711 [4] 64.21% 0.4035 [5] 66.93% 0.5072 [6] 63.34% - [10] 64.55% -ANRES 67.34% 0.5475 Table 4: Test set results on predicting S&P 500 index.…”

Section: Predicting Sandp 500 Indexmentioning

confidence: 99%

News-Driven Stock Prediction With Attention-Based Noisy Recurrent State Transition

Liu,

Huang,

Zhang

et al. 2020

Preprint

View full text Add to dashboard Cite

We consider direct modeling of underlying stock value movement sequences over time in the news-driven stock movement prediction. A recurrent state transition model is constructed, which better captures a gradual process of stock movement continuously by modeling the correlation between past and future price movements. By separating the effects of news and noise, a noisy random factor is also explicitly fitted based on the recurrent states. Results show that the proposed model outperforms strong baselines. Thanks to the use of attention over news events, our model is also more explainable. To our knowledge, we are the first to explicitly model both events and noise over a fundamental stock value state for news-driven stock movement prediction.

show abstract

Key-Track: A Lightweight Scalable LSTM-based Pedestrian Tracker for Surveillance Systems

Kulkarni

Mohan

Rogers

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A News-Driven Recurrent Neural Network for Market Volatility Prediction

Cited by 7 publications

References 5 publications

DLIFT: A deep‐learning‐based intelligent fund transaction system for financial Internet of Things

DLIFT: A deep‐learning‐based intelligent fund transaction system for financial Internet of Things

News-Driven Stock Prediction With Attention-Based Noisy Recurrent State Transition

Key-Track: A Lightweight Scalable LSTM-based Pedestrian Tracker for Surveillance Systems

Contact Info

Product

Resources

About