I found paper \"Enhancing Stock Movement Prediction with Adversarial Training\".
\n\nAbstract
\nThis paper contributes a new machine learning solution for stock movement prediction, which aims to predict whether the price of a stock will be up or down in the near future. The key novelty is that we propose to employ adversarial training to improve the generalization of a neural network prediction model. The rationality of adversarial training here is that the input features to stock prediction are typically based on stock price, which is essentially a stochastic variable and continuously changed with time by nature. As such, normal training with static price-based features (e.g., the close price) can easily overfit the data, being insufficient to obtain reliable models. To address this problem, we propose to add perturbations to simulate the stochasticity of price variable, and train the model to work well under small yet intentional perturbations. Extensive experiments on two real-world stock data show that our method outperforms the state-of-the-art solution [Xu and Cohen, 2018] with 3.11% relative improvements on average w.r.t. accuracy, validating the usefulness of adversarial training for stock prediction task.
\nConclusion
\nWe showed that neural network solutions for stock movement prediction could suffer from weak generalization ability since they lack the ability to deal with the stochasticity of stock features. To solve this problem, we proposed an Adversarial Attentive LSTM solution, which leverages adversarial training to simulate the stochasticity during model training. We conducted extensive experiments on two benchmark datasets and validated the effectiveness of the proposed solution, signifying the importance of accounting for the stochasticity of stock prices in stock movement prediction. Morever, the results showed that adversarial training enhances the robustness and generalization of the prediction model. In future, we plan to explore the following directions: 1) we are interested in testing Adv-ALSTM in movement prediction of more assets such as commodities. 2) We plan to apply adversarial training to stock movement solutions with different structures such as the CNNs [Lin et al., 2017]. 3) We will explore the effect of adversarial training over fundamental analysis methods of stock movement prediction.
", "messages": [ { "id": "1624005", "postDate": "12/20/2021 13:03:34", "content": "I found paper \"Enhancing Stock Movement Prediction with Adversarial Training\".
\n\nAbstract
\nThis paper contributes a new machine learning solution for stock movement prediction, which aims to predict whether the price of a stock will be up or down in the near future. The key novelty is that we propose to employ adversarial training to improve the generalization of a neural network prediction model. The rationality of adversarial training here is that the input features to stock prediction are typically based on stock price, which is essentially a stochastic variable and continuously changed with time by nature. As such, normal training with static price-based features (e.g., the close price) can easily overfit the data, being insufficient to obtain reliable models. To address this problem, we propose to add perturbations to simulate the stochasticity of price variable, and train the model to work well under small yet intentional perturbations. Extensive experiments on two real-world stock data show that our method outperforms the state-of-the-art solution [Xu and Cohen, 2018] with 3.11% relative improvements on average w.r.t. accuracy, validating the usefulness of adversarial training for stock prediction task.
\nConclusion
\nWe showed that neural network solutions for stock movement prediction could suffer from weak generalization ability since they lack the ability to deal with the stochasticity of stock features. To solve this problem, we proposed an Adversarial Attentive LSTM solution, which leverages adversarial training to simulate the stochasticity during model training. We conducted extensive experiments on two benchmark datasets and validated the effectiveness of the proposed solution, signifying the importance of accounting for the stochasticity of stock prices in stock movement prediction. Morever, the results showed that adversarial training enhances the robustness and generalization of the prediction model. In future, we plan to explore the following directions: 1) we are interested in testing Adv-ALSTM in movement prediction of more assets such as commodities. 2) We plan to apply adversarial training to stock movement solutions with different structures such as the CNNs [Lin et al., 2017]. 3) We will explore the effect of adversarial training over fundamental analysis methods of stock movement prediction.
", "rawMarkdown": "I found paper \"[Enhancing Stock Movement Prediction with Adversarial Training](https://www.ijcai.org/proceedings/2019/0810.pdf)\".\n\n[Github](https://github.com/fulifeng/Adv-ALSTM)\n\n**Abstract**\n\n*This paper contributes a new machine learning solution for stock movement prediction, which aims to predict whether the price of a stock will be up or down in the near future. The key novelty is that we propose to employ adversarial training to improve the generalization of a neural network prediction model. The rationality of adversarial training here is that the input features to stock prediction are typically based on stock price, which is essentially a stochastic variable and continuously changed with time by nature. As such, normal training with static price-based features (e.g., the close price) can easily overfit the data, being insufficient to obtain reliable models. To address this problem, we propose to add perturbations to simulate the stochasticity of price variable, and train the model to work well under small yet intentional perturbations. Extensive experiments on two real-world stock data show that our method outperforms the state-of-the-art solution [Xu and Cohen, 2018] with 3.11% relative improvements on average w.r.t. accuracy, validating the usefulness of adversarial training for stock prediction task.*\n\n\n\n**Conclusion**\n\n*We showed that neural network solutions for stock movement prediction could suffer from weak generalization ability since they lack the ability to deal with the stochasticity of stock features. To solve this problem, we proposed an Adversarial Attentive LSTM solution, which leverages adversarial training to simulate the stochasticity during model training. We conducted extensive experiments on two benchmark datasets and validated the effectiveness of the proposed solution, signifying the importance of accounting for the stochasticity of stock prices in stock movement prediction. Morever, the results showed that adversarial training enhances the robustness and generalization of the prediction model. In future, we plan to explore the following directions: 1) we are interested in testing Adv-ALSTM in movement prediction of more assets such as commodities. 2) We plan to apply adversarial training to stock movement solutions with different structures such as the CNNs [Lin et al., 2017]. 3) We will explore the effect of adversarial training over fundamental analysis methods of stock movement prediction.*", "votes": null }, { "id": "1631834", "postDate": "12/28/2021 20:29:07", "content": "Very interesting, but not useful I think in this competition because I think inference of such model will be big. And it's smth similar to 1st solution on Optiver competition
", "rawMarkdown": "Very interesting, but not useful I think in this competition because I think inference of such model will be big. And it's smth similar to 1st solution on Optiver competition", "votes": null }, { "id": "1631997", "postDate": "12/29/2021 03:41:27", "content": "Interesting! I think I should try to adapt. Thanks a lot.
", "rawMarkdown": "Interesting! I think I should try to adapt. Thanks a lot.", "votes": null } ], "comments": [ { "id": 1631834, "author_name": "vladimircape", "author_url": "", "post_date": "12/28/2021 20:29:07", "content": "Very interesting, but not useful I think in this competition because I think inference of such model will be big. And it's smth similar to 1st solution on Optiver competition
", "votes": null, "replies": [] }, { "id": 1631997, "author_name": "theethadprhompradith", "author_url": "", "post_date": "12/29/2021 03:41:27", "content": "Interesting! I think I should try to adapt. Thanks a lot.
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "1624005": "I found paper \"[Enhancing Stock Movement Prediction with Adversarial Training](https://www.ijcai.org/proceedings/2019/0810.pdf)\".\n\n[Github](https://github.com/fulifeng/Adv-ALSTM)\n\n**Abstract**\n\n*This paper contributes a new machine learning solution for stock movement prediction, which aims to predict whether the price of a stock will be up or down in the near future. The key novelty is that we propose to employ adversarial training to improve the generalization of a neural network prediction model. The rationality of adversarial training here is that the input features to stock prediction are typically based on stock price, which is essentially a stochastic variable and continuously changed with time by nature. As such, normal training with static price-based features (e.g., the close price) can easily overfit the data, being insufficient to obtain reliable models. To address this problem, we propose to add perturbations to simulate the stochasticity of price variable, and train the model to work well under small yet intentional perturbations. Extensive experiments on two real-world stock data show that our method outperforms the state-of-the-art solution [Xu and Cohen, 2018] with 3.11% relative improvements on average w.r.t. accuracy, validating the usefulness of adversarial training for stock prediction task.*\n\n\n\n**Conclusion**\n\n*We showed that neural network solutions for stock movement prediction could suffer from weak generalization ability since they lack the ability to deal with the stochasticity of stock features. To solve this problem, we proposed an Adversarial Attentive LSTM solution, which leverages adversarial training to simulate the stochasticity during model training. We conducted extensive experiments on two benchmark datasets and validated the effectiveness of the proposed solution, signifying the importance of accounting for the stochasticity of stock prices in stock movement prediction. Morever, the results showed that adversarial training enhances the robustness and generalization of the prediction model. In future, we plan to explore the following directions: 1) we are interested in testing Adv-ALSTM in movement prediction of more assets such as commodities. 2) We plan to apply adversarial training to stock movement solutions with different structures such as the CNNs [Lin et al., 2017]. 3) We will explore the effect of adversarial training over fundamental analysis methods of stock movement prediction.*", "1631834": "Very interesting, but not useful I think in this competition because I think inference of such model will be big. And it's smth similar to 1st solution on Optiver competition", "1631997": "Interesting! I think I should try to adapt. Thanks a lot." }, "source": "meta" }