Astock: A New Dataset and Automated Stock Trading based on Stock-specific News Analyzing Model

Jin-an, Zou; Cao, Haiyao; Liu, Lingqiao; Lin, Yu-Hao; Abbasnejad, Ehsan; Shi, Javen Qinfeng

doi:10.18653/v1/2022.finnlp-1.24

Cited by 1 publication

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(5) The definition of classification y 𝑛 in the Zou et al [34] is followed, where mainly divided into three categories: positive, netural, and negative:…”

Section: Sdpg Processing Results Based On Srlmentioning

confidence: 99%

“…Astock 1 is a dataset proposed by [34], which contains stock and news data from 2018-07-01 to 2021-11-30. Specifically, this famous dataset spanning 1248 days contains many items, such as price, news, and so on.…”

Section: Experiments 41 Datasetsmentioning

confidence: 99%

“…It's the only dataset which contains both factors and news. We follow the splitting strategy of [34]. 2018-07-01 to 2020-7-01 of the dataset is used for training, 2020-7-01 to 2020-10-01 for validation, and the rest for testing (2020-10-01 to 2020-12-31).…”

Section: Experiments 41 Datasetsmentioning

confidence: 99%

“…Firstly, we utilized accuracy, F1 score, recall, and precision as evaluation metrics for our news factorization module, same as [34]. Secondly, we employed the GRS (Goodness-of-Fit R-squared) [5] metric, its p-value and the mean absolute value of alpha to measure the model's explanatory power on return predictions for explainable news effects.…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…2) methods are integrated both news and factors information, including RoBERTa WWM Ext [6], Chinese Lert large [7], Chinese Pert large [8], and Self-supervised SRLP [34].…”

Section: News Factorization Evaluationmentioning

confidence: 99%

See 4 more Smart Citations

FinReport: Explainable Stock Earnings Forecasting via News Factor Analyzing Model

Li,

Shen,

Zeng

et al. 2024

Companion Proceedings of the ACM Web Conference 2024

View full text Add to dashboard Cite

The task of stock earnings forecasting has received considerable attention due to the demand investors in real-world scenarios. However, compared with financial institutions, it is not easy for ordinary investors to mine factors and analyze news. On the other hand, although large language models in the financial field can serve users in the form of dialogue robots, it still requires users to have financial knowledge to ask reasonable questions. To serve the user experience, we aim to build an automatic system, FinReport, for ordinary investors to collect information, analyze it, and generate reports after summarizing.Specifically, our FinReport is based on financial news announcements and a multi-factor model to ensure the professionalism of the report. The FinReport consists of three modules: news factorization module, return forecasting module, risk assessment module. The news factorization module involves understanding news information and combining it with stock factors, the return forecasting module aim to analysis the impact of news on market sentiment, and the risk assessment module is adopted to control investment risk. Extensive experiments on real-world datasets have well verified the effectiveness and explainability of our proposed FinReport. Our codes and datasets are available at https://github.com/frinkleko/FinReport.

show abstract

“…(5) The definition of classification y 𝑛 in the Zou et al [34] is followed, where mainly divided into three categories: positive, netural, and negative:…”

Section: Sdpg Processing Results Based On Srlmentioning

confidence: 99%

Section: Experiments 41 Datasetsmentioning

confidence: 99%

Section: Experiments 41 Datasetsmentioning

confidence: 99%

Section: Evaluation Metricsmentioning

confidence: 99%

“…2) methods are integrated both news and factors information, including RoBERTa WWM Ext [6], Chinese Lert large [7], Chinese Pert large [8], and Self-supervised SRLP [34].…”

Section: News Factorization Evaluationmentioning

confidence: 99%

See 3 more Smart Citations