A long-short dual-mode knowledge distillation framework for empirical asset pricing models in digital financial networks
The continuous combination of digital network technology and traditional financial services has given birth to digital financial networks, which explore massive economic data under the AI-driven models to achieve intelligent connections among financial institutions, markets, transactions, and instru...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | Connection Science |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/09540091.2024.2306970 |
| _version_ | 1797346275795927040 |
|---|---|
| author | Yuanyuan Yi Kai Cui Minghua Xu Lingzhi Yi Kun Yi Xinlei Zhou Shenghao Liu Gefei Zhou |
| author_facet | Yuanyuan Yi Kai Cui Minghua Xu Lingzhi Yi Kun Yi Xinlei Zhou Shenghao Liu Gefei Zhou |
| author_sort | Yuanyuan Yi |
| collection | DOAJ |
| description | The continuous combination of digital network technology and traditional financial services has given birth to digital financial networks, which explore massive economic data under the AI-driven models to achieve intelligent connections among financial institutions, markets, transactions, and instruments. Empirical asset pricing is a challenging task in financial analysis, which has attracted research attention. However, existing studies only focus on tackling the challenges of equity risk premium in the single stock market. Considering multiple economic linkages between the two countries, the transaction history of the US stock market as empirical knowledge is a powerful supplement to improve the prediction of equity risk premium in the China market. In this paper, we aim to fully leverage the prior information in two stock markets for empirical asset pricing models. Due to the rich financial domain knowledge, there may be various characteristic signals that partially overlap in different periods. To address these issues, we propose a framework based on long-short dual-mode knowledge distillation, termed as LSDM-KD, which incorporates US and China stock market models, and a shared characteristic signals model. The method effectively understands the relationships between assets and market behaviour, reducing reliance on expensive correlation databases and professional knowledge. Extensive experiments conducted on US and China stock market datasets demonstrate that our LSDM-KD can significantly improve the performance of empirical asset pricing. |
| first_indexed | 2024-03-08T11:30:43Z |
| format | Article |
| id | doaj.art-15477366cfe54432bd18d704d2fb99cc |
| institution | Directory Open Access Journal |
| issn | 0954-0091 1360-0494 |
| language | English |
| last_indexed | 2024-03-08T11:30:43Z |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Connection Science |
| spelling | doaj.art-15477366cfe54432bd18d704d2fb99cc2024-01-25T19:16:26ZengTaylor & Francis GroupConnection Science0954-00911360-04942024-12-0136110.1080/09540091.2024.2306970A long-short dual-mode knowledge distillation framework for empirical asset pricing models in digital financial networksYuanyuan Yi0Kai Cui1Minghua Xu2Lingzhi Yi3Kun Yi4Xinlei Zhou5Shenghao Liu6Gefei Zhou7School of Journalism and Information Communication, Huazhong University of Science and Technology, Wuhan, People's Republic of ChinaSchool of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, People's Republic of ChinaSchool of Journalism and Information Communication, Huazhong University of Science and Technology, Wuhan, People's Republic of ChinaSchool of Information and Safety Engineering, Zhongnan University of Economics and Law, Wuhan, People's Republic of ChinaImperial College Business School, Imperial College London, London, UKWuhan Research Institute of Post and Telecommunication, Wuhan People's Republic of ChinaSchool of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, People's Republic of ChinaSchool of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, People's Republic of ChinaThe continuous combination of digital network technology and traditional financial services has given birth to digital financial networks, which explore massive economic data under the AI-driven models to achieve intelligent connections among financial institutions, markets, transactions, and instruments. Empirical asset pricing is a challenging task in financial analysis, which has attracted research attention. However, existing studies only focus on tackling the challenges of equity risk premium in the single stock market. Considering multiple economic linkages between the two countries, the transaction history of the US stock market as empirical knowledge is a powerful supplement to improve the prediction of equity risk premium in the China market. In this paper, we aim to fully leverage the prior information in two stock markets for empirical asset pricing models. Due to the rich financial domain knowledge, there may be various characteristic signals that partially overlap in different periods. To address these issues, we propose a framework based on long-short dual-mode knowledge distillation, termed as LSDM-KD, which incorporates US and China stock market models, and a shared characteristic signals model. The method effectively understands the relationships between assets and market behaviour, reducing reliance on expensive correlation databases and professional knowledge. Extensive experiments conducted on US and China stock market datasets demonstrate that our LSDM-KD can significantly improve the performance of empirical asset pricing.https://www.tandfonline.com/doi/10.1080/09540091.2024.2306970Financial networksempirical asset pricingknowledge distillationrepresentation learning |
| spellingShingle | Yuanyuan Yi Kai Cui Minghua Xu Lingzhi Yi Kun Yi Xinlei Zhou Shenghao Liu Gefei Zhou A long-short dual-mode knowledge distillation framework for empirical asset pricing models in digital financial networks Connection Science Financial networks empirical asset pricing knowledge distillation representation learning |
| title | A long-short dual-mode knowledge distillation framework for empirical asset pricing models in digital financial networks |
| title_full | A long-short dual-mode knowledge distillation framework for empirical asset pricing models in digital financial networks |
| title_fullStr | A long-short dual-mode knowledge distillation framework for empirical asset pricing models in digital financial networks |
| title_full_unstemmed | A long-short dual-mode knowledge distillation framework for empirical asset pricing models in digital financial networks |
| title_short | A long-short dual-mode knowledge distillation framework for empirical asset pricing models in digital financial networks |
| title_sort | long short dual mode knowledge distillation framework for empirical asset pricing models in digital financial networks |
| topic | Financial networks empirical asset pricing knowledge distillation representation learning |
| url | https://www.tandfonline.com/doi/10.1080/09540091.2024.2306970 |
| work_keys_str_mv | AT yuanyuanyi alongshortdualmodeknowledgedistillationframeworkforempiricalassetpricingmodelsindigitalfinancialnetworks AT kaicui alongshortdualmodeknowledgedistillationframeworkforempiricalassetpricingmodelsindigitalfinancialnetworks AT minghuaxu alongshortdualmodeknowledgedistillationframeworkforempiricalassetpricingmodelsindigitalfinancialnetworks AT lingzhiyi alongshortdualmodeknowledgedistillationframeworkforempiricalassetpricingmodelsindigitalfinancialnetworks AT kunyi alongshortdualmodeknowledgedistillationframeworkforempiricalassetpricingmodelsindigitalfinancialnetworks AT xinleizhou alongshortdualmodeknowledgedistillationframeworkforempiricalassetpricingmodelsindigitalfinancialnetworks AT shenghaoliu alongshortdualmodeknowledgedistillationframeworkforempiricalassetpricingmodelsindigitalfinancialnetworks AT gefeizhou alongshortdualmodeknowledgedistillationframeworkforempiricalassetpricingmodelsindigitalfinancialnetworks AT yuanyuanyi longshortdualmodeknowledgedistillationframeworkforempiricalassetpricingmodelsindigitalfinancialnetworks AT kaicui longshortdualmodeknowledgedistillationframeworkforempiricalassetpricingmodelsindigitalfinancialnetworks AT minghuaxu longshortdualmodeknowledgedistillationframeworkforempiricalassetpricingmodelsindigitalfinancialnetworks AT lingzhiyi longshortdualmodeknowledgedistillationframeworkforempiricalassetpricingmodelsindigitalfinancialnetworks AT kunyi longshortdualmodeknowledgedistillationframeworkforempiricalassetpricingmodelsindigitalfinancialnetworks AT xinleizhou longshortdualmodeknowledgedistillationframeworkforempiricalassetpricingmodelsindigitalfinancialnetworks AT shenghaoliu longshortdualmodeknowledgedistillationframeworkforempiricalassetpricingmodelsindigitalfinancialnetworks AT gefeizhou longshortdualmodeknowledgedistillationframeworkforempiricalassetpricingmodelsindigitalfinancialnetworks |