Two research papers on financial artificial intelligence (AI) authored by an employee of Shinhan Investment Corp. were presented at 'ICLR 2025,' a global AI conference.


According to Shinhan Investment Corp. on the 30th, Hanul Lee, Senior Researcher at the AI Solutions Department, presented two papers at the 'Advanced in Financial AI' workshop held on April 28 in Singapore as part of ICLR 2025. ICLR is recognized as the world’s leading conference in the fields of AI and machine learning.


The first paper focused on the development of a Korean-language natural language processing model specialized for the financial sector. Existing models have primarily been based on English and Chinese data, resulting in limitations when it comes to accurately understanding and analyzing Korean financial documents. In response, the paper proposed new standards tailored to Korean financial language and, through experiments, achieved more sophisticated results compared to existing models.


The second paper dealt with technology for predicting changes in stock market trading volumes. In particular, it addressed methods for precisely forecasting the daily trading volume ratio and applying this to investment strategies. By leveraging advanced data processing techniques and AI models, the research enabled stable predictions of highly volatile trading volume changes. Experiments applying simple investment strategies in the Korean stock market also yielded positive results. This paper was written under the leadership of Senior Researcher Lee in collaboration with interns from the AI Solutions Department.



Shinhan Investment Corp. stated, "AI technology is playing an increasingly important role in the financial market," and added, "We will continue to provide customers with more sophisticated and differentiated investment information and analytical services through innovative financial AI research."


This content was produced with the assistance of AI translation services.

© The Asia Business Daily(www.asiae.co.kr). All rights reserved.

Today’s Briefing