Build a pipeline for company intelligence analysis
Research Themes
Currently, securities reports, which are disclosure documents under the Financial Instruments and Exchange Act, are published as digital data in the form of XBRL instances on EDINET via the Internet. Compared to the past, they are now easier to obtain and can be analyzed using a computer. The purpose of this research is to analyze various information contained in securities reports using a programming language called Python. By using Python, it is possible to build a pipeline that accesses the EDINET API, obtains large volumes of securities reports, parses XBRL instances, aggregates and analyzes large volumes of data, and visualizes the analysis results. By taking this research course, you will be able to learn not only how to analyze corporate information but also the basics of programming.
Activities
Study 1: Introduction to Python
Study 2a: Introduction to pandas
Study 2b: Accessing EDINET API and parsing XBRL instances
Graduation Research A: Analysis of Past Data
Graduation Research B: Analysis of the latest data