Projects

2024

1. 

   Korea discount and corporate governance

   SK Kim, Ye Jun Kim, and Gio (Jiwoong) Choi

   MSCI Inc., 2024

   Abs

   This paper examines the "Board and Ownership and Control" Key Issue within the MSCI ESG Ratings Corporate Governance Theme, with a focus on board independence and adherence to the one-share-one-vote (OSOV) principle. Our analysis reveals significant governance challenges among Korean companies. Notably, less than half of the directors on Korean company boards are independent, a figure significantly lower than the global average of 66%. Additionally, 82% of Korean companies were flagged for Related Party Transactions (RPT), with smaller firms exhibiting lower board independence. Furthermore, Korean companies that deviated from the OSOV principle demonstrated weaker financial performance, with both return-on-equity (ROE) and price-to-book ratio (PBR) falling below the market average. These findings underscore the need for enhanced governance practices within Korean corporations to align more closely with global standards.

2. 

   ASEAN Gender Outlook 2024: Achieving the SDGs for all and leaving no women or girl behind

   United Nations, Women Count Flagship Programme on Gender Statistics, 2024

   Abs PDF

   - Conducted SDG Gender Outlook research as part of the Women Count Flagship Programme on Gender Statistics, in charge of SDG 4th, 9th, 16th goal.
   - Analyzed the household survey data, such as DHS and MICS data, and visualized the result in R and Python.
   - Utilized GIS data to find the association between illiteracy and the time required to reach dense areas in Cambodia, Philippines, and Myanmar.

2023

1. 

   Stock Market Regime Analysis

   Bachelor’s Thesis, 2023

   Abs Code

   - Analyzed stock market regimes of the United States using 10 macroeconomic indicators, specifically focusing on the Financial Stress Index(FSI).
   - Developed a classification model to identify bear and bull markets based on FSI changes.
   - Achieved 85.96% prediction accuracy in the test set data, utilizing a RandomForest and Deep Neural Network(DNN) and implementing techniques to prevent overfitting.

2022

1. 

   Outdoor visual SLAM and Path Planning for Mobile-Robot

   Seongil Heo, Jueun Mun, Jiwoong Choi, Jiwon Park, and Eric T. Matson

   In 2022 Sixth IEEE International Conference on Robotic Computing (IRC), Dec 2022

   Abs HTML Code

   This paper proposes a robust visual SLAM and a path planning algorithm for autonomous vehicles in the outdoor environment. The consideration of the outdoor characteristics was essential in both SLAM and path planning processes. This study can be used when it is necessary to know the exact appearance of the environment due to the impossibility of observing the environment through a satellite map, e.g., inside a forest. The visual SLAM system was developed using GPS data in consideration of the deterioration of camera recognition performance outdoors. The GPS data was inserted into every multi-thread of visual SLAM, which are Camera Tracking, Local Mapping, and Loop Closing. It enhanced the accuracy of the map and saved computational power by preventing useless calculations. In the path planning part, our method divided the path based on the stability of the roads. When determining the optimal path, the stability of the road and the driving time were considered, and the weight was assigned based on the GPS data.

2021

1. 

   Stock Investment Opinion Sentimental Analysis

   Mirae Asset Big Data Hackathon, Nov 2021

   Abs PDF Code

   - Collected text data from YouTube videos, YouTube comments, News, and Bank Reports by STT, OCR, and Crawling methods.
   - Fine-tuned Google’s ELECTRA model which is a GAN-based transformer model by PyTorch.
   - Conducted a Sentimental Analysis and made a prototype service.
   - Gave a presentation on behalf of our team and finally achieved 4th place out of 1,000.

2. 

   Korean Financial News Sentimental Analysis

   Capstone Project, Dec 2021

   Abs Code

   - Aimed to develop a Korean NLP model and Translated the English dataset into Korean by API.
   - Utilized LSTM and GRU networks by PyTorch first.
   - Conducted Transfer Learning of BERT multilingual base model for Korean and KoBERT.

3. 

   Panel Regression Analysis about the influence ESG Management has on Enterprise Value

   Capstone Project, Jun 2021

   Abs

   - Conducted Linear Regression Analysis to discern a postive relation between corporate value and ESG movement.
   - Collected Financial Statement data of 898 companies from 2016 to 2020 by crawling in Python3.
   - Utilized three Panel Data Regression methods: Pooled OLS, Fixed Effects, Random Effects in STATA.
   - Compared model through F-test, Hausman test, and LM test.

4. 

   Job Recommendation System based on Natural Language Processing(NLP)

   Seoul Business Agency Hackathon, Feb 2021

   Abs Code

   - Developed a Job Recommendation System based on Natural Language Processing(NLP) and Contents-Based Filtering(CBF) method, using ‘Scikit-learn’ and ‘KoNLPy’ libraries.
   - Collected language data through crawling by the ‘Selenium’ library and preprocessed them in Python.