Decision Making Problem: Efficient Portfolio Management
01/2020 - 03/2021
- Implemented reinforcement learning methods (e.g. policy gradient and temporal difference) to efficiently allocate the weights of investment to minimize risk and maximize profit.
- Integrated reinforcement learning with deep learning method called long-short term memory.
Time Series Prediction using Deep Learning Methods
01/2019 - 03/2021
- Participated in a project utilizing time series prediction to predict stock prices.
- Implemented deep learning methods (e.g. random forests, convolutional neural networks, and long-short term memory) to accurately predict the stock price.
- Scraped and analyzed the historical stock prices and the financial data to improve the performance of the prediction models.
- Conducted research and survey on papers related to the time series prediction problems.
Object Detection with LiDAR Sensor
03/2019 - 03/2020
- Participated in a project aimed at improving the accuracy of human detection given LiDAR sensory data.
- Collected and preprocessed datasets using a LiDAR machine.
- Implemented machine learning methods such as random forest for a classification.
Anomaly Detection with Imbalanced Dataset for CNC Machines
09/2018 - 02/2019
- Participated in a project for an anomaly detection where the data was extremely imbalanced.
- Analyzed datasets with Pandas and Scikit-learn libraries and selected preprocessed features for a model to classify the anomalies.
- Conducted research on handling imbalanced datasets and implemented an algorithm to solve the imbalanced problem.
- Implemented machine learning models (e.g. random forests and multi-layered perceptron) to classify anomalies
Optimization for Balancing the Sputter Uniformity of LCD
06/2018 - 08/2018
- Implemented a deep learning method (multi-layer perceptron) to find the best state that the target matters are uniformly distributed on a substrate.
- Preprocessed and analyzed sputtering dataset with python libraries such as Scikit-learn to find features used for inputs of a model.
AI, Big Data in Pohang University of Sci. and Tech.
12/2017 - 03/2018
- Studied machine learning, deep learning, computer vision, and other general subjects regarding artificial intelligence.
- Participated in a project dealing with object detection and performed data trainings as well as hyperparameter tuning.
- Analyzed and translated papers on object detection (e.g. convolutional neural networks, faster-RCNN, etc.) and machine learning algorithms (e.g. random forests and SVM).