Andrew Kwon's repositories
question-answer-app
Question and Answer web applicaiton using fine-tuned and pre-trained T5 models. Application runs on Streamlit.
bootstrapping_for_regression_tasks
Project for building a linear regression model to predict estimated profits, calculate 95% confidence interval, and risk of loss for a mining company.
data_collection_and_storage
This project is a demontration of tasks for data collection from various sources and conducting data analysis on the results.
data_visualization_using_streamlit
Streamlit app demo for data visualization using a coffee quality dataset from Kaggle (provided by CQI).
knn_linear_algebra
An evaluation of a classification model using the k-nearest neighbors algorithm and analytical proof for data masking in linear regression.
numerical_methods
Trains, tunes, and evaluates different regression models to develop a time-efficient, high-quality model for predicting car prices based on RMSE and CPU runtime.
predict_customer_churn
Classification task for machine laerning models to predict customer churn for a telecom company. Includes EDA, work plan, and model training/evaluation/comparison.
predict_gold_recovery
Project compares three regression models for predicting the amount of gold recovered from gold ore in order to optimize gold production and eliminate unprofitable parameters. Data provided by Zyfra.
sentiment_analysis
Using sentiment analysis and various techniques, this project trains different models to classifiy positive and negative movie reviews.
statistical_data_analysis
Statistical data analysis, data visualization, and hypothesis testing on customer usage data for the telecom company, Megaline.
time_series_analysis
Time series analysis and regression model to predict the number of taxi rides ordered in the next hour.
video_game_sales
Exploratory and statistical data analysis project on global video game sales from 1980-2016.