Zhujun Tan (竹君谭)'s Projects
This project use Logistic Regression, Random Forest, XGBoost, and SVM to classify whether to give the loan for each observation.
This project build logistic regression model to predict the probability of default of each customer and evaluate by using Gini Coefficients
use XGBoost and Adaboost to predict heart disease and use SHAP to explain the potential factors behind the result.
predict the user rating from the review by using BERT, RoBERTa, Xlnet.
This repository summarizes the content of Python Crash Course by Eric Matthes (2023 edition). It is suitable for anyone who wants to brush up on the basics of Python or for those who do not have time to read the entire book.
use Random Forest for regression and then use LIME to interpret the the variables behind the customer churn
This project uses SQL for data preprocessing, feature engineering, and analysis on Sales data. Subsequently, Tableau is employed to create an informative Sales Performance Dashboard. Together, these tools provide comprehensive insights into the store's sales dynamics, aiding strategic decision-making.
(Active project) Predict Thai stock closing price with time series, machine learning, and deep learning methods
This study aims to investigate the effectiveness of three Transformers (BERT, RoBERTa, XLNet) in handling data sparsity and cold start problems in the recommender system. We present a Transformer-based hybrid recommender system that predicts missing ratings and ex- tracts semantic embeddings from user reviews to mitigate the issues.
use BERT to analyze whether each tweet is neutral, positive, or negative.