Data Science, Machine Learning

BUI THANH TUNG

Ho Chi Minh City, Vietnam

033*-***-*** *******.****@*****.***

Github: tungbtt Linkedin: tungbtt

ABOUT ME

A dedicated data science student with a strong grasp of data collection, cleaning, and preprocessing. Proficient in utilizing various machine learning models such as regression, classification, clustering, and neural networks. Seeking an opportunity to apply these skills and contribute effectively to a dynamic data science role. TECHNICAL SKILL

Python, C++, SQL, Pandas, Plotly, Tableau, Scikit-Learn, TensorFlow,… EDUCATION

University of Science – VNU-HCM (2020-now)

Computer Science - Data Science

GPA (2020-2023): 8.33/10

PROJECT

Disaster Tweets Prediction 7 -2023

• Position: Team Leader

• Team size: 5

• Description: This project employs the BERT Large model to predict disaster-related tweets and deploys it as a web application. Users input a tweet link, and the application determines if the tweet is disaster-related. Model achieved an accuracy of 0.83 on the Kaggle test dataset.

• Responsibilities: Cleaning and preprocessing data, building the model.

• Technical: Python (pandas, transformers, nltk, flask)

• Source code: https://github.com/tungbtt/DisasterTweetsPrediction-BERT-MODEL.git Dashboard: Housing Prices in Hanoi 7-2023

• Description: The project utilizes Python libraries for data cleaning, preprocessing, and employs Tableau to deploy as a dashboard.

• Technical: Python (pandas, numpy), Tableau.

• Source code: https://www.kaggle.com/code/tungbtt/data-cleaning-data-viz-with-tableau Shop Customer Cluster 4-2023

• Description: The project encompasses data cleaning, preprocessing, exploratory data analysis, and employs the K-means model for customer segmentation.

• Technical: Python (pandas, seaborn, plotly, sklearn)

• Source code: https://www.kaggle.com/code/tungbtt/shop-customer-data-cleaning-k-means-clustering Analysis of Room Rental Prices in Ho Chi Minh City 1-2023

• Position: Team Leader

• Team size: 4

• Description: The project is conducted through the following steps: data collection (data collected from phongtro123.com using the Scrapy library), data preprocessing, and exploratory data analysis.

• Responsibilities: collecting, preprocessing, analyzing data.

• Technical: Python (scrapy, pandas, numpy, seaborn, matplotlib)

• Source code: https://github.com/tungbtt/LTKHDL_Project_Phongtro.git

Contact this candidate