Intern Data Science

MẠC VĂN HƯNG

HCMC, Vietnam +84-357-***-*** ***********@*****.*** linkedin.com/in/vanhungmac

SUMMARY

Energetic and friendly data science student who is passionate about data analysis and machine learning. Eager to join Wisdom as an intern data engineer to improve skills, knowledge and earn more experience. Will finish Senior year in September. Have a good understanding of statistical models, algorithms and analysis. Proficient in a range of modern technologies including Python. HIGHLIGHTS

Data Analysis Data Visualization Data Mining Machine Learning EXPERIENCE

Freelancer, News Addict - 11/2020 - 05/2021

● As a developer, collected RSS feeds (Really Simple Syndication) from over 20 countries' online newspapers, including the U.S.A., the U.K., Australia, Vietnam, etc. With Python, developed parsers for the content of worldwide newspapers, as well as for specific topics such as Fashion, Sports, Business, etc.

● As a tester, used IDEs such as XCode and Android Studio to run the applications on virtual devices. Internship, GSoft - 06/2022 - 09/2022

● Conducted a Customer Segmentation Analysis to learn more about the customers of the company. Used several Data Science tools, including Orange, Jupyter Notebook, to handle the data (preprocessing, cleansing, transformation, etc.) that has over 10000 customers and 10GB of storage capacity. Developed the best algorithm and model for data training, prediction, segmentation and classification.

● Using PowerBI, visualized the company's data through various types of graphs, then made a report and embedded it on the website of the company, where it is available to all of the company's customers. PROJECTS

SoundCloud Data Analysis:

● Collected data of over 50000 tracks, playlists and users from HTML and API on SoundCloud website using Selenium to analyze and visualize the data through more than 10 graphs. Healthcare Stroke Data Analysis:

● Collected data about healthcare and stroke of over 1000 patients on Kaggle to analyze and visualize the data through 5 graphs, implemented models to predict whether the patient suffers from stroke disease. AQI Data Analysis:

● Collected data about AQI (Air Quality Index) and Air Pollution in 5 provinces in Vietnam, analyzed and visualized the data through over 10 graphs using Tableau, implemented models to predict the near future. Text Summarization:

● Implemented extract-based text summarization program using TF-IDF score (term frequency-inverse document frequency) to convert a long text or sentence into a summarized and shorter one. H.A.R.U Shopping WebApp:

● Built a shopping website named H.A.R.U (Handmade All Round Us) to sell handmade products. Moodiary App:

● Developed an Android Studio application for tracking emotions, moods, and statistics about emotions; shows graphs and statistics about emotional expression on a weekly and yearly basis. American Express Prediction:

● Used the American Express data provided by Kaggle which has millions of rows (each row represents a transaction) and almost 50 GB of storage capacity. Applied multiple Data Science techniques such as preprocessing, cleansing, transforming, etc in order to make the training process easier and more optimal.

● Utilized several machine learning algorithms including XGBoost, CATBoost and LGBM (light gradient-boost machine) to train and predict the data with an accuracy of over 95%. SKILLS

Languages: English - Intermediate

Programming Languages: Python, Java

Technologies & Tools: Jupyter Notebook, JupyterLab, Tableau, PowerBI, Django, MySQL EDUCATION

Data Science - Ho Chi Minh City University of Natural Sciences Sep 2019 - Now

Contact this candidate