Machine Learning Data Analyst

Ngoc Luong Nguyen

An Binh Apartment, An Binh ward, Di An town, Binh Duong province, Vietnam

Ħ +84-386-***-*** ć ***************@*****.*** ^ lkpilot luong2311 Summary

I am a passionate and motivated student specializing in investigating Big Data by utilizing Data Processing, Data Analyst and state of the art Machine Learning methods to solve challenging tasks such as Data Mining, Natural Language Processing, and Social Analysis, which provide powerful visualization tools and predictive models for leaders and organizations to make the right decisions at the right time. Education

VNUHCM University of Information Technology Ho Chi Minh City, Vietnam BACHERLOR OF DATA SCiENCE; GPA: 3.33/4.0 Sep. 2021 Present Research interest: Natural Language Processing (NLP), Information Extraction, Emotions and Sentiment Analysis, Social Media Mining Skills

Programming Python, R, C/ C++, Java

Databases MSSQL, MySQL, PostgreSQL

Technologies Hadoop, Spark, Git, PyTorch, Power BI, Azure, MongoDB Languages Vietnamese (Native), English (TOEIC: 780) Others Algorithms skill, Critical thinking, Quick learner, Team work, Communication skill, Collaboration skill Projects

Comprehensive analysis and forecasting of apartment prices in Ho Chi Minh City Oct 2023 Jan 2024 KEYWORDS: MACHiNE LEARNiNG, DEEP LEARNiNG, DATA MiNiNG, DATA ViSUALiZATiON

• Develop and implement web crawling script to collect data from ChoTot.

• Preprocess the collected data by cleaning and transforming it.

• Visualize data using matplotlib and seaborn to understand its distribution, relationships, and underlying trends.

• Perform transformations such as normalization, feature extraction, and creating new variables to prepare data for modeling.

• Use different models such as Random Forest, XGBoost to predict the results.

• Evaluate performances of models using evaluation metrics. A real time energy consumption prediction system for the city Nov 2023 Jan 2024 KEYWORDS: DEEP LEARNiNG, FORECASTiNG, APACHE SPARK, BiG DATA, SPARK STREAMiNG

• Collect data using Selenium library.

• Preprocess data and prepare it for further analysis by cleaning, transforming, and normalizing the dataset.

• Exploratorydataanalysis to have a deeper understanding of the data’s underlying patterns, relationships, and trends.

• Build deep learning model such as CNN, RNN, LSTM to predict energy consumption.

• Evaluate the performance of models using MSE and RMSE.

• Deploy the model using real time data.

Deploying a virtual teaching assistant system based on mooccubex dataset Jan 2024 Jun 2024 KEYWORDS: DEEP LEARNiNG, TRANSFORMER, NLP, DATA MiNiNG, BiG DATA

• Degisn a robust and Scalable Chatbot Architecture.

• Leverage PineCone vector database technology for efficient data storage.

• Create chunks using Recursive character text splitter of LangChain.

• Deploy Chatbot with Docker.

• Implement the Retrieval Augmented Generative (RAG) to enhance contextual response generation.

• Demonstrated expertise in LangChain, PyTorch, and Scikit learn for implementing advanced machine learning functionalities in Chatbot. Real time Aspect Sentiment Quad Predictions for Vietnamese Youtube Comments Feb 2024 Jul 2024 KEYWORDS: DEEP LEARNiNG, DATA MiNiNG, NLP, ASBA, ASQP, APACHE SPARK, BiG DATA, SPARK STREAMiNG

• Collect comment data from Rap Viet and King of Rap on YouTube using Youtube API and Selenium library

• Annotate data with 4 elements quads: aspect category, aspect term, opinion term and sentiment polarity.

• Preprocesse data by cleaning and transforming it into a suitable format for ASQP.

• Apply transformer models to predict aspect category, aspect term, opinion term, and sentiment polarity.

• Evaluate the performance of models using F1 score macro.

• analysis error to understand the underlying reasons and improve its performance.

• Deploy the model using real time data.

NGOC LUONG NGUYEN · RÉSUMÉ

Contact this candidate