Machine Learning Data Analysis
Resume:
Nam
***************@*****.***
Thu Duc, Ho Chi Minh, Viet Nam
https://github.com/lovejerryk52
PROFESSIONAL SKILLS
• Data Cleaning, Exploration &
Visualization
• Data Analysis & Modeling
• Data Mining, Cloud Computing
• Computer Vision & Graphics
• NLP, Audio & Speech Processing
• Information Retrieval
• Machine Learning, Deep Learning
• Java & C# Application Programming
TECHNOLOGIES & TOOLS
Technologies: Apache Hadoop, Apache
Hive, Apache Spark, Apache HDFS .
Tools:
• MySQL Server, Azure Data, Azure
Machine Learning Studio
• VMware Workstation, Oracle VM
VirtualBox
• Google Colab, Kaggle, Jupyter
Notebook, Visual Studio, NetBeans
• Microsoft: Word, Excel, PowerPoint
OBJECTIVE
Short-term goals:
• Graduate from university ahead of schedule.
• Gain solid experience through practical work and projects to confidently enhance personal skills.
Long-term goals:
• Develop substantial expertise to become a valuable employee, with the goal of contributing significantly to the company's long-term success. EDUCATION
October 2021 - Present
UNIVERSITY OF INFORMATION TECHNOLOGY - VNU HCMC Computer Science Classification: Excellent
Cumulative Grade Point Average (GPA): 9.06/10
HONORS & AWARDS
• Four times honored as a student with excellent academic and training achievements in Semester 1 of 2021-2022, 2 of 2021-2022, 1 of 2022-2023, and 1 of 2023-2024 (GPA >=9.0)
• Twice honored as a student with good academic and training achievements in Semester 2 of 2022-2023, 2 of 2023--2024 (GPA >= 8.0)
• Four times received the Excellent Academic Encouragement Scholarship Award in Semester 1 of 2021-2022, 2 of 2021-2022, 1 of 2022-2023, and 1 of 2023-2024
(GPA >=9.0)
PROJECTS
02/2024 - 06/2024
DROPOUT PREDICTION Data mining
• Description: Based on the MOOC dataset from Tsinghua University in China, which records students' learning information through online courses, my team explored, preprocessed data, and extracted insights. We built models with Azure Machine Learning to predict student dropout rates and deployed these predictions as a web app
• Using: Azure Data Factory, Azure Data Lake, Azure Databricks, Azure Machine Learning
• My responsibilities: Data exploration, data analysis, feature engineering, model training, model selection, and model fine-tuning, model evaluation
• Link: https://s.net.vn/tIIR
02/2024 - 07/2024
REAL-TIME RESTAURANT REVIEWS ASPECT SENTIMENT QUAD PREDICTION Big Data, Machine Learning
• Description: Developed a system for real-time prediction of aspect-based sentiment using Aspect Sentiment Quad Prediction (ASQP) from restaurant reviews. Utilizing Big Data tools such as Apache Spark and Apache Kafka, the team successfully trained a T5 model, achieving an F1-Score of 0.5883 on the test set
• Using: Apache Spark, PySpark, Apache Kafka, Kaggle, Hugging Face
• My responsibilities: Integrated Spark Streaming with Kafka for batch data ingestion, used PySpark for SQL-based querying and preprocessing, and trained various T5 models
• Link: https://s.net.vn/rFT3
HỒ ĐỨC TRƯỞNG
Machine Learning Engineer Intern
Data Analyst Intern
Data Scientist Intern
Software Developer Intern
SOFT SKILLS
Attention to Detail
Problem solving
Time management
Collaboration
Effective Communication
Presentation Skills
Leadership
CERTIFICATIONS
12/11/2022
TOEIC L&R: 660
Hobbies
● Watching movies, reading
manga, swimming, playing video
games
02/2024 - 7/2024
3D GEOMETRY SIMULATOR Computer Graphics, Web Application Development
• Description: This web application allows users to interactively create and manipulate 3D objects using the Three.js library. Explore various geometric shapes, lighting effects, transformations, textures, and animations
• Using: HTML, CSS, JQUERY, ThreeJS
• My responsibilities: Backend Development, Frontend Support, Testing and Debugging
• Link: https://s.net.vn/aXUJ
09/2023 - 12/2023
CLASSIFICATION OF ANIMAL SOUNDS USING CNN
Machine Learning, Audio Processing
• Description: Automated classification of animal species using soundscape recordings. The project involves converting audio into spectrogram images using the Scipy library, combined with data augmentation and transfer learning on ImageNet. Convolutional Neural Networks (CNNs) are then employed to classify the spectrogram images into different animal species categories
• Using: Python (Google Colab, Kaggle, Jupyter Notebook)
• My responsibilities: data preprocessing, data augmentation, feature engineering, model training, model fine-tuning, model evaluation
• Link: https://s.net.vn/Ec4N
09/2023 - 12/2023
FASHION IMAGE SEARCH ENGINE
Machine Learning, Information Retrieval, Computer Vision
• Description: This project develops a fashion image retrieval tool using pre-trained models (VGG16, ResNet50, Xception) with transfer learning. Features are extracted and indexed using the Faiss library for efficient similarity search, with performance evaluated by the mean Average Precision (mAP) metric
• Using: Python, Pre- trained CNN models and Faiss
• My responsibilities: data preprocessing, feature extraction, indexing, model evaluation, app deployment
• Link: https://s.net.vn/p5n2
2/2023 - 7/2023
COFFEE APPLICATION DEVELOPMENT Application Programming
• Description: This project develops a desktop application in C# for managing a coffee shop. The user-friendly interface is created with Windows Forms, enabling easy navigation for inventory management, order processing, and sales tracking. SQL Server is used for secure data storage, ensuring reliable management of customer and transaction information
• Using: C# (.NET Framework), Visual Studio, Windows Forms, SQL Server.
• My responsibilites: Backend Development, Frontend Support, Database Support, Testing and Debugging
• Link: https://s.net.vn/9Ujp
SOME SMALLER PROJECTS
Cusomer Segmentation using K-means clustering.
Diabetes Prediction using Machine Learning.
Title and Description Classification for Articles Using Word2Vec and Machine Learning Models.
Library Management System: A Windows Application Using Java, SQL Server, and Java Swing GUI.
Web Crawlers Using Scrapy for Python. © topcv.vn
Contact this candidate