Data Science Machine Learning

096*-***-*** **************.***@*****.***

Ho Chi Minh City, Vietnam /in/kien-duong-trung/

EDUCATION

Ho Chi Minh City University of Technology and Education 2021 - 2025 KIEN DUONG TRUNG

Analytics Enthusiast Data Science Problem-Solving SUMMARY

I am an ambitious data aficionado eager to apply my knowledge of descriptive, predictive, and prescriptive statistics to practical challenges. I excel in data preparation, analysis, and presenting findings in an understandable manner. I aspire to shape sustainable, accessible, and inclusive business practices through data science. My skill set includes Python, R, SQL, Scikit-learn, Tensorflow, and statistical modeling, with a goal to drive real accountability and professional growth in a supportive team environment. Web Development and Computer Science Lecturer

MindX Techonology School

2022 - Present Ho Chi Minh City, Vietnam

Designed and developed curricula for courses in Web Development and Computer Science, ensuring students grasp both fundamental and advanced concepts. Led over 300 students through hands-on courses, teaching programming languages such as HTML, CSS, JavaScript, and Python.

Incorporated cutting-edge technology into teaching, including Python, React, Node.js, and other web technologies, preparing students for real-world work environments. Facilitated group projects, encouraging teamwork and the practical application of knowledge, enhancing problem-solving skills and logical thinking. Achieved a 95% course completion rate, with positive feedback from students on teaching style and course content.

Part-time

Software Developer Internship

TOPFOLIDA Co ., Ltd

2021 - 2022 Ho Chi Minh City, Vietnam

Developed and maintained websites using WordPress, ensuring responsive design and optimal user experience.

Implemented front-end features using HTML, CSS, and JavaScript, ensuring websites were interactive and visually appealing.

Provided technical support and training for clients, enabling them to manage and update their websites independently.

Part-time

EXPERIENCE

Crop Recommendation Model

Aug 01, 2024 Ho Chi Minh City, Vietnam

Objective: Developed a machine learning model to recommend the optimal crop to plant based on soil and weather conditions.

Tools and Technologies Used: Python, Scikit-learn, Pandas, NumPy, Matplotlib, Seaborn, Jupyter Notebook

Key Achievements:

Data Collection and Preprocessing: Collected and cleaned data on soil properties, weather conditions, and crop yield from agricultural datasets. Feature Engineering: Engineered features such as Nito, Phopho, Kali, temperature, humidity, rainfall, and pH levels to improve model accuracy. Model Development: Implemented and compared multiple algorithms, including Logistic Regression, Random Forest, Decision Trees, and K-Nearest Neighbors. Model Evaluation: Achieved an accuracy of 98% using cross-validation and hyperparameter tuning.

Visualization: Created visualizations to interpret feature importance and model predictions, aiding in decision-making for crop selection.

Impact: Provided insights that could help farmers optimize crop yield and resource allocation. Diabetes Prediction Model

Jul 20, 2024 Ho Chi Minh City, Vietnam

Objective: Developed a machine learning model to predict the likelihood of diabetes in patients using medical and lifestyle data.

Tools and Technologies Used: Python, Scikit-learn, Pandas, NumPy, Matplotlib, Seaborn, Jupyter Notebook

Key Achievements:

Collected and preprocessed data from the Pima Indians Diabetes Database, ensuring data quality by handling missing values and outliers.

Exploratory data analysis (EDA) was performed to understand the relationships between variables and identify significant features impacting diabetes risk. Feature selection and engineering were employed to improve model performance, including normalization and the creation of new features.

Implemented various machine learning algorithms, including logistic regression, decision trees, and random forests, to identify the best-performing model. Achieved a model accuracy of 78% with Support Vector Machine Algorithm, optimizing hyperparameters through cross-validation techniques. Visualized model performance using ROC curves, confusion matrices, and other metrics to evaluate precision, recall, and F1-score.

Presented findings in a detailed report, offering actionable insights for early intervention and treatment strategies based on model predictions.

PERSONAL PROJECTS

Calories Burnt Prediction Model

June 04, 2024 Ho Chi Minh City, Vietnam

Objective: Developed a machine learning model to predict the number of calories burnt during physical activities based on user data and activity metrics. Tools and Technologies Used: Python, Scikit-learn, Pandas, NumPy, Matplotlib, Seaborn, Jupyter Notebook, TensorFlow/Keras

Key Achievements:

Collected and preprocessed data from sources such as fitness trackers or public datasets, ensuring the removal of anomalies and handling missing values. Conducted exploratory data analysis (EDA) to identify key factors influencing calorie expenditure, such as age, weight, height, duration, and activity type. Engineered features to enhance model performance, including creating new variables like intensity levels and categorizing activity types.

Implemented multiple machine learning algorithms, including linear regression, random forests, and neural networks, to compare model effectiveness. Achieved a model accuracy of 97% with the XGBRegressor algorithm, fine-tuning hyperparameters for optimal performance.

Visualized the relationship between features and calorie expenditure through scatter plots, heatmaps, and regression plots, providing insights into data patterns. Presented findings in a comprehensive report, highlighting practical applications for personalized fitness recommendations and health monitoring. Laptop Price Prediction Model

May 05, 2024 Ho Chi Minh City, Vietnam

Objective: Developed a machine learning model to predict laptop prices based on specifications and features.

Tools and Technologies Used: Python, Pandas, NumPy, Scikit-learn, XGBoost, Matplotlib, Seaborn, Jupyter Notebook

Key Achievements:

Data Collection and Preprocessing: Collected and cleaned a dataset of laptop specifications and prices from online retailers and other public sources. Feature Engineering: Engineered features such as CPU type, RAM size, storage capacity, GPU, and screen size to enhance model predictions.

Model Development: Implemented and compared multiple regression algorithms, including Linear Regression, Random Forest Regressor, and XGBoost Regressor. Model Evaluation: Achieved an accuracy of 87% using the best-performing model. Conducted cross-validation and hyperparameter tuning to improve accuracy and generalization. Visualization: Created visualizations to analyze feature importance and model predictions, aiding in understanding key factors affecting laptop prices. Impact: Provided a tool to assist consumers and retailers in understanding pricing trends and making informed decisions.

CERTIFICATIONS

Machine Learning Engineer

Completed a comprehensive program covering machine learning algorithms, model deployment, and data preprocessing using Python and Scikit-learn. datacamp Jul 15, 2024

Associate Data Scientist in Python

Covered data manipulation with Pandas, clean data, data visualization with Matplotlib and Seaborn, and Machine Learning with Scikit-learn. datacamp Dec 08, 2023

Data Analyst with Python

Mastered data manipulation and analysis using Pandas, data visualization with Matplotlib and Seaborn, and statistical analysis techniques. Completed projects involving exploratory data analysis and visualizations of real-world datasets. datacamp Oct 05, 2023

Google IT Automation with Python Professional

Mastered data manipulation and analysis using Pandas, data visualization with Matplotlib and Seaborn, and statistical analysis techniques. Completed projects involving exploratory data analysis and visualizations of real-world datasets. coursera Sep 24, 2022

IBM Data Science Professional

Completed a comprehensive program covering data science fundamentals, including Python, SQL, and data visualization. Gained hands-on experience with data analysis, machine learning, and statistical methods using tools such as Jupyter Notebook and IBM Watson.

coursera Sep 12, 2023

SKILLS

Python Numpy Pandas Matplotlib Seaborn Scikit-learn Data Analysis Machine Learning Data Science SQL Server LANGUAGE

English

Proficiency Level: Basic Communication

Skills: Able to read and understand technical documentation, basic conversational skills.

Contact this candidate