Data Science/AI/ML

Dang Nguyen Quang Huy

AI/ML Engineering

PROFILE

Male

039*******

ad5y39@r.postjobfree.com

https://github.com/ZeusCoderBE

Linh Trung ward,Thu Duc City,Ho Chi Minh City

SKILLS

MAIN SKILL

Programming Languages:Python, Java, C#, C++, OOP

EDA and Visualization: Python(numpy,pandas, seaborn

,matplotlib),Data Preprocessing,Power BI,Excel

Machine Learning/Deep Learning Python (scikit-learn

,tensorflow),Regression, Classification, Clustering,NLP

(Sentiment Analysis,Text Generator...), Google Colab,Kaggle Data Modelling:SQL Server, Relational Database (SQL), SSAS Mathematics: Probability and Statistics, Linear Algebra English: Ability to read and study documents

Version Control:Git

OTHER SKILL

Apache Hadoop, Apache Hive, Spring MVC, NET Framework, Ubuntu Desktop/Server

STRENGTH

- Hardworking

- Creative

- Planning

- Highly responsible

- Teamwork

OBJECTIVE

After graduation, I aspire to embark on a professional journey as an AI Engineer or Data Science Specialist, specializing in the processing of various data types, with a particular focus on Natural Language Processing (NLP) and Generative AI. EDUCATION

Major: Data Engineering 2021 - 2025

School: Ho Chi Minh City University of Technology and Education GPA : 8.54

Certificate - Coursera: Machine Learning Specialization (3/2024) Certificate - English: TOEIC 600 (8/2023)

PROJECT

I.Project Name: Applying Artificial Neural Networks to Build Text Generation Models as Part of the Generative AI Problem : (3/2024 - 4/2024)

Source: https://github.com/ZeusCoderBE/Next_word_predicting Team : 1 (Individual Project)

Description: I developed an RNN-based model to predict the next word in a sentence, addressing a key task in natural language processing. The project involved several data preprocessing steps, including sentence extraction, meaningful word matching, word dictionary creation, and input sequence generation using the n-gram method. The deep learning architecture I built includes embedding layers and a SimpleRNN, using TensorFlow and Keras libraries for model development and evaluation. I assessed the model's performance with metrics such as accuracy, precision, recall, and F1 score. II.Project Name: Applying artificial neural networks to build models to analyze customer emotions based on comments and evaluation serves for determination business-related trends: (3/2024 - 5/2024) Source: https://github.com/ZeusCoderBE/NLP-clustering-word--Vietnamese-Sentiment-Analysis Team : 1 (Individual Project)

Description: Sentiment analysis combined with text generation:

- I developed a project to analyze customer sentiment from comments using CNN and LSTM models. Data preprocessing included removing punctuation, stop words, and symbols, combining meaningful Vietnamese words, reformatting text, tokenizing words, and creating a corpus. For the CNN model, I used word2vec (skip-gram) for word embedding to capture the relationship between words and their context. In the LSTM model, I used an embedding layer to represent word relationships and visualized the embedded words as vectors in space.

- Additionally, I rebuilt the text generator model to automatically generate comments for users, integrating it with the emotion recognition model to analyze sentiment when comments are sent. The models were evaluated using accuracy, precision, recall, and F1 score. I implemented the model on a web app using Streamlit to identify sentiment in new comments. III.Project Name: Building The Recommender System through content filtering and collaborative filtering:

(1/2024 - 3/2024)

Source: https://github.com/ZeusCoderBE/Recommender-System Team : 1 (Individual Project)

Description: I implemented two recommendation algorithms sush as Content Filtering and Collaborative Filtering. 1. Content Filtering:

- I created a vector representation for each movie using TF- IDF (item profiles).

- I trained a ridge regression model for each user to learn the weights(user profiles).

- I used item profiles and user profiles to predict and recommend movie ratings. 2. Collaborative Filtering:

- I utilized two approaches: item-item and user-user.

- I calculated cosine similarity between items or users.

- I implemented a KNN model by selecting K similar users/items to predict rating scores. AWARDS

OUTSTANDING STUDENT SCHOLARSHIP IN THE FIELD OF STUDY 2023 - 2024 School: HCMUTE

That school year, I had the highest score in my major © topcv.vn

Contact this candidate