Portfolio

Updated: 03/07/2023

📈 Data Analysis

Hanoi Housing Prices

In this project, I am going to clean a dataset about real estate sales in Hanoi, Vietnam. I will then perform some feature engineering techniques and exploratory data analysis (EDA). Finally, I will create a model to predict the price of each home.

Cookie Cats: Analyze A/B tests

Cookie Cats is a hugely popular mobile puzzle game developed by Tactile Entertainment. It’s a classic “connect three”-style puzzle game where the player must connect tiles of the same color to clear the board and win the level.

As players progress through the levels of the game, they will occasionally encounter gates that force them to wait a non-trivial amount of time or make an in-app purchase to progress. In addition to driving in-app purchases, these gates serve the important purpose of giving players an enforced break from playing the game, hopefully resulting in that the player’s enjoyment of the game being increased and prolonged.

But where should the gates be placed? Initially the first gate was placed at level 30. In this project, we’re going to analyze an AB-test where we moved the first gate in Cookie Cats from level 30 to level 40. In particular, we will look at the impact on player retention.

League of Legends Diamond Ranked Games Analysis (10 minutes early game)

📡 Computer Vision

Kaggle: Global Wheat Detection (YOLOv8)

Global Wheat Detection was a challenge on Kaggle that was held in 2020. Challengers had to detect wheat heads from outdoor images of wheat plants.

YOLOv8 is the latest version of YOLO by Ultralytics. As a cutting-edge, state-of-the-art (SOTA) model, YOLOv8 builds on the success of previous versions, introducing new features and improvements for enhanced performance, flexibility, and efficiency. YOLOv8 supports a full range of vision AI tasks, including detection, segmentation, pose estimation, tracking, and classification. This versatility allows users to leverage YOLOv8’s capabilities across diverse applications and domains.

In this project, I used YOLOv8_n with an image size of 320x320 as a baseline and applied few augmentation techniques to enhance the accuracy.

Classify handwritten characters in ancient Japanese manuscripts (Kuzushiji-MNIST)

As a beginner japanese learner, so I want to combine japanese and machine learning. I am very excited went i saw this dataset.

Kuzushiji MNIST is a drop-in replacement for the MNIST dataset (28x28 grayscale, 70,000 images), provided in the original MNIST format as well as a NumPy format. Since MNIST restricts us to 10 classes, they chose one character to represent each of the 10 rows of Hiragana when creating Kuzushiji-MNIST.

Hiragana ひらがな is a Japanese syllabary, part of the Japanese writing system, along with katakana カタカナ as well as kanji 漢字.

My hiragana and katakana hand writing 🤗🤗🤗

This project is my baseline for further improvements. I hope you enjoy it!

“千里の道も一歩から”

“Vạn sự khởi đầu nan”

Face recognition with InsightFace

2021 was a terrible year for Vietnam, as COVID-19 surged in the southern provinces. It was also my second year of university, and during that time, I participated in undergraduate scientific research on the topic of “Identification of individuals wearing masks” in the hope of contributing a small effort to the fight against the pandemic.

InsightFace was a useful tool to begin developing an identity recognition system. It provides both face detection and face recognition for us.