Classification with an Academic Success Dataset

Kaggle Playground June 2024

About the Tabular Playground Series

The goal of the Tabular Playground Series is to provide the Kaggle community with a variety of fairly light-weight challenges that can be used to learn and sharpen skills in different aspects of machine learning and data science. The duration of each competition will generally only last a few weeks, and may have longer or shorter durations depending on the challenge. The challenges will generally use fairly light-weight datasets that are synthetically generated from real-world data, and will provide an opportunity to quickly iterate through various model and feature engineering ideas, create visualizations, etc.

Goal: The goal of this competition is to predict academic risk of students in higher education

Table of content

1. Preparation (libraries and data)

2. Exploratory Data Analysis (Univariate and Multivariate)

3. Data Visualization

4. Data Preprocessing (LabelEncoder(), OneHotCoder(), StandardScaler())

5. Machine Learning (LGBM, XGB, CatBoost, KNN, Random Forest)

6. Hyperparameter Tuning with Optina

7. Deep Learning

8. Ensemble Models (VotingClassifier())

9. Model Evaluation

10. Predict & Submit

As a beginner in data science, I have done a lot of trial-and-errors through Hyperparameter Tuning and first-time trying Ensembling/Voting method! I also applied Deep Learning (Neural Networks) to my voting models.

> My accuracy score is 0.838 and placed in 147/2678 entries, making me *top 5%* of the leaderboard!

* I'd excited to share my notes about this competition in more details through my Medium blog