This repository documents my participation in the Kaggle Playground Series – Model Ranking competition. I joined this competition primarily to test my knowledge, sharpen my machine learning skills, and most importantly, to have fun while experimenting with different modeling approaches.
The objective of the competition was to build a model that accurately ranks inputs according to given criteria. It served as a great opportunity to explore a practical ML problem in a low-stakes, learning-friendly environment.
I ranked #2956 on the final leaderboard.
While this wasn’t a top-ranking result, the competition gave me valuable hands-on experience with:
- Data preprocessing
- Model selection and tuning
- Evaluation metrics for ranking problems
- Experimentation and iteration strategies
- To challenge myself with a real-world-style ML problem.
- To explore new libraries, tools, and techniques.
- To enjoy the process of building and refining models in a competitive setting.
- Python
- scikit-learn / XGBoost / LightGBM
- pandas / NumPy / matplotlib / seaborn
- Jupyter Notebooks
This repo includes:
- Kaggke Notebook with my experiments and approach
- Scripts for data preprocessing and model training
- Notes and observations from the competition
- Dataset used
- Output and predictions