Hlayisani-nkuna/Motus-datascience-Hackathon

Config files for my GitHub profile. Hi there 👋 My project was developed as part of the Motus 2025 Data Science hackathon where the goal was to develop a predictive machine learning model that is capable of identifying meaningful relationships to assess the likelihood of a customer purchasing a vehicle using a large dataset. The model performance was evaluated using the following metrics: PR-AUC (precision-recall area under curve) which is useful for imbalanced datasets Log-loss which measures the prediction uncertainty and probability accuracy How to run the notebook: 1. clone this repo 2. open the notebook in google colab or a local Jupyter environment 3. install the required dependencies 4. run the notebook cells sequentially OR open it directly at colab.research.google.com Important: The primary model used in this project was CatBoost The datasets used in this project were provided through external access links rather than direct downloads during the hackathon