This repo uses my code from the kaggle competition "PetFinder.my Adoption Prediction". DATA: The data can be downloaded from https://www.kaggle.com/c/petfinder-adoption-prediction/data as per Kaggle's terms of use.
PetFinder.my has been Malaysia’s leading animal welfare platform since 2008, with a database of more than 150,000 animals. PetFinder collaborates closely with animal lovers, media, corporations, and global organizations to improve animal welfare.
Animal adoption rates are strongly correlated to the metadata associated with their online profiles, such as descriptive text and photo characteristics. As one example, PetFinder is currently experimenting with a simple AI tool called the Cuteness Meter, which ranks how cute a pet is based on qualities present in their photos.
As at the time of the first commit, a Random Forest Classifier is used to predict the AdoptionRate. Best features are selected through Grid Search. In the coming iterations, image data will be utilized to be fed into a CNN, which will hopefully provide better insights.
Link to kaggle kernel- https://www.kaggle.com/abhineethmishra/using-random-forest