Pawfect Match: A User-Interactive Dog Breed Recommendation Powered by Machine Learning

Selecting a dog companion using machine learning can enhance the compatibility between pet and owner. This study introduces dog breed recommendation using machine learning addressing the challenge of matching dog breeds with owners preferences and lifestyles. Traditional methods often result in mismatches, underscoring the need for personalized solutions. Our system uses a comprehensive dataset of dog breed characteristics and machine learning algorithms to align user preferences with breed traits, offering tailored recommendations. Key methods include data wrangling, exploratory data analysis, and recommendation algorithms such as content-based filtering (87% performance), collaborative filtering (67%), and k-nearest neighbor (65%). Content-based filtering was chosen for its superior performance. A user-friendly interface allows users to input preferences and receive personalized breed recommendations, promoting better pet-owner compatibility and responsible dog ownership.