This project aims to predict shelter animal outcomes using machine learning models. The target variable is an animal's outcome (adopted, transferred, returned to owner, died, disposed, euthanized). Predictor variables include animal type, sex, age, breed, and color. Several models are tested on the Austin Animal Center dataset, including logistic regression, random forest, decision tree, KNN, and SVC. The results show animal type and sex have more influence on adoption outcomes than other variables. Dogs have a better chance of adoption than cats. Spayed/neutered animals are more likely to be adopted, especially spayed females and neutered males. Age, breed and color have little effect, contradicting common