Transportation is a fundamental tool to develop communities, cities, and countries on a larger scale, and more extensive transportation networks have developed ubiquitously. However, it is needed to consider the fact that animals also live in the same environment without using the same means, and there is always a chance of colliding with them while driving vehicles. Animal-Vehicle Collision (AVC) is a principal concern for transportation agencies and roadway hazards that influences human safety, property, and wildlife. State of Tennessee animal crash data has been collected for 23 years from 1994 to 2017 by Tennessee law enforcement, containing 60 different types of information for each collision. As most of the data is categorical, from these 60 parameters, 16 have been selected as most suitable using Weight of Evidence (WOE) and Principal Component Analysis (PCA) (which is not appropriate for categorical data). This research presents and evaluates the performance of five machine learning-based prediction models for animal collisions in the presence of both categorical and non-categorical features. These five models are developed using Logistic Regression, Random Forest, CatBoost, eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LGBM). The CatBoost model has the highest accuracy level at 78.52%. Therefore, it seems to be the most suitable model to predict animal collisions based on 23-year data from Tennessee. The experimental results demonstrate the potential of leveraging categorical data with Support Vector Machine (SVM) classifiers as a viable solution for creating up-to-date and complete analysis for AVC data. This study presents the implementation of different machine learning techniques to find the most reliable features in generating prediction models and then evaluating these prediction models. The results show the most promising contributing factors to animal vehicle collisions.