Date on Master's Thesis/Doctoral Dissertation


Document Type

Master's Thesis

Degree Name



Computer Engineering and Computer Science

Degree Program

Computer Science, MS

Committee Chair

Kantardzic, Mehmet

Committee Co-Chair (if applicable)

Elmaghraby, Adel

Committee Member

Elmaghraby, Adel

Committee Member

Lewis, James

Author's Keywords

data mining; graph theory; machine learning


This thesis presents an applied horse racing prediction using graph based features on a set of horse races data. We used artificial neural network and logistic regression models to train then test to prediction without graph based features and with graph based features. This thesis can be explained in 4 main parts. Collect data from a horse racing website held from 2015 to 2017. Train data to using predictive models and make a prediction. Create a global directed graph of horses and extract graph-based features (Core Part) . Add graph based features to basic features and train to using same predictive models and check improvements prediction accuracy. Two random horses were picked that are in same races from data and tested in systems for prediction. With graph based features, prediction of accuracy better than without graph-based features. Also We tested this system on 2016 and 2017 Kentucky Derby. Even though we did not predict top three results from 2017 Kentucky Derby, in 2016 Kentucky Derby, we predicted top four position.