Predicting of Hosting Animal Centre Outcome Based on Supervised Machine Learning Models

Parte, Sushant (2019) Predicting of Hosting Animal Centre Outcome Based on Supervised Machine Learning Models. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (954kB) | Preview

Abstract

In 2010 Austin passed a plan known as No kill implementation plan which is maintained by Austin Animal center and pursued a 90% live outcome goal. Today Austin is one of the largest no kill animal county in world. These research project helps by the means of data science to develop an approach to its best capabilities to increases the live rate by different means in future. In this research article we used four different supervised learning classification models with feature engineering and implementing the vectorization process. The dataset was cleaned, and monitoring data was created to implement the models. The models implemented were logistic regression, Neural Network, XGboost and Random forest with K-fold holdout cross validation to calculate the and predict the outcome type of animals from Austin animal center outcome dataset. The models evaluated with different evaluation metrics like accuracy, logarithmic loss, sensitivity and specificity providing the output as XGboost outperformed compared to all the other classification models with accuracy of 65.33%. the prediction and actual figures were determined by building confusion metrics.
Keywords- Classification, XGboost, Neural Network, Logistic Regression, Random Forest, Animal center.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Dan English
Date Deposited:	16 Jun 2020 10:45
Last Modified:	16 Jun 2020 10:45
URI:	https://norma.ncirl.ie/id/eprint/4292

Actions (login required)

View Item