COMPARATIVE ANALYSIS OF CLASSIFIERS AND ENSEMBLERS IN ASSET MAPPING IN BIG DATA

Ensemble learning refers to a collection of methods that learn a target function by training a number of individual learners and combining their prediction. We explore different ensemble methods in boosting like AdaBoost, CatBoost, Light Boost, and XGBoost by combining their outputs, for classification and regression problems. When compare with single classifiers like Navies Bayes, Decision trees, Support Vector machines, Ensemble methods are more accurate in decision making. In this research, the dataset is school asset dataset, where the major target attributes are latitude, longitude of the school and population in one particular community. Based on the childrens population, the available school assets are requisite for the community or not. Many classification and ensemble algorithms are used to map the school assets in the community and boosting algorithms gives maximum accuracy in mapping the assets. Experiment is conducted in the Asset dataset and results according to classification parameters such as accuracy and AUC are presented.