Comparison of Classification Algorithms on th...

Comparison of Classification Algorithms on the Basis of Size of Dataset

Author Name : Pranay Singhal, Dr. Sunil Maggu

ABSTRACT

In today’s world of rapid increase of technology, machine learning and artificial intelligence has taken over the world. There has been keen interest of everybody associated with technology in this sector. However there are multiple algorithms that can be employed in solving various problems. Classification, one of the main domains of data mining, involves known structure generalizing to apply to a new data point and predict its class. We have chosen to implement the classification algorithms on two datasets for the comparative study. The datasets have been selected based on their size and/or number and nature of attributes. Results have been discussed using some performance evaluation measures like precision, accuracy, mean absolute error, relative absolute error, F-measure, ROC Area etc. Comparative analysis has been carried out using the performance evaluation measures of accuracy, precision. We specify features and limitations of the algorithms for the diverse datasets.

Keywords- Machine learning, Classification algorithms; size of dataset; Credit card fraud; Heart disease detection, KNN, Logistic Regression.