Zainab Iqbal et al, International Journal of Computer Science and Mobile Computing, Vol.9 Issue.4, April- 2020, pg. 27-35 © 2020, IJCSMC All Rights Reserved 27 Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology ISSN 2320–088X IMPACT FACTOR: 7.056 IJCSMC, Vol. 9, Issue. 4, April 2020, pg.27 – 35 Multiclass Classification with Iris Dataset using Gaussian Naive Bayes Zainab Iqbal 1 ; Manoj Yadav 2 ¹Department of Computer Science and Engineering, Al-Falah University, India ²Department of Computer Science and Engineering, Al-Falah University, India zainaishna1234@gmail.com 1 ; manoj200.yadav@gmail.com 2 Abstract— A prominent subset of artificial intelligence is machine learning which in today’s modern era, is all around us. A model is created in machine learning based on training data and it is predicted that whether the inferences made were correct .Thus the essence of machine learning lies in data extraction and then predictions. It assists a computer to be programmed by self-learning and thereby improve its performance at a specific task. Supervised machine learning tasks primarily include classification for which various algorithms have been applied so far. In this paper, we apply a supervised learning algorithm such as Gaussian Naïve Bayes to classify the species of an Iris flower based on the length and width of their sepals and petals. The performance of the classifier is then tested in terms of its accuracy and classification metrics. Keywords—Effectiveness Measures, Gaussian Naïve Bayes, Iris Dataset, Supervised learning, Multiclass classification I. INTRODUCTION Machine learning approach has a vital role in classification. Classification algorithms come under the category of supervised machine learning concept which fundamentally categorizes a set of data into classes. We present a multiclass classification for the Iris dataset through implementation of a supervised machine learning algorithm Gaussian Naive Bayes which determines the accuracy and performance for prediction of the class of an Iris flower. The dataset that we have used for our research is based on the version present in the UCI machine learning repository as mentioned in [1]. This data set consists of 3 classes of 50 instances each, where each class refers to a type of an Iris plant. The classes into which it is classified are Iris setosa, Iris versicolor and Iris virginica. Python is used along with machine learning on the Iris dataset to facilitate the classification.