A Comparative Study on Mushroom Classification using Supervised Machine Learning Algorithms

Mushroom hunting is gaining popularity as a leisure activity for the last couple of years. Modern studies suggest that some mushrooms can be useful to treat anemia, improve body immunity, fight diabetes and a few are even effective to treat cancer. But not all the mushrooms prove to be beneficial. Some mushrooms are poisonous as well and consumption of these may result in severe illnesses in humans and can even cause death. This study aims to examine the data and build different supervised machine learning models that will detect if the mushroom is edible or poisonous. Principal Component Analysis PCA algorithm is used to select the best features from the dataset. Different classifiers like Logistic Regression, Decision Tree, K Nearest Neighbor KNN , Support Vector Machine SVM , Naïve Bayes and Random Forest are applied on the dataset of UCI to classify the mushrooms as edible or poisonous. The performance of the algorithms is compared using Receiver Operating Characteristic ROC Curve. Kanchi Tank "A Comparative Study on Mushroom Classification using Supervised Machine Learning Algorithms" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-5 | Issue-5 , August 2021, URL: https://www.ijtsrd.com/papers/ijtsrd42441.pdf Paper URL: https://www.ijtsrd.com/computer-science/embedded-system/42441/a-comparative-study-on-mushroom-classification-using-supervised-machine-learning-algorithms/kanchi-tank