Assessment of various Supervised Learning Techniques by means of open source API for Qualitative Bankruptcy

Main Article Content

K.Thanweer Basha
B.Rama Ganesh


The improvement of machine learning household tasks such as classification, clustering and association has exposed the call for machine learning algorithms to be applied on huge amount of data. In this paper we present the evaluation of diverse classification techniques and find the suitable finest classification algorithm for taken dataset, using Waikato Environment for Knowledge Analysis API or in short, WEKA. WEKA is an open source which consists of a group of machine learning algorithms for performing data mining tasks. The aim of this paper is to investigate the performance of different classification methods and come across the finest classification algorithm for given set of large data and we also propose the implication rules for Bankruptcy using Apriori. The actual evaluation of learning by example is done with help of confusion matrix and Receiver Operating Characteristics curve. At this time classification algorithms experienced are Bayesnet, Naivebayesclassifier, ConjuctiveRules, DecisionTable/Naivebayes, DecisionTable, Nearestneighbors, and OneR. In this paper I had chosen Bankruptcy dataset for performing data mining tasks.


Keywords: Data Mining, Supervised learning, Time complexity, Confusion Matrix, open source, API, Qualitative Bankruptcy.


Download data is not yet available.

Article Details