INTRODUCTIONHeart ailment are one of the significant reason of death and disability on the planet, killing 17.5 million individuals every year and more than twenty-three million anticipated passing from cardiovascular sickness by 2030. Coronary illness incorporates different sorts of conditions that can influence center reason. The heart is an important organ of human body.  On the off chance that the blood dissemination to the body is lacking, the organs of the body that is cerebrum and heart quit working and passing happens in couple of minutes.  The peril factors related are distinguished as age, family history, diabetes , hypertension, elevated cholesterol, tobacco, smoke, liquor inward breath, heftiness, physical idleness, chest torment write and less than stellar eating routine [1].Medical industry is data rich yet learning poor. There is requirement for a wise emotionally supportive network for ailment forecast. Data mining strategies like Classification, regression are utilized to anticipate the infection. With the advancements of computing facility gave by software engineering innovation, it is currently conceivable to anticipate many states of infirmities more accurately[15]. Data mining is a cognitive  procedure of discovering the hidden approach patterns from large data set. It is generally utilized for applications, for example, financial data ,analytic thinking, retail, media transmission industry, genome data analysis, logical applications and health mind frameworks and so on. Data mining holds Extraordinary potential to improve heath frameworks by utilizing data and analytics to recognize the accepted procedures that enhance care and reduce cost. WEKA is a effective tool as it contains both supervised and unsupervised learning techniques[14]. We utilize WEKA because it causes us to evaluate and compare data mining techniques (like Classification, Clustering, and Regression etc.) conveniently on real data. The objective of this work is to anayze the potential utilization of classification based data mining techniques like naive bayes, decision tree(j48), ensemble algorithms and simple logistic and so forth.  LITERATURE REVIEWVarious work has been improved the situation disease forecast concentrating on heart illness utilizing different data mining systems.  Authors have connected distinctive data mining techniques like decision trees, KNN, support vector machine, neural network that contrast in their accuracy, execution time. Mr.Chintan Shah [1], clarifies dialog of different classification algorithms in view of specific parameters like time taken to build the model, accurately and inaccurately classified instances and so on. Theresa Princy. R. [2] proposed a framework to precisely foresee heart disease utiizing ID3 and KNN classifiers and  accuracy level also provided for different number of attributes.Finding of coronary illness with the assistance of Bayesian Network calculation has been characterized by Xue et al [3].  Abraham proposed a methodology so as to increase classification accuracy of medical data based on Naive Bayes classifier algorithm [4]. Palaniappan & Awang [5] recommended  a model of IHDPS (Intelligent Heart Disease Prediction System) actualizing data mining calculations, like Naive-Bayes, Decision Trees and Neural Network. The last yield of these algorithm depicts that every strategy has its distinctive capacities in the reason for the portrayed mining objectives. Jagdeep Singh impemented  different association and classification methods on the heart datasets to foresee the heart illness. The association algorithm like Apriori and FPGrowth are used to discover association rules of heart dataset attributes[6].In [7], diverse machine learning systems including Decision Tree (DT), Naive Bayes (NB), Multilayer Perceptron (MLP), K-Nearest Neighbor (K-NN), Single Conjunctive Rule Learner (SCRL), Radial Basis Function (RBF) and Support Vector Machine (SVM) have been applied, individually and in combination, using ensemble machine learning approaches, on the Cleveland Heart Disease data set keeping in mind the end goal to analyze the execution of every strategy. Gudadhe et al. [8] realized a design base with both the MLP network and the SVM approach. This design accomplished an accuracy of 80.41% in terms of the classification between two classes (the presence or absence of heart disease,respectively). Author in [9] assesses the disease categorization using three different machine learning calculations by WEKA Tool. We compare the results in terms of time taken to build the model and its accuracy.  This work demonstrate the Random Forest is best classifier for disease categorization of WEKA tool because it runs efficiently on large datasets. In  paper [10], author applied HNB classifier for analysis of coronary illness tested execution for heart stalog data collection. Experimental result demonstrate that HNB model exhibits a predominant execution compared with other Approaches. Proposed approach applies discretization and IQR filters to enhance the efficiency of Hidden naïve bayes.Authors in [12] executed the framework that extracts hidden knowledge from a historical heart disease database. Mamta Sharma[13] uncovers that the Neural Networks with 15 attributes shows  significant results over all other data mining techniques. Decision Tree methods has proven excellent precision with C4.5, ID3, CART and J48.   THEORITICAL BACKGROUNDKnowledge discovery in databases (KDD) is the interactive and iterative process of finding valuable information from a collection of data. KDD incorporates multidisciplinary exercise. The means engaged with KDD process are listed below-• Selection –  Data applicable to the analysis task are retrieved from the database• Pre-processing – In this step noise and inconsistent data are removed from large data set. Data cleaning is a fundamental step to solve inconsistency problem and cleanup errors in crude data.• Transformation – The strategies like smoothing, aggregation, normalization to transform them into forms appropriate for mining.• Data mining – Intelligent strategies are applied in order to extract data patterns.• Interpretation/ Evaluation – Data patterns are evaluated and visualized and removing redundant patterns from the patterns we generated. Data mining is the core part of the knowledge discovery process of sorting through large data sets to discover correlation among attributes. There are few noteworthy data mining techniques have been produced and used in data mining projects as outlined in underneath figure. Fig. Taxonomy of Data Mining Methods Description methods concentrate on understanding the way the underlying data operates while prediction-oriented methods aim to build a behavioral model for acquiring new and unseen samples and for foreseeing estimations of at least one variables related to the sample. These strategies falls into two categories in particular supervised and unsupervised learning. In supervised learning a function is inferred from training data while in unsupervised learning, find hidden structured data in unlabeled data.