• Manuja Sharma

With the emergence of technology, the availability of raw data over the network has increased unprecedentedly and this data is continuously exploding day by day. This data needs to be processed and analyzed in some efficient ways, and the information thus extracted can help serving some or the other purpose. Data mining is one of the emerging research fields that offer various techniques and methods that are again used for predicting the patterns and future trends in the available data. There are numerous techniques which are used for predicting the class in which the particular data falls in. Classification of data becomes difficult with the unbounded size and imbalance nature of data. The problems of over-fitting and bias are somewhat solved with the help of Meta learning methods (also known as Ensemble methods). This research focuses on analyzing the behavior of Meta Learning techniques, such as Bagging, Boosting and Stacking, with the help of three base classifiers, i.e. Naïve Bayes, Decision Table and J48, over the increasing size of data. WEKA tool has been used for the experimental purpose and the parameters that helped in evaluating the performance are accuracy, root mean squared error, kappa statistics, precision and recall.

Data Mining, Classification, Naïve Bayes, Decision Table, J48, Ensemble Methods, Bagging, Boosting, Stacking, WEKA Tool

"PERFORMANCE ANALYSIS OF META LEARNING ALGORITHMS FOR INCREASING DATASET SIZE ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.333-343, May-2019, Available :http://www.jetir.org/papers/JETIR1905Q45.pdf

"PERFORMANCE ANALYSIS OF META LEARNING ALGORITHMS FOR INCREASING DATASET SIZE ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp333-343, May-2019, Available at : http://www.jetir.org/papers/JETIR1905Q45.pdf