Provissional access for improving classification accuracy on diabetes dataset

Abstract

Data mining helps to solve many problems in the area of medical diagnosis using real-world data. However, much of the data is unrealizable as it does not have desirable features and contains a lot of gaps and errors. A complete set of data is a prerequisite for precise grouping and classification of a dataset. Preprocessing is a data mining technique that transforms the unrefined dataset into reliable and useful data. It is used for resolving the issues and changes raw data for next level processing. Discretization is a necessary step for data preprocessing task. It reduces the large chunks of numeric values to a group of well-organized values. It offers remarkable improvements in speed and accuracy in classification. This paper investigates the impact of preprocessing on the classification process. This work implements three techniques such as NaiveBayes, Logistic Regression, and SVM to classify Diabetes dataset. The experimental system is validated using discretize techniques and various classification algorithms.