The universe is overwhelmed with various kinds of data like medical data, scientific data, web data, environmental data, financial data and mathematical data. Due to incredible increase in data in this age of network and information sharing, physical analysis, classification and summarization of data became difficult. By using a number of techniques, such missing data can be brought to line. Among the methods which are used to handle this issue to substitute the missing values, some popular methods can be adopted, such as k-means, C4.5, SVM, EM, decision tree, Apriori, CART, kNN, and naive Bayes. Missing data is a universal problem in all data fields, missing data or missing values occur when the data value is preserved for the variable in an observation. It has a major effect on the conclusion that can be drawn towards the data. This research investigates the fundamentals of data mining and whether the incomplete values occur in the training dataset and same will impute or not.

data mining, missing data, SVM, Apriori.