Empirical evaluation of algorithms to impute missing values for financial dataset

While mining the data of investment in different financial instruments, we encounter with the problem of incomplete data. In order to have more efficient analysis and results, there is a need to calculate missing values in data. Various approaches for missing value imputation have been proposed and compared in the literature. But to the best of my knowledge work reported here on performance analysis of K-means, Fuzzy K-means and Weighted K-means to compute missing values has yet not been done using financial dataset. This paper analyzes the performance of these three algorithms to find incomplete values of missing factors. Root mean square error is used as an evaluation criterion for the comparison for three mentioned algorithms. Computation is done on the data of investment patterns in different financial instruments. Results show that K-Means algorithm suite the financial data best for incomplete values imputation in comparison to other variants.