A Comprehensive Analysis Of Normalization Approaches For Privacy Protection In Data Mining

Abstract

Data Mining is a fundamental method of extracting large volumes of data sets by unfamiliar patterns. These extracted data can be shared between enterprises to improve their corporate benefits. For the data mining process, sharing such confidential data is very important. It is very important to safeguard such information against unwanted exposure that leads to privacy leakage. In recent days, privacy in various data mining applications has become very important. In order to overcome such problem privacy, data mining techniques are preserved. It provides accurate data mining results without scarifying the original data values and ensures both accuracy and privacy. Data protection is achieved through the analysis of the data using normalization techniques in this proposed work. The approach proposed in comparison the effects of min-max, decimal scaling, and Z-Score normalization techniques. Experimental effects confirmed that the Min-max Standardization technology archived the most precision with minimum data loss.