Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Jurnal Teknik Informatika (JUTIF)

LINEAR REGRESSION FOR PREDICTION OF EXCESSIVE PERMISSIONS DATABASE ACCOUNT TRAFFIC Agus Pamuji; Heri Satria Setiawan
Jurnal Teknik Informatika (Jutif) Vol. 3 No. 2 (2022): JUTIF Volume 3, Number 2, April 2022
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20884/1.jutif.2022.3.2.206

Abstract

Today, the security of information and data is an important asset for everyone in protecting data. Data and information become critical when weaknesses and threats come. In this study, an estimation of the observed variables will be carried out. The application of data mining, especially with the estimation method by using linear regression techniques. The next stage is data preparation by referring to the dataset recorded in the user activity log. Data preparation takes a lot of time because you have to make sure the data fits the needs of data mining analysis. The analysis technique with linear regression involves three independent variables as Type Permissions, Type of User Account, Status, and the dependent variable, namely User Actions. The strongest effect was found in type_permissions and state when together on user_actions. The type_permissions variable keeps increasing when the state on the user is active. The status attribute also suffers from the same condition. Accrording to the results, our findings in root mean squared error is 37.614 and absolute error is 31.058, and mean absolute percentage about 23%. Furthermore, User_action as an estimated variable gives two data opportunities whether it is allowed or not. Therefore, in future research, it is necessary to map users of the database system still in the context of data mining when digging for information on excessive permissions.