How to filter/Tag Outlier values
msacs09
New Altair Community Member
We have a single table that captures daily sales and loans and we wanted to filter all loans.. so generally our loans will be quite high compared to actual sales ex:- sale value is ~38877and loan is ~1073173 and we wanted to filter all loans
sample data
sample data
date dept_id Sal 201907 10 723 201907 10 1073173 201907 10 38877 201907 10 100000 201907 10 500000 201908 20 16818 201908 20 701 201908 20 700 201908 20 850000 201908 20 1000000 201909 10 5909999 201909 10 19999997 201909 10 21999998
Expected Output as below
Y date dept_id Sal out_of_normal_values 201907 10 723 N<br> 201907 10 1073173 Y<br> 201907 10 38877 N<br> 201907 10 100000 Y 201907 10 500000 Y 201908 20 16818 N <br> 201908 20 701 N<br> 201908 20 700 N 201908 20 850000 Y 201908 20 1000000 Y 201909 10 5909999 Y<br> 201909 10 19999997 Y<br> 201909 10 21999998
0
Answers
-
date dept_id Sal out_of_normal_values 201907 10 723 N 201907 10 1073173 Y 201907 10 38877 N 201907 10 100000 Y 201907 10 500000 Y 201908 20 16818 Y 201908 20 701 N 201908 20 700 N 201908 20 850000 Y 201908 20 1000000 Y 201909 10 5909999 Y 201909 10 19999997 Y 201909 10 21999998 Y0
-
@msacs09 you depending on the version of RapidMiner Studio that you are using you may have access to automodel. With it you could use it to find the outliers and then filter them from your Data Set.
In case you don´t have access to AutoModel you could watch this tutorial
https://academy.rapidminer.com/learn/video/workshop-outlier-detection
-1 -
MarcoBarradas GREAT THANK U0