Hello everyone,
My data has
5 input features(columns) ( M1 , M2, M3, M4, M5) which are float numbers.
6 output labels(columns) (E1, E2, E3 ,E4 ,E5 ,E6) , which contain discrete numbers (classes) 0 to 8 such as 0,1,2,3,4,5,6,7,8. , for example samples look likes this :
M1 M2 M3 M4 M5 E1 E2 E3 E4 E5 E6
7.6 15.2 38.7 54.8 67.5 0 0 2 1 0 0
7.8 16.5 39.7 64.6 77.5 8 0 0 0 5 0
8.8 26.5 49.7 74.8 87.5 0 7 0 0 0 6
9.8 28.5 50.7 76.8 89.5 1 0 3 0 0 0
Now,this looks like to me,multiclass multioutput classification , what is best solution to this problem. Solution which gives highest acuuracy or best prediction.
Should i use, machine learning classification approach or nural network approach.
I have tried few of methods, but could not get desired reults.
csv file attached , which is not too big.
Data.csv (11.9 KB)
Need help in this regard
Thanks.
1 post - 1 participant