“…In order to properly validate the data mining regression performance, the well‐known k ‐fold cross‐validation method was executed, repeating five times a fivefold and in each run performing grid search parameters. The following parameters were analyzed with an (a) original database and (b) new databases without declared outliers: - Kernel type: [Lineal, Polynomial, RBF]
- Gamma:[2 −5 , 2 −4 , 2 −3 , 2 −2 , 2 −1 , 2 0 , 2 1 , 2 2 , 2 3 , 2 4 , 2 5 ]
- C: [2 −5 , 2 −4 , 2 −3 , 2 −2 , 2 −1 , 2 0 , 2 1 , 2 2 , 2 3 , 2 4 , 2 5 ]
- NU: [0.015, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]
- Polynomial degree in Polynomial kernel:
…”