SVM model taking more time and results are not obtained even after 48 hours

Machine Learning and Modeling
1

The following code is executed to find the best model after performing tuning using cross-validation. But the model is still running even after 48 hours. is there any problem with the code. The data used in the model is having 62000 cases.

tuneGrid <- expand.grid(
  cost = c(0.1, 1, 10),
  gamma = c(0.01, 0.1, 1)
)

# Perform tuning using cross-validation
set.seed(123)
tuneResult <- tune(
  svm,
  test_result ~ .,
  data = trainDataFull,
  kernel = "radial",
  ranges = list(cost = tuneGrid$cost, gamma = tuneGrid$gamma),
  class.weights = class_weights,
  probability = TRUE
)

# Best parameters
bestModel <- tuneResult$best.model
print(bestModel)
2

Is this using caret or e1071? There is a lot of detail not shown here and that would help.

The issue is probably that SVMs do not scale well with the number of rows in the data set.

3

Thanks for the response. Yes, I am using the library e1071.