diff --git a/dashboard/R/fit_model.R b/dashboard/R/fit_model.R
index 0703f3b..8d7487d 100644
--- a/dashboard/R/fit_model.R
+++ b/dashboard/R/fit_model.R
@@ -365,10 +365,9 @@ update_tune_model_parameters <- function(method, params) {
     }
   }
 
-  # rimappare il parametro tune_elanet
-
-  mth_params <- getOption("tsf.dashboard.methods_params")[["Elastic Net"]]
-  tune_params <- clean_chr_inv(params$tune_elanet)
+  mth_params <- getOption("tsf.dashboard.methods_params")[[method]]
+  prm_name <- grep("_xx_", names(params), value = TRUE)
+  tune_params <- clean_chr_inv(params[[prm_name]])
   is_to_tune <- mth_params %in% tune_params
   params_list <- map2(mth_params, is_to_tune, get_tune) |> set_names(mth_params)
   update_params <- c(params, params_list)
@@ -521,7 +520,7 @@ fit_model_tuning <- function(
   # grid_spec <- generate_grid_spec(method, model_spec, grid_size, seed)
 
   # tuning
-  if (n_folds > 10 | grid_size > 25) {
+  if (n_folds > 20 | grid_size > 25) {
     doFuture::registerDoFuture()
     future::plan(strategy = "multisession", workers = parallelly::availableCores() - 1)
     message("Number of parallel workers: ", future::nbrOfWorkers())
@@ -531,7 +530,7 @@ fit_model_tuning <- function(
       resamples = cv_splits,
       grid = params$grid_size, # grid_spec
       metrics = modeltime::default_forecast_accuracy_metric_set(),
-      control = tune::control_grid(save_pred = FALSE)
+      control = tune::control_grid(save_pred = FALSE, allow_par = TRUE)
     )
   future::plan(strategy = "sequential")
 
diff --git a/dashboard/R/generate_forecast.R b/dashboard/R/generate_forecast.R
index a68e237..7af535c 100644
--- a/dashboard/R/generate_forecast.R
+++ b/dashboard/R/generate_forecast.R
@@ -4,14 +4,12 @@ generate_forecast <- function(
     ensemble_method = NULL
   ) {
 
-  splits <- timetk::time_series_split(
-    data, date_var = date,
-    initial = nrow(data) - n_assess,
-    assess = n_assess,
-    cumulative = ifelse(assess_type == "Expanding", TRUE, FALSE)
-  )
+  # initial split
+  splits <- generate_initial_split(data, n_assess, assess_type)
   train_tbl <- training(splits) |> select(-id, -frequency)
   test_tbl <- testing(splits) |> select(-id, -frequency)
+
+  # future split
   future_tbl <- future_frame(data, .date_var = date, .length_out = n_future)
 
   # model summary
diff --git a/dashboard/test.R b/dashboard/test.R
index c9ae0fa..2350374 100644
--- a/dashboard/test.R
+++ b/dashboard/test.R
@@ -209,7 +209,7 @@ input <- list(
   n_folds = 5,
   metric = "RMSE",
   grid_size = 10,
-  tune_rf = c("rf_mtry")
+  tune_xx_rf = c("rf_mtry")
 )
 
 data = data_selected
diff --git a/dashboard/todo.txt b/dashboard/todo.txt
index 2d41675..321778d 100644
--- a/dashboard/todo.txt
+++ b/dashboard/todo.txt
@@ -11,8 +11,10 @@ Next steps:
 - documentazione in alto a destra
 
 To Do:
-- rimappare tune_elanet ecc
+- aggiungere rbf_sigma conditional su svm_rbf
 - finire update_tune_model_parameters con mapping parametri (occhio, non mtry ma rf_mtry)
+- testare flusso optimize fino al forecast
+- change split in generate_forecast
 - fare la funzione parse_parameters per ottenere i nomi da mostrare in UI dal parametro
 
 - aggiungere metodi di automl (h2o)
diff --git a/dashboard/tsf_dashboard.Rmd b/dashboard/tsf_dashboard.Rmd
index e1df624..869d178 100644
--- a/dashboard/tsf_dashboard.Rmd
+++ b/dashboard/tsf_dashboard.Rmd
@@ -1107,7 +1107,7 @@ conditionalPanel(
   condition = "input.tune_method == 'Elastic Net'",
   h5("Algorithm hyperparameters to optimize: "),
   pickerInput(
-    inputId = "tune_elanet", label = NULL, 
+    inputId = "tune_xx_elanet", label = NULL, # _xx_ need to recognize it easily in update_tune_model_parameters()
     choices = methods_params_cl[["Elastic Net"]], multiple = TRUE, 
     selected = methods_params_cl[["Elastic Net"]][2],
     options = list("actions-box" = TRUE)