Input:
- Dataset: CDFTM_Dataset; CDFTM_Validation_Dataset
- Parameters:
  - Min and Max values for each hyperparameter
  - Step size for each hyperparameter

Output:
- Best combination of hyperparameters (BestCombo)

Procedure:
1. Initialize the search space:
   - Define min, max, and step for each hyperparameter:
     - LeavesMin, LeavesMax, LeavesStep
     - MinExamplesMin, MinExamplesMax, MinExamplesStep
     - TreesMin, TreesMax, TreesStep
     - MaxBinsMin, MaxBinsMax, MaxBinsStep
     - FeatureFractionMin, FeatureFractionMax, FeatureFractionStep
     - LearningRateMin, LearningRateMax, LearningRateStep
	 - BestCombo

2. Set iteration counter t = 0

3. Define termination criteria:
   - Maximum number of iterations (MaxIterations)
 
4. Generate all possible hyperparameter combinations:
FOR leaf IN RANGE(LeavesMin, LeavesMax + LeavesStep, LeavesStep) DO
    FOR minExample IN RANGE(MinExamplesMin, MinExamplesMax + MinExamplesStep, MinExamplesStep) DO
        FOR tree IN RANGE(TreesMin, TreesMax + TreesStep, TreesStep) DO
            FOR maxBin IN RANGE(MaxBinsMin, MaxBinsMax + MaxBinsStep, MaxBinsStep) DO
                FOR featureFraction IN RANGE(FeatureFractionMin, FeatureFractionMax + FeatureFractionStep, FeatureFractionStep) DO
                    FOR learningRate IN RANGE(LearningRateMin, LearningRateMax + LearningRateStep, LearningRateStep) DO
                        t = t + 1
                        IF t > MaxIterations THEN
                            BREAK ALL LOOPS
                        END IF

                        // Create current hyperparameter combination
                        CURRENT_COMBO = HyperparameterCombo(
                            NumberOfLeaves = leaf,
                            MinimumExampleCountPerLeaf = minExample,
                            NumberOfTrees = tree,
                            MaximumBinCountPerFeature = maxBin,
                            FeatureFraction = ROUND(featureFraction, 4),
                            LearningRate = ROUND(learningRate, 4)
                        )

                        // Train and evaluate model with CURRENT_COMBO
                        MODEL = TrainModel(Dataset = CDFTM_Dataset, Hyperparameters = CURRENT_COMBO)
                        ACCURACY = EvaluateModel(Model = MODEL, ValidationDataset = CDFTM_Validation_Dataset)

                        // Update BestCombo if current accuracy is better
                        IF ACCURACY > BestAccuracy THEN
                            BestAccuracy = ACCURACY
                            BestCombo = CURRENT_COMBO
                        END IF
                    END FOR
                END FOR
            END FOR
        END FOR
    END FOR
END FOR

7. Return the best solution (BestCombo) from the final population