Logo

Training into multiple chunks of Test-Validation Splits to get correct model accuracy, reducing overfits.

1. K - Fold CV

Break down Test-Validation Sets into "k" chunks.

Example: Pasted image 20240818141003.png

Here, Size of dataset (rows) = 500 If k = 5

Test size = (500/5) = 100

  1. Take 1st 100 rows as test, remaining as train
  2. Take 2nd 100 rows as test, remaining as train, and so on…
  • Finally take averages of model score accuracy of all Chunks / Folds
Note

In CVs, one model does not have the idea about the other -> to avoid overfitting, different models are used, and their accuracies are averaged.

2. Time Series CV

Pasted image 20240818142005.png

Acts on a Time Series Dataset

3. Grid Search CV

Pasted image 20240904171441.png

Trying out all possible combinations of hyper-parameters to train model & see which one suits the use case

4. Randomized CV

Pasted image 20240904171701.png

Iterate through random sets of hyper-parameters

Tip
  • Grid & Randomized CVs are used for Hyperparameters
  • K - Fold & Stratified K - Folds are used for Training

Hence, they can be combined and used

© 2025 All rights reservedBuilt with DataHub Cloud

Built with LogoDataHub Cloud