Scribd Logo
Upload

Welcome to Scribd!

  • 2 views

    Model Cross Validation

    Uploaded by

    aryf TJ

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Model Cross Validation

    Uploaded by

    aryf TJ
    2 views11 pages

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    2 views11 pages

    Model Cross Validation

    Uploaded by

    aryf TJ

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 11

    WHAT ARE THE DIFFERENT METHODS OF

    MODEL CROSS-
    VALIDATION?

    www.benchmarksixsigma.com
    MEANING

    Model Cross Validation is a term


    used in Machine Learning to
    estimate the model's predictive
    accuracy when fed with real-life
    data.

    www.benchmarksixsigma.com
    COMMON METHODS OF
    VALIDATION TECHNIQUES:

    1) The Validation Set Approach


    (Data Split): In this approach, the
    data is randomly split into two
    sets. One set, 50% of the dataset,
    is used to train the model, and the
    remaining 50% is used to test the
    model.

    www.benchmarksixsigma.com
    2) Leave one out Cross Validation
    (LOOCV): In this approach, only
    one data point from the dataset is
    reserved, and the rest of the data is
    used to train the model to record
    the test error associated with the
    prediction. This process is repeated
    for every data point.

    www.benchmarksixsigma.com
    3) k-fold Cross Validation: The cons
    of the previous two approaches are
    addressed in this approach. Here the
    model performance on a different
    subset of the training data is
    evaluated, and the average
    prediction error rate is calculated.

    www.benchmarksixsigma.com
    4) Repeated k-fold Cross
    Validation: In this approach, the
    process of splitting the data into k
    folds can be repeated n times, thus
    resulting in n random partitions of
    the original sample. The results are
    then averaged to come up with a
    single estimation.

    www.benchmarksixsigma.com
    5)Stratified k-fold Cross
    Validation: In this approach, the
    data is rearranged to ensure that
    each fold is a good representation
    of the whole dataset.

    www.benchmarksixsigma.com
    6) Adversarial Validation: This
    approach generally checks the
    similarity between the test
    /validation and train sets
    regarding feature distribution. If
    there is not much similarity, then
    we can suspect that the datasets
    are quite different.

    www.benchmarksixsigma.com
    7) Cross Validation for Time Series:
    A time series dataset cannot be
    randomly split because the time
    section of the data will be messed
    up. For a time series forecasting
    problem, folds for time series cross-
    validation are created in a forward
    chaining fashion.

    www.benchmarksixsigma.com
    8) Custom Cross-Validation
    Techniques: No single method works
    best for all problem statements.
    Hence a custom cross-validation
    technique can be created based on
    a feature or combination of features
    that will give the user stable cross-
    validation scores.

    www.benchmarksixsigma.com
    Learn about Model building in our
    Business Modelling Expert
    program.

    +91 98113 70943

    www.benchmarksixsigma.com

    https://tinyurl.com/BSSinquire

    You might also like