RapidMiner Classification (Part 4): Holdout Validation скачать в хорошем качестве

RapidMiner Classification (Part 4): Holdout Validation

In this lesson you are going to learn how to validate the model in RapidMiner Studio using a "hold out" method, i.e. the available data is split into two parts - one used for the predictive model training and another for its validation (or testing). In the video we are trying to assess the realistic performance of the model. We also discuss the use of the stratified sampling - as opposed to shuffling - to ensure that both training and validation data have the same mix of labelled classes. We are continuing to work with workers compensation claims and trying to predict the possibility of claim subrogation, i.e. recovery of insurance payout due to the claim irregularities. At the end, the lessons experiments with different ways of splitting the data to highlight the unpredictability of the hold out method of model validation. This video is best to watch as part of the series on classification:    • RapidMiner Classification (Part 1): Introd...   The data for this lesson appeared in a number of tutorials for text mining. However, in this video it will be used to predict various aspects of workers compensation claims based on structured variables only. The data for the video can be obtained from: http://jacobcybulski.com/youtube-rsrc... http://jacobcybulski.com/youtube-rsrc... The original source of the data does not seem to be available online anymore. Videos in data analytics and data visualization by Jacob Cybulski, jacobcybulski.com.