There are many different types of statistical tests that can be used to understand the predictive accuracy of a model. This is done by comparing the results of the model to the data in the dataset to see the deviation in the results. These tests can be based on the tests we are using to predict the data and the data type used. One of these tests that is often used to calculate the predictive accuracy of a model are r, r2, MSE, and RMSE (Li, 2017). These evaluation types are recommended for numeric data that has a linear such as sales or inventory predictions. When looking for non-numeric or categorical analysis we would want to use a tool like a confusion matrix to find the accuracy of the model being used. When it comes to having a unbiased forecast I believe that there are two factors that come into view to help us obtain this goal. The first is to make sure that we are using the right type of tool to ensure that the models that we are using have a high degree of predictability and also to make sure that we are not using a model because they fit our agenda and make the project seem better for the needs of the analysis but providing the best possible information to decision-makers.
Uploaded by MinisterStrawRedPanda22 on coursehero.com