You've built an ML pipeline which trains a regression model to predict inventory levels for the next month.
You have completed several runs and you need to decide which of them gives the best performance.
You use the output of the Evaluate model designer module, i.e.: Mean Absolute Error (MAE) Root Mean Squared Error (RMSE) Coefficient of Determination You select the run as best performer, for which...
Click on the arrows to vote for the correct answer
A. B. C. D.Answer: D.
Option A is incorrect because for Coefficient of Determination, the higher values are favorable.
Option B is incorrect because the value of metrics representing the size of the error (MA, RMSE) should be as low as possible.
Option C is incorrect because the value of metrics representing the size of the error (MA, RMSE) should be as low as possible.
Option D is CORRECT because MAE and RMSE both measure how close the model's predicted values are to the actual results.
The lower these values the better.
Coefficient of Determination shows “how powerful” the model is, in terms of predictions.
Higher values (close to 1) represent higher predicting power..
Reference:
The best performer run will be the one for which the evaluation metrics are the lowest (for MAE and RMSE) and highest (for Coefficient of Determination), respectively.
Mean Absolute Error (MAE) is a metric that measures the average absolute difference between the actual and predicted values. It is calculated by taking the sum of the absolute differences between the actual and predicted values and dividing by the number of samples. A lower MAE indicates better performance.
Root Mean Squared Error (RMSE) is a metric that measures the square root of the average squared difference between the actual and predicted values. It is calculated by taking the square root of the sum of the squared differences between the actual and predicted values divided by the number of samples. Like MAE, a lower RMSE also indicates better performance.
Coefficient of Determination (also known as R-squared) is a metric that measures the proportion of the variance in the target variable that is predictable from the independent variables. It ranges from 0 to 1, where 1 indicates that the model can perfectly predict the target variable, and 0 indicates that the model cannot predict the target variable at all. A higher Coefficient of Determination indicates better performance.
So, option D is the correct answer as it states that the best performer run is the one with low MAE, low RMSE, and high Coefficient of Determination, indicating that the model has accurately predicted the inventory levels.