Question

The accuracy is simply how good your machine learning model is at predicting a correct class for a given observation. You build the model with training data and validate with the test date. What are scenarios which have lower training accuracy as well as low test accuracy learned as ?

Answer 1

Answer:

By definition, when training accuracy (or whatever metric you are using) is higher than your testing you have an overfit model.

Explanation:

HOPE IT WILL HELP YOU PLEASE MARK ME AS BRAINLIEST

Answer 2

The accuracy is simply how good your machine learning model is at predicting a correct class for a given observation. You build the model with training data and validate with the test date scenarios which have lower training accuracy as well as low test accuracy learned as.

• An accuracy of up to 89% utilising just the top candidate was achieved when we evaluated a trained model using the generated test dataset.
• Once a machine learning model has been trained and the training accuracy has been determined, there is a significant likelihood that the accuracy will yield a high range, likely in the nineties or even 100%.
• Low test and training accuracy is referred to as high bias high variance.
• Even when the model is unable to forecast any crashes, it is 90% accurate. 90% of landings were safe, according to data. Accuracy therefore does not hold true for unbalanced data. Since most data in commercial settings won't be balanced, accuracy becomes a poor indicator of our classification model's performance.
• Low test and training accuracy is referred to as high bias high variance.
• Even when the model is unable to forecast any crashes, it is 90% accurate. 90% of landings were safe, according to data. Accuracy therefore does not hold true for unbalanced data. Since most data in commercial settings won't be balanced, accuracy becomes a poor indicator of our classification model's performance.
• When a model's accuracy on testing data is lower than its accuracy on training or validation data, it typically means that there are significant discrepancies between the training data and the testing data being used for evaluation.

#SPJ2