What is the purpose of model inference in the machine learning model lifecycle?
To predict outcomes or make decisions based on new data
Explanation:
Model inference is the process of using a trained machine learning model to make predictions or decisions on new, unseen data.
Example:
- A spam filter uses inference to decide whether a new email is spam or not spam.
- A loan model uses inference to predict whether a new applicant is likely to repay a loan.
Why not the others?
- a) To evaluate the model’s accuracy → This is part of the evaluation phase.
- b) To tune the model for better performance → This is part of model optimization/training.
- d) To train the model from scratch → Training happens before inference.
