Exams / AIF-C01 / ML lifecycle, MLOps and metrics / Question 1
AIF-C01 practice question: ML lifecycle, MLOps and metrics (1 of 4)
Fundamentals of AI and ML A free question from our original AIF-C01 practice exam. Try it, then open the answer to see why each option is right or wrong.
A bank is building its first ML model to flag suspicious transactions. Put these ML pipeline stages in the order they normally happen, first stage first.
Put these 5 steps in order.
- AA. Train the model on the prepared training data
- BB. Collect historical transaction data and its outcomes
- CC. Deploy the model and monitor its predictions in production
- DD. Clean the data and engineer useful features
- EE. Evaluate the model against held-back test data
Show the answer and explanation
Correct order: B, D, A, E, C
- B. Collect historical transaction data and its outcomes First: every ML project starts by gathering the data the model will learn from.
- D. Clean the data and engineer useful features Second: raw data is cleaned, transformed and turned into features before any training happens.
- A. Train the model on the prepared training data Third: training needs data that has already been collected and prepared.
- E. Evaluate the model against held-back test data Fourth: the trained model is measured on data it has not seen before anyone decides to deploy it.
- C. Deploy the model and monitor its predictions in production Fifth: only an evaluated model is deployed, and monitoring then watches for drift and decides when to retrain.
Explanation
The ML pipeline runs from data collection, through data preparation and feature engineering, to training, evaluation, and then deployment with monitoring. Monitoring feeds back into the start of the pipeline when the model needs retraining, which is the loop that MLOps automates.
Study
Keep practising
Answer questions with a score at the end, or practise just this topic with the explanation after each one. No sign-up needed.