Prepare and test your skills

Prepare and test your skills

Free sample question with answers and detailed explanation below. The Cloud Digital Leader practice bank has an additional 3,070 practice questions.Try 10 free realistic questions: instant score, no credit card, and no account required.
A financial services organization is developing a machine learning system to identify fraudulent transactions.
The project team established the following workflow requirements:
Which machine learning paradigm is used during model training, and which lifecycle stage represents generating predictions on new data?
Reinforcement learning (RL) is a machine learning paradigm where an autonomous software agent learns to make sequential decisions by taking actions in an environment to maximize cumulative numerical rewards. Data transformation is a data engineering step where raw inputs are cleaned, normalized, tokenized, or split into manageable representations before or during model ingestion.
This combination would be relevant if an autonomous trading agent was learning an optimal trading strategy via simulated market interactions while transforming incoming real-time ticker feeds into structured numerical vectors.
Unsupervised learning is a machine learning approach that discovers hidden patterns, groupings, or anomalous structures in datasets that do not contain pre-assigned labels or target outcomes. Hyperparameter tuning is an optimization process conducted during model development where automated trials test different training settings (such as learning rate or network depth) to maximize accuracy.
This option would be appropriate if the organization lacked labeled fraud records and needed an algorithm to cluster customer purchasing behaviors to detect unusual anomalies, and if the team needed to optimize learning rates prior to final deployment.
Generative AI refers to deep learning models trained on vast corpuses of unstructured content to produce novel outputs (such as natural language text, synthetic code, audio, or images) based on user prompts. Early stopping is a regularization technique applied during the training process that halts training iterations when validation loss begins to increase, preventing the model from overfitting.
This pairing would be applicable if an engineering team was training a large language model to draft automated customer support responses and wanted to stop gradient descent automatically as soon as validation loss stopped improving.
Supervised learning is a machine learning paradigm where an algorithm learns to map input features to correct target outputs by analyzing labeled training data (known as ground truth). Inference (or model serving) is the operational stage of the machine learning lifecycle where a trained model processes new, unseen live inputs to calculate and generate predictions.

Because the dataset includes known historical target labels (fraud vs. legitimate) and the production requirement is to calculate predictions on incoming records, supervised learning combined with inference perfectly satisfies both technical stages of the machine learning lifecycle.
Answer them yourself and get your score the moment you finish. No account needed.
Full access includes
Keep the momentum going with these hand-picked practice scenarios
Last updated Validated