Certbie
Question 1 of 30
A data scientist is tasked with developing a predictive model for customer churn in a subscription-based service using Automated Machine Learning (AutoML) on Azure. The dataset contains various features, including customer demographics, usage patterns, and previous interactions with customer service. After running the AutoML process, the data scientist notices that the model selected has a high accuracy but a low F1 score. What could be the most likely reason for this discrepancy, and how should the data scientist proceed to improve the model\'s performance?
The model may be overfitting to the training data, leading to high accuracy but poor generalization on unseen data, necessitating techniques like cross-validation or regularization.
The dataset is too small, which could lead to unreliable accuracy measurements, suggesting the need for more data collection.
The features used in the model are not relevant to the target variable, indicating a need for feature engineering or selection.
The AutoML process did not include enough algorithms, implying that the data scientist should manually add more algorithms to the pipeline.

Preparing for Microsoft DP-100 Designing and Implementing a Data Science Solution on Azure? Now land the interview.

73% of qualified candidates get rejected because of weak resumes. Build an ATS-optimized, recruiter-ready resume in under 5 minutes - free to start.

Build My Resume Free