Exam AWS Certified Machine Learning - Specialty topic 1 question 12 discussion

B seems to be okay

CLASSIFICATION - Binary Classification - Supervised Learning to be precise The company wants to predict customer churn (whether a customer will leave or stay). The data is labeled, meaning we have historical outcomes (churn or no churn). The task involves categorizing customers into two groups: Customers who will churn (leave) Customers who will not churn (stay) This means the problem is a Supervised Learning problem, specifically a binary classification problem. The company wants to predict customer churn (whether a customer will leave or stay). The data is labeled, meaning we have historical outcomes (churn or no churn). The task involves categorizing customers into two groups: Customers who will churn (leave) Customers who will not churn (stay) This means the problem is a Supervised Learning problem, specifically a binary classification problem.

The reason for this choice is that classification is a type of supervised learning that predicts a discrete categorical value, such as yes or no, spam or not spam, or churn or not churn1. Classification models are trained using labeled data, which means that the input data has a known target attribute that indicates the correct class for each instance2. For example, a classification model that predicts customer churn would use data that has a label indicating whether the customer churned or not in the past. Classification models can be used for various applications, such as sentiment analysis, image recognition, fraud detection, and customer segmentation2. Classification models can also handle both binary and multiclass problems, depending on the number of possible classes in the target attribute3.

Option B. This is a scenario for supervised learning model as data is labelled and only A, B are supervised learning algorithms from the options. Linear learning is to predict time series data and distribution is selecting which class the input belongs to. Hence most suitable is to use Binomial distribution model in this case.

A. NO - Linear regression is not best for classification B. YES - Classification C. NO - we want supervised classification D. NO - there is nothing to Reinforce from

The question is not clear. Actually we have 2 tasks here - group into categories (clustering) and predict if customers will churn/not churn (classification). If we had to simply do classification, why there was mentioned to group into categories?

This is definitely a classification problem

B is correct

B - it's a Binary Classification problem. Will the customer churn: Yes or No

100% is B since it is about labelled data

i think the key is "the company has labeled the data" so this is classification, so it's B

B is okey

B is correct