You are a machine learning specialist at a large online retailer.
Your team is working on a recommender model for your online purchase workflow.
The recommender will suggest similar items to the items the user has viewed or placed in their shopping cart.
To find items that are similar to the item your customer is viewing, you want to compare other users who like each item.
If these similar users like the same two items, then the probability the items are similar is higher. Which Amazon SageMaker built-in algorithm is best suited to your use case?
Click on the arrows to vote for the correct answer
A. B. C. D.Answer: B.
Option A is incorrect.
The semantic segmentation algorithm is used to develop computer vision applications.
You are trying to find items that are similar to each other.
Option B is correct.
The k-nearest neighbor algorithm is used to find items that are similar to each other.
This is what you need to find similar items to recommend to a user in the online purchase workflow.
Option C is incorrect.
The linear learner algorithm is used to show how a change in an independent variable affects a dependent variable.
You are trying to find items that are similar to each other.
Option D is incorrect.
The random cut forest algorithm is predominantly used to classify observations, such as whether a transaction is fraudulent or not.
You are trying to find items that are similar to each other.
Reference:
Please see the Amazon SageMaker developer guide titled.
Use Amazon Sagemaker Built-in Algorithms.
The best Amazon SageMaker built-in algorithm for this use case is the K-Nearest Neighbor (KNN) algorithm.
KNN is a type of supervised learning algorithm used for classification and regression analysis. The algorithm finds the K-nearest points in the dataset that are closest to the data point in question.
In this case, KNN can be used to find similar users based on their purchase history. If two users have similar purchase histories, then the items they like will likely be similar. By finding these similar users, the recommender can suggest items that the current user might be interested in based on the preferences of these similar users.
KNN is a good choice for this use case because it can handle large datasets with high dimensionality. The algorithm is also easy to implement and interpret, making it ideal for use in a recommender system. Additionally, KNN can be used for both classification and regression tasks, which means it can be adapted to different types of recommendation systems.
In contrast, Semantic Segmentation is used for image recognition tasks, while Linear Learner is used for binary classification, multi-class classification, and regression tasks. Random Cut Forest is used for anomaly detection tasks. These algorithms are not well-suited for the recommender system use case described in the question.