Professional Machine Learning Engineer

Question

You work for a retail company and have been asked to develop a model that predicts whether a customer will buy a product on a particular day. Your team has processed the company’s sales data and created a table with these rows:

Customer_id
Product_id
Date
Days_since_last_purchase (measured in days)
Average_purchase_frequency (measured in 1/days)
Purchase (binary class, indicating whether the customer purchased the product on the Date)

You need to interpret your model’s results for every individual prediction. What should you do?

Explanation

Vertex AI Explainable AI returns feature-attribution values for each prediction instance. An AutoML tabular classification model deployed to a Vertex AI endpoint can use the explain operation to provide local feature attributions that show how each feature contributed to an individual purchase prediction.

Learn more

Professional Machine Learning Engineer

AstroTutor

Notes

Readiness

QuestionQ32

Community Discussion