Answer-first summary for fast verification
Answer: Use product type and the feature cross of latitude with longitude, followed by binning, as features. Set profit as the model output.
This answer is correct because it effectively combines the necessary geographical context (through the feature cross of latitude and longitude with binning) and product type as inputs, focusing the model's output on profit. This approach enables the model to accurately assess the potential success of the new product line in various locations by directly predicting profitability, which is the ultimate goal of the analysis, while also considering scalability and compliance with data privacy regulations.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
As a data scientist for a multinational beverage company, you are tasked with developing a machine learning model to predict the profitability of a new line of natural flavored bottled waters across different regions. The historical data available includes product categories, sales, expenses, and profits for all regions. The model needs to consider geographical variations in consumer preferences and operational costs. Given the constraints of ensuring the model is scalable across regions and compliant with data privacy regulations, which of the following input and output configurations would best suit your model? Choose the best option.
A
Use product type along with the feature cross of latitude and longitude, followed by binning, as features. Set revenue and expenses as the model outputs.
B
Use latitude, longitude, and product type as features. Set profit as the model output.
C
Use product type and the feature cross of latitude with longitude, followed by binning, as features. Set profit as the model output.
D
Use latitude, longitude, and product type as features. Set revenue and expenses as the model outputs.
No comments yet.