An organization is training a machine learning model to predict extreme weather events in their country. How should they collect data to maximize prediction accuracy?

The correct answer is A. Collect all weather data evenly across all cities. Collecting ALL weather data (not just extreme events) EVENLY across ALL cities prevents training bias. A model needs to understand normal weather patterns as a baseline in order to correctly identify deviations that signal extreme events. Focusing only on at-risk cities or only o

Data Strategy for AI/ML

Question

Options

ACollect all weather data evenly across all cities
BCollect all weather data primarily from at-risk cities
CCollect extreme weather data evenly across all cities
DCollect extreme weather data primarily from at-risk cities

How the community answered

(37 responses)

A
70% (26)
B
16% (6)
C
11% (4)
D
3% (1)

Explanation

Collecting ALL weather data (not just extreme events) EVENLY across ALL cities prevents training bias. A model needs to understand normal weather patterns as a baseline in order to correctly identify deviations that signal extreme events. Focusing only on at-risk cities or only on extreme weather data would produce a biased, incomplete dataset, causing the model to fail to generalize and make accurate predictions across the entire country.

Topics

#Machine Learning Data#Data Collection Strategy#Predictive Modeling#Data Representativeness

Community Discussion

No community discussion yet for this question.

Full CLOUD-DIGITAL-LEADER Practice