Exam Cloud Digital Leader topic 1 question 85 discussion

My vote is for A. Collect all weather data evenly across all cities. Mainly because it seems that the emphasis for data collection for ML is to make sure there are no holes in your data collection.

For ML, its always good to have large amount of data ingest

A is correct

D is the correct answer as find in Google Gemini AI bot The best option for collecting data to maximize prediction accuracy for extreme weather events The goal is to train the model on data that closely resembles the real-world situations it will encounter when predicting extreme events.

Collect all weather data evenly across all citie

Collect all weather data evenly across all citie

D is correct

A is right. More relevant input training data for ML will help better predictions.

A is correct

D. Collect extreme weather data primarily from at-risk cities. To maximize the prediction accuracy of a machine learning model for extreme weather events, it is important to collect data from the locations and times where these events are most likely to occur. This can be done by identifying the cities and regions that are most at risk for extreme weather events, and then collecting data from those areas.

B is correct

By collecting extreme weather data primarily from at-risk cities, the organization can target areas where the occurrence of extreme weather events is higher. This approach allows the machine learning model to learn from data that is most relevant to the specific problem of predicting extreme weather events. It enables the model to capture the unique characteristics and patterns associated with extreme weather in those areas, leading to improved prediction accuracy.

3 / 3 The best approach to maximize prediction accuracy is to collect extreme weather data primarily from at-risk cities. This approach will allow the machine learning model to learn from data that is more relevant to the problem being solved. By focusing on at-risk cities, the model will have a better chance of accurately predicting extreme weather events, which is the goal of the project. Collecting extreme weather data evenly across all cities or collecting all weather data primarily from at-risk cities may not provide enough data for the model to accurately predict extreme weather events.

To maximize prediction accuracy, an organization training a machine learning model to predict extreme weather events in their country should collect extreme weather data primarily from at-risk cities (Option D). This is because collecting data evenly across all cities (Option A) or collecting all weather data primarily from at-risk cities (Option B) may not provide enough data on extreme weather events to train the model effectively. Collecting all extreme weather data evenly across all cities (Option C) may provide too much data on extreme weather events in areas that are not at risk, which could lead to overfitting of the model.

Definitely A or you skew the model

A is the correct answer for data completeness and coverage

To maximize prediction accuracy for extreme weather events, the organization should prioritize collecting data from at-risk cities. By the way, A is 'wrong', because collecting extreme weather data evenly across all cities doesn't make sense as this data is not evenly distributed and collecting all weather data primarily from at-risk cities will not provide enough data on extreme weather events.