Exam AI-900 topic 1 question 26 discussion

Actual exam question from Microsoft's AI-900

Question #: 26
Topic #: 1

DRAG DROP -
Match the machine learning tasks to the appropriate scenarios.
To answer, drag the appropriate task from the column on the left to its scenario on the right. Each task may be used once, more than once, or not at all.
NOTE: Each correct selection is worth one point.
Select and Place:

Show Suggested Answer

Suggested Answer:

Box 1: Model evaluation -
The Model evaluation module outputs a confusion matrix showing the number of true positives, false negatives, false positives, and true negatives, as well as
ROC, Precision/Recall, and Lift curves.

Box 2: Feature engineering -
Feature engineering is the process of using domain knowledge of the data to create features that help ML algorithms learn better. In Azure Machine Learning, scaling and normalization techniques are applied to facilitate feature engineering. Collectively, these techniques and feature engineering are referred to as featurization.
Note: Often, features are created from raw data through a process of feature engineering. For example, a time stamp in itself might not be useful for modeling until the information is transformed into units of days, months, or categories that are relevant to the problem, such as holiday versus working day.

Box 3: Feature selection -
In machine learning and statistics, feature selection is the process of selecting a subset of relevant, useful features to use in building an analytical model. Feature selection helps narrow the field of data to the most valuable inputs. Narrowing the field of data helps reduce noise and improve training performance.
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/studio/evaluate-model-performance https://docs.microsoft.com/en-us/azure/machine-learning/concept-automated-ml

by ipindado2020 at Dec. 2, 2020, 8:38 p.m.

Comments

Submit Cancel

idioteque

Highly Voted 3 years ago

For me to remember again xD Model Evalution = values Feature engineering = splitting Feature selection = picking

upvoted 46 times

...

ipindado2020

Highly Voted 4 years, 8 months ago

answer is correct

upvoted 23 times

...

saema

Most Recent 7 months ago

model evaluation model training feature selection

upvoted 1 times

...

gina_the_boss

1 year, 1 month ago

doesn't look like anyone in this thread had this question in their test?

upvoted 1 times

...

MNotABot

1 year, 5 months ago

Examining = Evaluation Spliting = new Features = Feature Engineering Picking = Selection = Feature Selection

upvoted 11 times

...

Bouncy

1 year, 5 months ago

Maybe these examples help understanding the different concepts: Feature Engineering Example: If you have data about a house's width and length, you could create a new feature called "area" by multiplying the width and length together. This new feature provides additional valuable information that can help the model make better predictions. Feature Selection Example: If you have a list of features such as house width, length, height, and color, feature selection helps you identify which features have the most impact on predicting the house price. By selecting only the key features (e.g., width and length) and discarding less important ones (e.g., height and color), you reduce the complexity of the model without losing predictive power.

upvoted 12 times

gina_the_boss

1 year, 1 month ago

this is helpful. thanks

upvoted 1 times

...

zellck

2 years, 1 month ago

1. Model evaluation 2. Feature engineering 3. Feature selection https://learn.microsoft.com/en-us/azure/machine-learning/how-to-configure-auto-features?view=azureml-api-1#feature-engineering-and-featurization Although many of the raw data fields can be used directly to train a model, it's often necessary to create additional (engineered) features that provide information that better differentiates patterns in the data. This process is called feature engineering, where the use of domain knowledge of the data is leveraged to create features that, in turn, help machine learning algorithms to learn better.

upvoted 3 times

zellck

2 years, 1 month ago

https://learn.microsoft.com/en-us/azure/architecture/data-science-process/select-features - feature engineering: This process attempts to create additional relevant features from the existing raw features in the data, and to increase predictive power to the learning algorithm. - feature selection: This process selects the key subset of original data features in an attempt to reduce the dimensionality of the training problem.

upvoted 2 times

...