Alteryx Advanced - Exercise 4

This tutorial guides you through building an XGBoost classification model to predict airline passenger satisfaction. It covers data preparation, including setting data types, cleaning missing values, and feature selection. The lesson explains setting up a machine learning pipeline, applying transformation tools, and fitting the model. Finally, it evaluates the model's performance, highlighting prediction accuracy and error rates.

What is the primary goal of the XGBoost classification model discussed in the lesson?

• To optimize ticket pricing

• To analyze customer feedback

• To forecast flight delays

• To predict airline passenger satisfaction

Which tool is used to check and correct data types in the data preparation process?

• Transformation tool

• Predict tool

• Select tool and Auto field tool

• Classification tool

What is the purpose of setting the transformer to 'set data types' in the transformation tools?

• To increase data storage capacity

• To remove duplicate records

• To enhance data security

• To automatically recognize and assign correct data types

How are missing values in the 'Arrival Delay in minutes' field handled?

• By replacing them with zero

• By using the mean value

• By deleting the records

• By replacing them with the median value

Which features are selected for one-hot encoding?

• Airline name, flight duration, and baggage allowance

• Departure time, arrival time, gate location, and convenience

• Flight number, seat number, and ticket price

• Gender, customer type, type of travel, and class

What algorithm is chosen for the classification tool in the modeling process?

• XGBoost

• Random Forest

• Support Vector Machine

• K-Nearest Neighbors

What is the overall error rate of the model as mentioned in the results?

• More than 10%

• Between 5% and 10%

• Exactly 5%

• Less than 5%