Question-8: You are working with a giant retail bank which has issued various credit cards to the customer in the united states, and you are monitoring each transaction to find the fraudulent activity on the credit card. You are having one of the variable which is received as part of the transaction data, which represent the date time when this transaction was done. However, this date-time can never happen and has unique values for all the transactions made by an individual customer. Do you thing this variable can be useful for Machine Learning?
- No, being a unique value for each individual customer it does not have any meaning for predictions.
- No, we should not use it because it un-necessarily put the model in the out of memory issue.
- Get Latest Certification Questions & Answer from this link, which is regularly updated as per recent syllabus.
- All AWS Certification & Training Material Can be accessed from this link as well.
Feature engineering: Before applying any machine learning algorithm, you might want to pre-process the data and a particular variable you want to make it more meaningful. And the process is known as feature processing or feature engineering. For example, say you have a variable that captures the date and time at which an event occurred. This date and time will never occur again and hence won’t be useful to predict your target. However, if this variable is transformed into features that represent the hour of the day, the day of the week, and the month, these variables could be useful to learn if the event tends to happen at a particular hour, weekday, or month. Such feature processing to form more generalizable data points to learn from can provide significant improvements to the predictive models.