Question 1

A college endowment office is using S3 data lake with structured and unstructured data to identify potential big donors. Many different data lake records refer to the same person, so fundraisers need to de-duplicate data before storing it and preparing for further processing. What is the easiest and most effective way to achieve that goal?

A Write a Python code for a custom de-duplication and run it on EMR cluster.
B Use AWS Glue Crawler to identify and eliminate duplicate people.
C Find a matching algorithm on AMI Marketplace.
D Store data in compressed JSON format. 

Answer: B

Question 2

A Machine Learning Engineer is tasked with developing a server less BI Dashboard on AWS that has ML methods build-in. What is the best AWS service he can choose?

A Google BI integrated with AWS Dash
B AWS Quick Sight
C AWS Tableau
D  Sage Maker Server less

Answer: B

Question 3

Mark is running a small print-on-demand (POD) business. This month he has been selling an average of 5 T-shirts per day. He is running low on inventory and he wants to calculate the probability that he will sell more than 10 T-shirts tomorrow. What probability distribution should he use for that calculation?

A Poisson distribution
B Normal (Gaussian) distribution
C Modified alpha distribution
D Student t-distribution

Answer: A

Question 4

The AWS Glue Data Catalog contains references to data that are used as sources and targets of extract, transform, and load (ETL) jobs in AWS Glue. To create a data warehouse or data lake, a user must catalog this data. One way to take inventory of the data in the data store is to run a Glue crawler. What is NOT the datastore a crawler can connect to?

A Amazon S3
B Amazon Redshift
C JDBC API
D Amazon Elasti Cache

Answer: D

Question 5

A Data Scientist is dealing with s binary classification problem with highly imbalanced classes in a 1:200 ratio. He wants to fit and evaluate a decision tree algorithm but does not expect it to perform very well on a raw unbalanced dataset. What are the two techniques he can use as data preparation? (Select TWO.)

A Transform Training Data with SMOTE
B Under-sample majority (normal) class.
C Use SVM (Support-Vector Machine) Algorithm.
D Normalize features of the majority class.
E Collect more data.

Answer: A,B

Question 6

A researcher in a hospital is building an ML model that ingests the dataset containing patients’ names, ages, medical record numbers, medical conditions, medications dosages and strengths, doctors’ notes, and other protected health information (PHI). The dataset will be stored on Amazon S3. What is the BEST way to securely store that data?

A Redact patients names and medical record numbers from the patients' data set with AWS Glue and use AWS KMS to encrypt the data on Amazon S3.
B Replace the medical record numbers with randomly generated integers.
C Use Data Encryption Standard (DES) to hash all PHI data.
D Store the data in Aurora Medical DB.

Answer: A

Question 7

A Machine Learning company intern was given a project to double the input data set used to train the model. While the previous model was performing well, with 90% accuracy, the updated model that used the expanded data set is performing much worse. What could be a possible explanation?

A Amazon has updated seq2seq algorithm.
B Expanded data set was not shuffled.
C New observations should have additional labels added.
D New observations should have been used just for validation purpose.

Answer: B

Question 8

A Data Scientist is using an ML regression model to fit the data set containing thousands of features. The training times are long and the costs are escalating. What can he do to improve training time?

A Use clustering to reduce the number of features.
B Do nothing, all features might be relevant.
C Remove uncorrelated features.
D Normalize all features.

Answer: A

Question 9

The optimal compromise (the most accurate in diagnosing the outcome) between sensitivity and specificity of the ROC curve is:

A The point nearest to the bottom right corner
B The intersection of the curve and specificity=1 line
C The point nearest to the top left corner (TP=1, TN=0)
D The point with sensitivity=1

Answer: C

Question 10

A Machine Learning Specialist is building an ML model using the EMR cluster. He would like to test the application on a cluster processing a small, but representative subset of his data. He would also like to enable the log file writing on the master node. What he has to do?

A Set Redirect Flag=1 on S3.
B Install YARN.
C SSH to Master Node and create /mnt/var/log directory.
D Nothing, logging is enabled by default.

Answer: D