DP-100 Dumps & Test Certification  DP-100 Cost
                      
 
Micros oft
DP-10 0
Designing and Implementing a Da ta Science Solution on Azure
 
 
 
 
 
 
 
 
Case Study 
Overview 
You are a data scientist in a company that provides data science for professional sporting 
events. Models will be global and local market data to meet the following business goals: 
•Understand sentiment of mobile device users at sporting events based on audio from crowd 
reactions. 
•Access a user's tendency to respond to an advertisement. 
•Customize styles of ads served on mobile devices. 
•Use video to detect penalty events. 
Current environment 
Requirements 
•   Media used for penalty event detection will be provided by consumer devices. Media may 
include images and videos captured during the sporting event and snared using social media. 
The images and videos will have varying sizes and formats. 
• The data available for model building comprises of seven years of sporting event media. The 
sporting event media includes: recorded videos, transcripts of radio commentary, and logs from 
related social media feeds feeds captured during the sporting events. 
•Crowd sentiment will include audio recordings submitted by event attendees in both mono 
and stereo 
Formats. 
Advertisements 
•   Ad response models must be trained at the beginning of each event and applied during the 
sporting event. 
•   Market segmentation nxxlels must optimize for similar ad resporr.r history. 
•   Sampling must guarantee mutual and collective exclusivity local and global segmentation 
models that share the same features. 
•   Local market segmentation models will be applied before determining a user’s propensity to 
respond to an advertisement. 
•   Data scientists must be able to detect model degradation and decay. 
 
•   Ad response models must support non linear boundaries features. 
•   The ad propensity model uses a cut threshold is 0.45 and retrains occur if weighted Kappa 
deviates from 0.1 +/-5%. 
•   The ad propensity model uses cost factors shown in the following diagram: 
 
 
The ad propensity model uses proposed cost factors shown in the following diagram: 
 
 
Performance curves of current and proposed cost factor scenarios are shown in the following 
diagram: 
 
 
 
Penalty detection and sentiment 
Findings 
•Data scientists must build an intelligent solution by using multiple machine learning models 
for penalty event detection. 
•Data scientists must build notebooks in a local environment using automatic feature 
engineering and model building in machine learning pipelines. 
•Notebooks must be deployed to retrain by using Spark instances with dynamic worker 
allocation 
•Notebooks must execute with the same code on new Spark instances to recode only the 
source of the data. 
•Global penalty detection models must be trained by using dynamic runtime graph 
computation during training. 
•Local penalty detection models must be written by using BrainScript. 
•   Experiments for local crowd sentiment models must combine local penalty detection data. 
•   Crowd sentiment models must identify known sounds such as cheers and known catch 
phrases. Individual crowd sentiment models will detect similar sounds. 
•   All shared features for local models are continuous variables. 
•   Shared features must use double precision. Subsequent layers must have aggregate running 
mean and standard deviation metrics Available. 
segments 
 
During the initial weeks in production, the following was observed: 
•Ad response rates declined. 
•Drops were not consistent across ad styles. 
•The distribution of features across training and production data are not consistent. 
Analysis shows that of the 100 numeric features on user location and behavior, the 47 features 
that come from location sources are being used as raw features. A suggested experiment to 
remedy the bias and variance issue is to engineer 10 linearly uncorrected features. 
Penalty detection and sentiment 
•Initial data discovery shows a wide range of densities of target states in training data used for 
crowd sentiment models. 
•All penalty detection models show inference phases using a Stochastic Gradient Descent (SGD) 
are running too stow. 
•Audio samples show that the length of a catch phrase varies between 25%-47%, depending on 
region. 
•The performance of the global penalty detection models show lower variance but higher bias 
when comparing training and validation sets. Before implementing any feature changes, you 
must confirm the bias and variance using all training and validation cases. 
 
Question: 1 
   
You need to resolve the local machine learning pipeline performance issue. What should you do? 
 
A. Increase Graphic Processing Units (GPUs). 
B. Increase the learning rate. 
C. Increase the training iterations, 
D. Increase Central Processing Units (CPUs). 
 
Answer: A     
 
Question: 2 
   
DRAG DROP 
 
You need to modify the inputs for the global penalty event model to address the bias and variance issue. 
Which three actions should you perform in sequence? To answer, move the appropriate actions from 
the list of actions to the answer area and arrange them in the correct order. 
 
Answer:  
Select the Location data 
Select the Behavior data 
Performa a primary component Analysis (PCA) 
Adda K-Means clustering module with 10 clusters. 
Bin the New data 
Build ratios. 
 
Question: 3 
You need to select an environment that will meet the business and data requirements. 
Which environment should you use? 
 
A. Azure HDInsight with Spark MLlib 
B. Azure Cognitive Services 
C. Azure Machine Learning Studio 
D. Microsoft Machine Learning Server 
 
Answer: D     
 
Question: 4 
   
HOTSPOT 
You are using C-Support Vector classification to do a multi-class classification with an unbalanced 
training dataset. The C-Support Vector classification using Python code shown below: 
 
 
You need to evaluate the C-Support Vector classification code. 
Which evaluation statement should you use? To answer, select the appropriate options in the answer 
area. 
NOTE: Each correct selection is worth one point. 
 
 
Answer:      
 
 
Explanation:  
Box 1: Automatically adjust weights inversely proportional to class frequencies in the input data 
The “balanced” mode uses the values of y to automatically adjust weights inversely proportional to class 
frequencies in the input data as n_samples / (n_classes * np.bincount(y)). 
Box 2: Penalty parameter 
Parameter: C : float, optional (default=1.0) 
Penalty parameter C of the error term. 
References: 
https://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html 
 
Question: 5 
 
   
DRAG DROP 
You need to define a process for penalty event detection. 
Which three actions should you perform in sequence? To answer, move the appropriate actions from 
the list of actions to the answer area and arrange them in the correct order. 
 
Answer:  
 
 
Question: 6 
DRAG DROP 
You need to define an evaluation strategy for the crowd sentiment models. 
Which three actions should you perform in sequence? To answer, move the appropriate actions from 
the list of actions to the answer area and arrange them in the correct order. 
 
 
Answer:  
 
Explanation:  
Scenario:  
Experiments for local crowd sentiment models must combine local penalty detection data. 
Crowd sentiment models must identify known sounds such as cheers and known catch phrases. 
Individual crowd sentiment models will detect similar sounds. 
Note: Evaluate the changed in correlation between model error rate and centroid distance 
In machine learning, a nearest centroid classifier or nearest prototype classifier is a classification model 
that assigns to observations the label of the class of training samples whose mean (centroid) is closest to 
the observation. 
References:  
https://en.wikipedia.org/wiki/Nearest_centroid_classifier 
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/sweep-clustering 
 
Question: 7 
HOTSPOT 
You need to build a feature extraction strategy for the local models. 
 
How should you complete the code segment? To answer, select the appropriate options in the answer 
area. 
NOTE: Each correct selection is worth one point. 
 
 
Answer:      
 
 
 
Question: 8 
   
You need to implement a scaling strategy for the local penalty detection data. 
Which normalization type should you use? 
A. Streaming 
 
B. Weight 
C. Batch 
D. Cosine 
 
Answer: C     
 
Explanation:  
Post batch normalization statistics (PBN) is the Microsoft Cognitive Toolkit (CNTK) version of how to 
evaluate the population mean and variance of Batch Normalization which could be used in inference 
Original Paper. 
In CNTK, custom networks are defined using the BrainScriptNetworkBuilder and described in the CNTK 
network description language "BrainScript." 
Scenario: 
Local penalty detection models must be written by using BrainScript. 
References: 
https://docs.microsoft.com/en-us/cognitive-toolkit/post-batch-normalization-statistics 
 
Question: 9 
   
HOTSPOT 
You need to use the Python language to build a sampling strategy for the global penalty detection 
models. 
How should you complete the code segment? To answer, select the appropriate options in the answer 
area. 
NOTE: Each correct selection is worth one point. 
 
 
 
Answer:      
 
 
 
Explanation: 
Box 1: import pytorch as deeplearninglib 
Box 2: ..DistributedSampler(Sampler).. 
DistributedSampler(Sampler): 
Sampler that restricts data loading to a subset of the dataset. 
It is especially useful in conjunction with class:`torch.nn.parallel.DistributedDataParallel`. In such case, 
each process can pass a DistributedSampler instance as a DataLoader sampler, and load a subset of the 
original dataset that is exclusive to it. 
Scenario: Sampling must guarantee mutual and collective exclusively between local and global 
segmentation models that share the same features. 
Box 3: optimizer = deeplearninglib.train. GradientDescentOptimizer(learning_rate=0.10) 
Incorrect Answers: ..SGD.. 
Scenario: All penalty detection models show inference phases using a Stochastic Gradient Descent (SGD) 
are running too slow. 
Box 4: .. nn.parallel.DistributedDataParallel.. 
DistributedSampler(Sampler): The sampler that restricts data loading to a subset of the dataset. 
    It is especially useful in conjunction with :class:`torch.nn.parallel.DistributedDataParallel`. 
References: 
https://github.com/pytorch/pytorch/blob/master/torch/utils/data/distributed.py 
 
 
Question: 10 
   
You need to implement a feature engineering strategy for the crowd sentiment local models. 
What should you do? 
 
A. Apply an analysis of variance (ANOVA). 
B. Apply a Pearson correlation coefficient. 
C. Apply a Spearman correlation coefficient. 
D. Apply a linear discriminant analysis. 
 
Answer: D     
 
Explanation:  
The linear discriminant analysis method works only on continuous variables, not categorical or ordinal 
variables.  
Linear discriminant analysis is similar to analysis of variance (ANOVA) in that it works by comparing the 
means of the variables. 
Scenario:  
Data scientists must build notebooks in a local environment using automatic feature engineering and 
model building in machine learning pipelines. 
Experiments for local crowd sentiment models must combine local penalty detection data. 
All shared features for local models are continuous variables. 
Incorrect Answers: 
B: The Pearson correlation coefficient, sometimes called Pearson’s R test, is a statistical value that 
measures the linear relationship between two variables. By examining the coefficient values, you can 
infer something about the strength of the relationship between the two variables, and whether they are 
positively correlated or negatively correlated. 
C: Spearman’s correlation coefficient is designed for use with non-parametric and non-normally 
distributed data. Spearman's coefficient is a nonparametric measure of statistical dependence between 
two variables, and is sometimes denoted by the Greek letter rho. The Spearman’s coefficient expresses 
the degree to which two variables are monotonically related. It is also called Spearman rank correlation, 
because it can be used with ordinal variables. 
References:  
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/fisher-linear-
discriminant-analysis 
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/compute-linear-
correlation 
 
Question: 11 
   
DRAG DROP 
You need to define a modeling strategy for ad response. 
Which three actions should you perform in sequence? To answer, move the appropriate actions from 
the list of actions to the answer area and arrange them in the correct order. 
 
 
Answer:  
 
Explanation:  
Step 1: Implement a K-Means Clustering model 
Step 2: Use the cluster as a feature in a Decision jungle model. 
Decision jungles are non-parametric models, which can represent non-linear decision boundaries. 
Step 3: Use the raw score as a feature in a Score Matchbox Recommender model 
The goal of creating a recommendation system is to recommend one or more "items" to "users" of the 
system. Examples of an item could be a movie, restaurant, book, or song. A user could be a person, 
group of persons, or other entity with item preferences. 
Scenario: 
Ad response rated declined. 
Ad response models must be trained at the beginning of each event and applied during the sporting 
event. 
Market segmentation models must optimize for similar ad response history. 
Ad response models must support non-linear boundaries of features. 
References:  
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/multiclass-
decision-jungle 
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/score-matchbox-
recommender 
 
 
Question: 12 
DRAG DROP 
You need to define an evaluation strategy for the crowd sentiment models. 
Which three actions should you perform in sequence? To answer, move the appropriate actions from 
the list of actions to the answer area and arrange them in the correct order. 
 
Answer:  
 
Explanation:  
Step 1: Define a cross-entropy function activation 
When using a neural network to perform classification and prediction, it is usually better to use cross-
entropy error than classification error, and somewhat better to use cross-entropy error than mean 
squared error to evaluate the quality of the neural network. 
Step 2: Add cost functions for each target state. 
Step 3: Evaluated the distance error metric. 
References: 
https://www.analyticsvidhya.com/blog/2018/04/fundamentals-deep-learning-regularization-
techniques/ 
 
Question: 13 
You need to implement a model development strategy to determine a user’s tendency to respond to 
anad. 
 
Which technique should you use? 
 
 
A. Use a Relative Expression Split module to partition the data based on centroid distance. 
B. Use a Relative Expression Split module to partition the data based on distance travelled to the event. 
C. Use a Split Rows module to partition the data based on distance travelled to the event. 
D. Use a Split Rows module to partition the data based on centroid distance. 
 
Answer: A     
 
Explanation:  
Split Data partitions the rows of a dataset into two distinct sets. 
The Relative Expression Split option in the Split Data module of Azure Machine Learning Studio is helpful 
when you need to divide a dataset into training and testing datasets using a numerical expression. 
Relative Expression Split: Use this option whenever you want to apply a condition to a number column. 
The number could be a date/time field, a column containing age or dollar amounts, or even a 
percentage. For example, you might want to divide your data set depending on the cost of the items, 
group people by age ranges, or separate data by a calendar date. 
Scenario:  
Local market segmentation models will be applied before determining a user’s propensity to respond to 
an advertisement. 
The distribution of features across training and production data are not consistent 
References: 
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/split-data 
 
Question: 14 
   
You need to implement a new cost factor scenario for the ad response models as illustrated in the 
performance curve exhibit. 
Which technique should you use? 
 
A. Set the threshold to 0.5 and retrain if weighted Kappa deviates +/- 5% from 0.45. 
B. Set the threshold to 0.05 and retrain if weighted Kappa deviates +/- 5% from 0.5. 
C. Set the threshold to 0.2 and retrain if weighted Kappa deviates +/- 5% from 0.6. 
D. Set the threshold to 0.75 and retrain if weighted Kappa deviates +/- 5% from 0.15. 
 
Answer: A     
 
Explanation:  
Scenario:  
Performance curves of current and proposed cost factor scenarios are shown in the following diagram: 
 
 
The ad propensity model uses a cut threshold is 0.45 and retrains occur if weighted Kappa deviated from 
0.1 +/- 5%. 
Case Study 
Overview 
You are a data scientist for Fabrikam Residences, a company specializing in quality private and 
commercial property in the United States. Fabrikam Residences is considering expanding into 
Europe and has asked you to investigate prices for private residences in major European cities. 
You use Azure Machine Learning Studio to measure the median value of properties. You 
produce a regression model to predict property prices by using the Linear Regression and 
Bayesian Linear Regression modules. 
Datasets 
There are two datasets in CSV format that contain property details for two cities, London and 
Paris, with the following columns: 
 
The two datasets have been added to Azure Machine Learning Studio as separate datasets and 
included as the starting point of the experiment. 
Dataset issues 
 
The AccessibilityToHighway column in both datasets contains missing values. The missing data 
must be replaced with new data so that it is modeled conditionally using the other variables in 
the data before filling in the missing values. 
Columns in each dataset contain missing and null values. The dataset also contains many 
outliers. The Age column has a high proportion of outliers. You need to remove the rows that 
have outliers in the Age column. The MedianValue and AvgRoomsinHouse columns both hold 
data in numeric format. You need to select a feature selection algorithm to analyze the 
relationship between the two columns in more detail. 
Model fit 
The model shows signs of overfitting. You need to produce a more refined regression model 
that reduces the overfitting. 
Experiment requirements 
You must set up the experiment to cross-validate the Linear Regression and Bayesian Linear 
Regression modules to evaluate performance. 
In each case, the predictor of the dataset is the column named MedianValue. An initial 
investigation showed that the datasets are identical in structure apart from the MedianValue 
column. The smaller Paris dataset contains the MedianValue in text format, whereas the larger 
London dataset contains the MedianValue in numerical format. You must ensure that the 
datatype of the MedianValue column of the Paris dataset matches the structure of the London 
dataset. 
You must prioritize the columns of data for predicting the outcome. You must use non-
parameters statistics to measure the relationships. 
You must use a feature selection algorithm to analyze the relationship between the 
MedianValue and AvgRoomsinHouse columns. 
Model training 
Given a trained model and a test dataset, you need to compute the permutation feature 
importance scores of feature variables. You need to set up the Permutation Feature Importance 
module to select the correct metric to investigate the model’s accuracy and replicate the 
findings. 
You want to configure hyperparameters in the model learning process to speed the learning 
phase by using hyperparameters. In addition, this configuration should cancel the lowest 
performing runs at each evaluation interval, thereby directing effort and resources towards 
models that are more likely to be successful. 
You are concerned that the model might not efficiently use compute resources in 
hyperparameter tuning. You also are concerned that the model might prevent an increase in 
the overall tuning time. Therefore, you need to implement an early stopping criterion on 
models that provides savings without terminating promising jobs. 
Testing 
You must produce multiple partitions of a dataset based on sampling using the Partition and 
Sample module in Azure Machine Learning Studio. You must create three equal partitions for 
cross-validation. You must also configure the cross-validation process so that the rows in the 
test and training datasets are divided evenly by properties that are near each city’s main river. 
The data that identifies that a property is near a river is held in the column named NextToRiver. 
You want to complete this task before the data goes through the sampling process. 
 
When you train a Linear Regression module using a property dataset that shows data for 
property prices for a large city, you need to determine the best features to use in a model. You 
can choose standard metrics provided to measure performance before and after the feature 
importance process completes. You must ensure that the distribution of the features across 
multiple training models is consistent. 
Data visualization 
You need to provide the test results to the Fabrikam Residences team. You create data 
visualizations to aid in presenting the results. 
You must produce a Receiver Operating Characteristic (ROC) curve to conduct a diagnostic test 
evaluation of the model. You need to select appropriate methods for producing the ROC curve 
in Azure Machine Learning Studio to compare the Two-Class Decision Forest and the Two-Class 
Decision Jungle modules with one another. 
 
Question: 15 
   
DRAG DROP 
You need to implement early stopping criteria as suited in the model training requirements. 
Which three code segments should you use to develop the solution?  To answer, move the appropriate 
code segments from the list of code segments to the answer area and arrange them in the correct order. 
NOTE: More than one order of answer choices is correct. You will receive credit for any of the correct 
orders you select. 
 
Answer:  
 
 
Explanation:  
You need to implement an early stopping criterion on models that provides savings without terminating 
promising jobs. 
Truncation selection cancels a given percentage of lowest performing runs at each evaluation interval. 
Runs are compared based on their performance on the primary metric and the lowest X% are 
terminated. 
Example:  
from azureml.train.hyperdrive import TruncationSelectionPolicy 
early_termination_policy = TruncationSelectionPolicy(evaluation_interval=1, truncation_percentage=20, 
delay_evaluation=5) 
Incorrect Answers: 
Bandit is a termination policy based on slack factor/slack amount and evaluation interval. The policy 
early terminates any runs where the primary metric is not within the specified slack factor / slack 
amount with respect to the best performing training run. 
Example:  
from azureml.train.hyperdrive import BanditPolicy 
early_termination_policy = BanditPolicy(slack_factor = 0.1, evaluation_interval=1, delay_evaluation=5 
References: 
https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-tune-hyperparameters