1 - Tools of the Trade

Question 1

What is Steve’s main task at Shu Money Financial?

Answer 1

To lead the development of a new strategy for prioritizing cases sent to the Recoveries Department.

Question 2

What happens to a debt if a customer has not paid anything owed in the previous six months?

Answer 2

The debt is charged off.

Question 3

What are the three tiers of account assignment in the Recoveries Department?

Answer 3

• Tier 1: Accounts that have made a payment
• Tier 2: Accounts that have never made a payment but had some contact
• Tier 3: Accounts that have never made a payment and had no contact

Question 4

What is the primary goal for Steve in the Recoveries Department?

Answer 4

To increase the profitability of the Recoveries Department by improving work prioritization.

Question 5

What does a data-informed approach involve according to Steve?

Answer 5

Gathering appropriate data about customers and systematically analyzing it.

Question 6

What is the basic data workflow comprised of?

Answer 6

• Data collection
• Storage
• Preparation
• Exploration
• Modeling (including experimentation and prediction)

Question 7

What does the acronym ETL stand for in data processing?

Answer 7

Extract, Transform, Load.

Question 8

What is the purpose of the data transformation step?

Answer 8

To ensure data quality by resolving inconsistencies, standardizing formatting, and removing duplicate records.

Question 9

True or False: Data quality checks are unnecessary if the data is collected from reliable sources.

Answer 9

False.

Question 10

What are some key features of good data architectures?

Answer 10

• Scalability
• Availability
• Security
• Performance
• Cost efficiency

Question 11

What is one major advantage of cloud computing over local computing?

Answer 11

Data can be accessed from anywhere with internet access.

Question 12

Fill in the blank: The process of loading transformed data can be done in a _______ load or in _______ loads.

Answer 12

full; incremental

Question 13

What was a significant disadvantage of local data storage mentioned in the text?

Answer 13

Data was vulnerable to physical disasters and required manual backups.

Question 14

How does cloud computing help in terms of data security?

Answer 14

Cloud providers manage security and integrity of the systems.

Question 15

What did Steve learn from his data analysis project at business school?

Answer 15

Cloud computing has major advantages over local storage solutions.

Question 16

What is the difference between local computing and cloud computing as explained by Brett?

Answer 16

Local computing stores data on a personal device, while cloud computing stores data on remote servers accessible via the internet.

Question 17

What is the primary responsibility of systems defenders?

Answer 17

Defending the integrity of systems

This includes protecting against ransomware and malware attacks.

Question 18

What is ransomware?

Answer 18

A type of malicious software that blocks access to a computer system until a payment is made.

Question 19

What is malware?

Answer 19

Software that disrupts, damages, or misuses a computer system.

Question 20

How has cloud computing improved data portability?

Answer 20

Allows data to remain in the country of interest while being accessible from other locations.

Question 21

What are the key services delivered by cloud computing?

Answer 21

• Data storage
• Servers
• Databases
• Networking
• Software

Question 22

What does it mean that cloud computing is elastic?

Answer 22

Users can adjust the number of services they need without being locked into a specific amount.

Question 23

What are the cost advantages of cloud computing?

Answer 23

Pay only for the storage and services actually used.

Question 24

What security risks are associated with cloud computing?

Answer 24

Accounts can be hacked and data stolen.

Question 25

What is a disadvantage of cloud storage?

Answer 25

Delays in transferring data and creating backups due to internet speeds.

Question 26

What is vendor lock-in in cloud computing?

Answer 26

Difficulty in migrating from one cloud storage provider to another.

Question 27

Which major cloud vendors are mentioned?

Answer 27

* Google Cloud * Amazon Web Services * Microsoft Azure

Question 28

What are APIs?

Answer 28

Sets of rules that explain how computers or applications communicate with one another.

Question 29

What is the difference between structured and unstructured data?

Answer 29

* Structured data: predefined values, stored in relational databases * Unstructured data: not captured in traditional databases, includes emails, chatbots, videos, etc.

Question 30

What is a data lake?

Answer 30

A data storage mechanism that holds raw data in its native format until needed.

Question 31

What is the significance of data quality in data science?

Answer 31

High data quality is crucial for accurate analysis and predictive modeling.

Question 32

What does 'garbage in, garbage out' mean?

Answer 32

The quality of output is determined by the quality of the input data.

Question 33

What is SQL?

Answer 33

Structured Query Language used for managing and querying relational databases.

Question 34

What is the purpose of the SELECT command in SQL?

Answer 34

Defines what fields to extract from a database.

Question 35

What are two popular programming languages for data science?

Answer 35

* Python * R

Question 36

What is the role of libraries and packages in Python and R?

Answer 36

They provide built-in functions that facilitate programming tasks.

Question 37

What must a data scientist understand about input data?

Answer 37

The nature of the data, including cleaning priorities and idiosyncrasies.

Question 38

What is the importance of collaboration between data science customers and teams?

Answer 38

Ensures data preparation improves quality for later modeling.

Question 39

Fill in the blank: The _______ is a data storage mechanism that holds raw data in its native format.

Answer 39

[data lake]

Question 40

What is the role of libraries and packages in programming languages?

Answer 40

They include built-in functions that can be readily called in the programming language.

Question 41

What is R commonly used for in data science?

Answer 41

Statistical analysis, modeling, analyzing spatial and time series data, classifying, and clustering.

Question 42

Name two popular integrated development environments for R.

Answer 42

* RStudio * R Tools for Visual Studio

Question 43

What is a key strength of Python?

Answer 43

It can be easily integrated with other programming languages.

Question 44

Why have Python and R gained popularity over the past decade?

Answer 44

They are free and have large networks of developers.

Question 45

Which programming language was once dominant for statistical programming?

Answer 45

SAS

Question 46

List three major proprietary software options for data analysis.

Answer 46

* Matlab * STATA * SPSS

Question 47

What can customers inquire about when using proprietary software?

Answer 47

The duration of the current license and plans for renewal.

Question 48

True or False: Simple programs can be quickly rewritten in a new language like Python or R.

Answer 48

True

Question 49

What is AutoML?

Answer 49

Automated machine learning solutions that can be used in point-and-click mode or hands-on programming.

Question 50

What does feature engineering in AutoML involve?

Answer 50

Automatically exploring new potential input variables.

Question 51

What is the primary function of code repositories in data science?

Answer 51

Allow multiple programmers to work on a project while tracking their contributions.

Question 52

Name two code repository platforms.

Answer 52

* Github * Bitbucket

Question 53

What is the importance of documenting code?

Answer 53

It helps others understand the purpose and functionality of the code.

Question 54

What is a data product in data science?

Answer 54

The translation of raw data into a practical solution tailored to the end user's needs.

Question 55

What is a data dictionary?

Answer 55

It identifies the fields in a database and how each field is defined.

Question 56

What should a cleaned data set include for effective modeling?

Answer 56

Quality-checked and documented data, along with derived data fields.

Question 57

What are predictive models used for in data products?

Answer 57

Estimating probabilities and expected outcomes relevant to business decisions.

Question 58

What is the highest level of data product?

Answer 58

An automated decision-making tool.

Question 59

Fill in the blank: The data science team is responsible for providing information for _______.

Answer 59

[business decisions]

Question 60

What should a customer ask about data storage options?

Answer 60

The advantages and disadvantages of the current data storage system.

Question 61

What is the significance of data quality checks?

Answer 61

They ensure the accuracy and reliability of data used in analysis.

Question 62

What should be included in data quality checks?

Answer 62

* Frequency of missing data * Patterns of missing data * Imputation methods for missing values

Question 63

What coding languages are often used in data science?

Answer 63

Python and R, among others.

Question 64

What is an important consideration regarding data products?

Answer 64

The level of data product appropriate for the business's IT capacity and human resource skill set.

Question 65

What does an automated decision-making algorithm do?

Answer 65

Identifies priorities and handles decision-making processes automatically.