27 Questions
What are some examples of supervised learning tasks?
Predicting real estate prices, classifying bank transactions, determining loan applicant risk factors
Can you provide examples of unsupervised learning applications?
Creating customer groups, grouping inventory, pinpointing associations in customer data
Give examples of reinforcement learning scenarios.
Teaching cars to park autonomously, controlling traffic lights to reduce traffic
What is the focus of 'deep learning' according to Dubovikov?
Deep learning studies neural networks
How does Dubovikov differentiate between 'structured' and 'unstructured' data?
Structured data is organized, unstructured data includes images and audio recordings
Why is analyzing unstructured data challenging?
Analyzing unstructured data is challenging due to its lack of organization and complexity
What are some limitations of data science?
Task solvability challenges, technical understanding issues, project failures, deployment problems.
Define 'machine learning' as a scientific field.
Machine learning studies algorithms that learn tasks without specific instructions based on data patterns.
Provide two examples of machine learning applications.
Face detection and recognition, credit scoring models.
List the three types of machine learning and give an example for each.
Supervised learning (e.g., spam email detection), Unsupervised learning (e.g., market segmentation), Reinforcement learning (e.g., game playing).
What are some challenges that can arise in data science projects?
Task may be unsolvable, lack of technical understanding, project failures, issues after deployment.
Give an example of an application of supervised learning.
Spam email detection.
What is the term 'business intelligence, BI' according to Sharda et al.?
Business Intelligence (BI) refers to evidence/fact-based managerial decision making.
According to Sharda et al., what is a 'data warehouse'?
A Data Warehouse (DW) is a pool of data produced to support decision making.
What kind of data is collected in a data warehouse according to Immon?
A data warehouse is a subject-oriented, integrated, time-variant (time series), nonvolatile collection of data.
Name four types of input sources of a Data warehouse according to Sharda et al.
ERP, Legacy, POS, Other OLTP/Web, External Data
What types of Business Analytics are classified as 'advanced analytics' according to Sharda et al.?
- Predictive (what will happen?→ projection of future events) - Prescriptive (what should I do?→ best possible business decision)
Please name and describe the stages of the CRISP-DM method.
Business understanding - What does the business need?
What is the role of data analysts in a data science project according to Dubovikov?
Creating datamarts, building complex database queries, visualizing data, and deriving insights.
What is the difference between push and pull communication?
Push communication sends information without recipients' request, while pull communication sends information at recipients' request.
List six guidelines for running effective meetings.
- Determine if a meeting can be avoided
- Define the purpose and outcome
- Identify attendees
- Provide an agenda
- Prepare handouts and visual aids
- Set ground rules and run the meeting professionally.
What tasks do data scientists perform in a data science project?
Creating models, performing statistical analysis, and applying existing algorithms.
What is the difference between a machine learning engineer and a research scientist as described in the text?
Machine learning engineer applies existing algorithms, while research scientist creates new state-of-the-art models.
Name two situations when you should consider turning a reusable component into a product.
When the reusable component has wider application potential or when there is a demand for the component in the market.
What are the responsibilities of data engineers in a data science project?
Handling data preparation and processing.
When does a project typically require a machine or deep learning researcher?
When the project involves research and creation of new state-of-the-art models.
Can data scientists with data engineering skills handle data preparation and processing in simple projects?
Yes.
Test your knowledge on the limitations of data science, including tasks that appear solvable but are not, the importance of understanding the technical aspects, and the possibility of project failure despite best efforts.
Make Your Own Quizzes and Flashcards
Convert your notes into interactive study material.
Get started for free
