2. The Evolution of Analytics Flashcards
1
Q
Why is Machine Learning suddenly so popular among business?
A
Both data storage and data processing capacities have grown tremendously to a point where it is now profitable for businesses to use machine learning
2
Q
Why is a “cold-start” the biggest problem when starting to use Machine Learning?
A
Most organisations do not have historical data to get started with, they have to start from scratch. It gets easier to use Machine learning when you’ve acquired some data already.
3
Q
What are the 3 types of streaming analytics?
A
- Edge analytics - Data colled within the device
- In-stream analytics - Data collected between the device and the server
- At-rest analytics - Data collected at rest
4
Q
What are some data quality issues?
A
- Noisy Data - Data that contains a large amount of conflicting or misleading information
- Dirty data - Data that contains missing values, categorical and character features with many levels, and inconsistent and erroneous values.
- Sparse data - Data that contains very few actual values
- Inadequate data - Data that is either incomplete or biased