Crowdly

Cloud object storage or data warehouses

HTML comments inside crawled pages

PostgreSQL or another relational DBMS

Browser scroll-depth variables

A local clustering coefficient is high for a node when:

Cloud storage costs are low

Cookies are shared across subdomains

API response payloads are large

Stop words dominate the associated text

Many of its neighbors are also connected to each other

What is Web Mining?

A synonym of image processing

An email filtering technique

An advanced SQL database

A form of data mining that extracts patterns from web data

A process of discovering useful information from the web

Which browser-side mechanism is designed for non-blocking transmission of small analytics/event data, often when a page is unloading?

CSS media queries

history.pushState()

navigator.sendBeacon()

IndexedDB.deleteDatabase()

document.write()

HITS algorithm identifies:

Authorities

Nodes

Hubs

Gateways

Tokens

Graph density is best interpreted as:

The fraction of possible edges that are actually present

The length of the longest document

The average number of text tokens per document

The number of web beacons per page

The expiration interval of user cookies

Linear regression is most appropriate when the target variable is:

A graph community identifier only

A class label such as spam/not-spam

A continuous numerical value

A stop-word list

A browser cookie expiration flag

In navigation modeling, a Markov model is used mainly to:

Replace all user segmentation methods

Create persistent cookies

Convert words to dictionary lemmas

Estimate transition probabilities between pages or states

Store protected health information securely

HIPAA compliance requires:

Tokenized credentials

50%

Controlled access to data

50%

DNS blacklisting

50%

Daily social media scans

Audit trails and logging

Which risks can follow from inaccurate predictive models in real applications?

Poor business or operational decisions

Incorrect medical or diagnostic decisions

Guaranteed fairness across all groups

Guaranteed improvement of privacy by default

Financial losses or missed profit