← Back to catalogue
Research draft

data mining

vr.tr.data-mining · ACT.ACT

Let an agent explain data mining, relay methods, process models, applications, privacy risks and regulation from computer science, statistics and data protection sources with debates attributed, describe the named methods and flag attack aliases as related risks without enabling attacks, and distinguish data mining from data collection, machine learning in general, statistics, text and data mining copyright exceptions and data dredging.

Thing Registry Activities and processes

Research draft, second pass

A second pass drafted this model: the structure a model of this thing needs, and what is known about it in the world. The line under this one says how the second half was obtained - researched against sources, or recalled without web access, in which case nothing here was read anywhere and every claim is a lead to verify. Unreviewed either way.

written by Claude from model knowledge without web access - no source was read, every claim is a lead to verify

Researched by: Claude

Purpose and description

Let an agent explain data mining, relay methods, process models, applications, privacy risks and regulation from computer science, statistics and data protection sources with debates attributed, describe the named methods and flag attack aliases as related risks without enabling attacks, and distinguish data mining from data collection, machine learning in general, statistics, text and data mining copyright exceptions and data dredging.

The process of discovering patterns, correlations and anomalies in large datasets using methods from statistics, machine learning and databases, including classification, association rule mining, clustering methods the registry aliases name such as unsupervised, hierarchical and Brown clustering, anomaly detection, and text mining tasks such as argument mining; it is part of knowledge discovery in databases and is used in business, science, healthcare and security. The aliases inference attack and membership inference attack name privacy attacks that deduce sensitive information from data or trained models, a related risk area. Data mining of personal data is regulated by data protection laws such as the GDPR, and ethics debates are attributed.

What it is for: Discovering patterns in data.

It can be explain methods and process; relay applications; describe named methods and privacy risks; relay regulation.

Distinguishing features

Large datasets

Pattern discovery

Algorithmic methods

Privacy implications

What it looks like

Not a physical object; seen in analyses, models, dashboards and reports.

Physical character

KDD process described: 1996 year - Fayyad and colleagues

CRISP-DM: 1999-2000 note - process model

Brown clustering: 1992 year - word clustering

How it is recognised

Pattern discovery in large datasets

Inference attack, unsupervised clustering, membership inference attack, hierarchical clustering, Brown clustering, argument mining

Data collection gathers data; machine learning builds models broadly; statistics tests hypotheses; TDM exceptions are legal rules; data dredging finds spurious results

Related models

is a kind of - in registry terms

text and data mining

uses -

cluster analysis

is threatened by - privacy risk

membership inference attack

is contrasted with -

data dredging

In practice

Families and kinds

classification and prediction

clustering

association rule mining

anomaly detection

text and argument mining

Standards and regulation

GDPR and data protection laws

EU AI Act

Text and data mining exceptions in copyright law

Failure modes and hazards

Privacy violations

Spurious patterns from data dredging

Enabling re-identification attacks

Also called

inference attackunsupervised clusteringMembership inference attackhierarchical clusteringBrown clusteringargument miningextracting structured informationknowledge extractionprocess miningCross-industry standard process for data miningstructure miningassociation rule learningCyborg Data Miningbibliominingcluster analysisaffinity analysisrelational data miningweb miningdecision miningsingle-cell clusteringsupervised clusteringparameter free clusteringBiclusteringspace-time clustering

Where this came from

wikidata · CC0 1.0

Source repository Registry entry point

Drafted structure

Bundle to layer to finding to question, as the second pass will find it: 4 bundles · 8 layers · 8 findings · 16 questions.

Understand What data mining is.

Attribution.

Definition

Definition.

Definition

Definition.

  1. What is data mining, and how does it differ from data collection, machine learning, statistics, TDM exceptions and data dredging? definition
  2. Is the question about methods, a privacy concern, which data protection authorities handle, or legal permissions? boundary

Methods

Named methods.

Methods

Methods.

  1. What are unsupervised, hierarchical and Brown clustering and argument mining, and what are inference attacks in general terms? definition
  2. Which entry fits the specific method? action
Methods Process.

Sources.

KDD

Knowledge discovery.

KDD

KDD.

  1. How do KDD and CRISP-DM structure data mining projects? provenance
  2. Which references are standard? provenance

Clustering

Clustering.

Clustering

Clustering.

  1. How do hierarchical and other clustering methods group data? provenance
  2. Which sources are cited? provenance
Privacy Privacy and law.

Regulation.

GDPR

Data protection.

GDPR

GDPR.

  1. How do data protection laws limit mining personal data? provenance
  2. Which entry fits General Data Protection Regulation? action

Attacks

Privacy attacks.

Attacks

Attacks.

  1. What are membership inference risks and defences such as differential privacy, in general terms? provenance
  2. Which entry fits differential privacy? action
Context Ethics.

Attribution.

Ethics

Ethics debates.

Ethics

Ethics.

  1. What debates exist about data mining in marketing, policing and health, with positions attributed? provenance
  2. Is the presentation neutral and attributed? boundary

Data dredging

Spurious patterns.

Data dredging

Data dredging.

  1. How can mining find false patterns, and how do statisticians guard against it? provenance
  2. Which entry fits data dredging? action

What the second pass must settle

  • The registry aliases inference attack and membership inference attack should be moved to privacy attack entries
  • Should argument mining be a separate entry?
  • How should data protection guidance be linked?
Draft as JSON