Association rule mining
Association rule mining is a data-mining technique that discovers relationships or implications among items, events, or categorical values based on their co-occurrence.
Data Without Labels
An association rule is a relationship expressing the co-occurrence or implication of items or events.
- How it is used
- Finds transaction-item relationships to inform market basket analysis, product placement, marketing, and pricing.
- How deep it goes
- Defines disjoint antecedents and consequents, introduces evaluation measures, and compares itemset algorithms without deriving metric formulas in the supplied excerpts.
- Examples
- Uses binary supermarket invoices, a beer-and-diapers anecdote, and grocery-store layout planning to illustrate patterns and decisions.
- What you can do after
- Apply it via Python libraries to generate and assess purchasing rules before considering retail layout changes.
Read how Data Without Labels explains association rule mining →
Outlier Detection in Python
An association rule is an implication describing how the presence of one set of categorical values is associated with another set of values.
- How it is used
- Detects interpretable outliers in categorical records by testing frequent-itemset associations and their exceptions.
- How deep it goes
- Explains rule formation, two scoring perspectives, frequent-itemset mining, and record-level exception testing.
- Examples
- Uses telephone area codes with cities and SpeedDating preference ranges to illustrate rules, confidence, and exceptions.
- What you can do after
- Builds categorical outlier scores with mlxtend by mining item sets, generating rules, and locating antecedent-consequent exceptions.
Read how Outlier Detection in Python explains association rule mining →
Related concepts
- supportmeasured by · Support is the proportion of records or transactions containing an itemset or all items associated with an association rule.
- market basket analysisproduced by · Market basket analysis is a data-mining technique that identifies associations among products or other items occurring together in transactions.
- confidencemeasured by · Confidence is the conditional proportion of transactions containing an association rule’s consequent among those containing its antecedent.
- data miningkind of · Data mining is the computational or systematic discovery of patterns, relationships, or other useful information in data.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.