# US 2012/0254242 A1 · Methods and systems for mining association rules

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2012/0254242 A1
- Document ID: US20120254242A1
- Status: Published application
- Kind: A1
- Application number: 13/111,178
- Filed: 2011-05-19
- Published: 2012-10-04
- Earliest claimed: 2011-03-31
- Assignees: Infosys Technologies Limited
- Inventors: Balasubramanian Kanagasabapathi; K. Antony Arokia Durai Raj
- Web page: https://patentgrep.com/patent/US20120254242A1

## CPC

- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- G06N 5/025: Extracting rules from data
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Systems, methods, and computer-readable code stored on a non-transitory media for mining association rules include determining a minimum support threshold and a minimum confidence threshold for association rule mining; determining a sampling model; sampling transactions from a transaction dataset; mining association rules from the sampled transactions; and transmitting mined association rules.

## Claims

### Claim 1

A computer implemented method for mining association rules, said method comprising:
determining, by a computing device, a minimum support threshold and a minimum confidence threshold for association rule mining;
determining, by a computing device, a sampling model;
sampling, by a computing device, transactions from a transaction dataset;
mining, by a computing device, association rules from the sampled transactions; and
transmitting, by a computing device, mined association rules.

### Claim 2 (depends on 1)

The method of claim 1, wherein said step of determining a minimum support threshold and a minimum confidence threshold comprises receiving the minimum support threshold and receiving the minimum confidence threshold.

### Claim 3 (depends on 2)

The method of claim 2, further comprising:
scanning the transaction dataset to identify 1-itemsets;
computing a statistic measure between identified 1-itemsets; and
prune the 1-itemsets from future calculations if the statistic measure is not greater than at least one of the minimum support threshold and the minimum confidence threshold.

### Claim 4 (depends on 1)

The method of claim 1, wherein the step of determining a minimum support threshold and a minimum confidence threshold comprises heuristically generating the minimum support threshold and the minimum confidence threshold.

### Claim 5 (depends on 4)

The method of claim 4, wherein heuristically generating the minimum support threshold and the minimum confidence threshold comprises:
scanning the dataset for all 1-itemset transactions;
determining a support count for at least one 1-itemset transaction;
initializing the minimum support threshold and the minimum confidence threshold based on at least one support count;
determining whether the mining association rules step mines at least one association rule; and
adjusting the minimum support threshold and the minimum confidence threshold if the determining step determines no association rules were mined.

### Claim 6 (depends on 5)

The method of claim 5, wherein the step of adjusting the minimum support threshold and the minimum confidence threshold comprises:
determining at least one of the minimum support threshold and the minimum confidence threshold;
decrementing the minimum support threshold and the minimum confidence threshold by a first percentage if at least one of the minimum support threshold and the minimum confidence threshold is below a first value; and
decrementing the minimum support threshold and the minimum confidence threshold by a second percentage if at least one of the minimum support threshold and the minimum confidence threshold is less than or equal to the first value and greater than a second value.

### Claim 7 (depends on 6)

The method of claim 6, wherein the first value is five, the second value is zero, the first percentage is five percent, and the second percentage is one percent.

### Claim 8 (depends on 4)

The method of claim 4, wherein the step of initializing the minimum support threshold and the minimum confidence threshold comprises initializing the minimum support threshold and the minimum confidence threshold to half of the sum of a minimum support count for a 1-itemset and a maximum support count for a 1-itemset.

### Claim 9 (depends on 1)

The method of claim 1, further comprising preprocessing the dataset containing plural transactions.

### Claim 10 (depends on 1)

The method of claim 1, wherein the determining step comprises receiving a selection of a sampling method from a user.

### Claim 11 (depends on 1)

The method of claim 1, wherein said step of determining a sampling method comprises determining a stratified sampling method and wherein said step of sampling comprises:
grouping transactions in the transaction database into plural subgroups according to an attribute associated with a customer associated with each transaction; and
sampling transactions from the subgroups according to one of a random sampling model and a systematic sampling model.

### Claim 12 (depends on 1)

The method of claim 1, wherein said step of determining a sampling method comprises determining a systematic sampling method and wherein said step of sampling comprises:
determining an ordered frame size;
grouping transactions into frames according to the ordered frame size; and
sampling a transaction from each frame.

### Claim 13 (depends on 1)

The method of claim 1, wherein said step of determining a sampling method comprises determining a cluster sampling method and wherein said step of sampling comprises:
grouping transactions in the transaction dataset into plural substantially heterogeneous clusters;
selecting one of the plural clusters; and
sampling transactions from the selected cluster.

### Claim 14 (depends on 1)

The method of claim 1, wherein said step of determining a sampling method comprises determining a classified data sampling method and wherein said step of sampling comprises:
receiving attributes of the transactions in the dataset;
grouping transactions in the dataset into plural sets of classified transactions; and
sampling transactions from at least one set of classified transactions.

### Claim 15

A system for mining association rules, said system comprising:
a memory; and
a processor operatively coupled to the memory, the processor performing the steps of:
determining a minimum support threshold and a minimum confidence threshold for association rule mining;
determining a sampling model;
sampling transactions from a transaction dataset;
mining association rules from the sampled transactions; and
transmitting mined association rules.

### Claim 16 (depends on 15)

The system of claim 15, wherein the processor further performs the steps of:
scanning the transaction dataset to identify 1-itemsets;
computing a statistic measure between identified 1-itemsets; and
prune the 1-itemsets from future calculations if the statistic measure is not greater than at least one of the minimum support threshold and the minimum confidence threshold.

### Claim 17 (depends on 16)

The system of claim 16, wherein the step of determining a minimum support threshold and a minimum confidence threshold comprises heuristically generating the minimum support threshold and the minimum confidence threshold.

### Claim 18

Computer-readable code stored on a non-transitory computer-readable medium that, when executed by a mobile device, performs the method:
determining, by a computing device, a sampling model;
sampling, by a computing device, transactions from a transaction dataset;
mining, by a computing device, association rules from the sampled transactions; and
transmitting, by a computing device, mined association rules.

### Claim 19 (depends on 18)

The computer-readable code of claim 18, the method further comprising:
scanning the transaction dataset to identify 1-itemsets;
computing a statistic measure between identified 1-itemsets; and
prune the 1-itemsets from future calculations if the statistic measure is not greater than at least one of the minimum support threshold and the minimum confidence threshold.

### Claim 20 (depends on 19)

The computer-readable code of claim 19, wherein the step of determining a minimum support threshold and a minimum confidence threshold comprises heuristically generating the minimum support threshold and the minimum confidence threshold.
