Big Data Analytics Made Easy by Prasad Y. Lakshmi

Author:Prasad, Y. Lakshmi
Language: eng
Format: epub, azw3
Publisher: Notion Press
Published: 2016-12-14T05:00:00+00:00

STEP 9

Market Basket Analysis

9.1 Introduction

Market Basket Analysis has several names like Pattern Discovery/Pattern Mining/Association rules/Market Basket Analysis/Itemset Mining. It Provides insights into which products tend to be purchased together and which are most acquiescent to promotion. Association rule learning is a popular Data Mining technique for discovering interesting relations between variables in large databases.

What Is Pattern Discovery?

Patterns: A set of items, subsequences, or substructures that occur frequently together in a data set. Patterns represent intrinsic and important properties of datasets. Pattern discovery is Uncovering patterns from massive data sets. Pattern Discovery is used to find out inherent regularities in a data set and it can act as a foundation for many essential data mining tasks like Association, Correlation, Time series Analysis, Causality analysis, Cluster analysis, Mining sequential and Structural patterns.

What are patterns?: Patterns are set of items that occur frequently together in a data set, which represents important properties of datasets.

We can Use association rules to answer these sort of questions:

What products were often purchased together?

What are the subsequent purchases after buying a Specific Product?

What word sequences likely form phrases in this corpus?

what are the frequent items this customer purchases?

What is the average number of items per order?

What is the most common item found in a one-item order?

Since he purchased Laptop, when will he purchase a printer?

Since he purchased iphone6 will he be interested in iphone7?

Which site he entered, then where he moved, how much time he spent there?

Which diseases are more common in individuals with this specific gene sequence?

Customers who have purchased this product, what other products do they tend to purchase?

What is the average number of orders per customer?

What is the average number of unique items per order?

Unusual combinations of insurance claims can be a sign of fraud, How Can I found them?

Medical patient histories can give indications of likely complications based on certain combinations of treatments, How often these adverse Events are occurring?

The objective of association rules is to discern exciting relationships among the items. Each of the uncovered rules is in the form X → Y, meaning that when item X is observed, item Y is also observed. In this case, the left-hand side (LHS) of the rule is X, and the right-hand side (RHS) of the rule is Y.

Let us take a list of few transactions given in the Transact.txt file from a grocery store adjacent to a fitness Centre.

We may want to answer the following questions:

What are the two items more likely to be purchased together than any other two items?

Which product is never purchased with Jam?

Those queries can be answered by observing the data manually. Now the real problem is How do we generate these rules automatically on large data?

9.2 Terminology of Pattern Discovery

Itemset: Each transaction that contains one or more items. This is also known as an Itemset. The term itemset refers to a collection of items or individual entities that contain some kind of relationship. This could be a set of items purchased together in one transaction, a set of profiles

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.