Unit 5 madras University in data mining bca dept

2. Agenda
 Introduction
 Data Mining Process
 Techniques in Data Mining
 Association Rule Mining
 Hash Based Techniques
 Multi level Association Rules
 Partition Algorithm
 Parallel and distributed algorithms
 Measuring Quality of Rules

3. Data Mining
Definition
 Data mining is the process of sorting through
large data sets to identify patterns and
relationships that can help solve business
problems through data analysis.
 Data mining techniques and tools enable
enterprises to predict future trends and make
more-informed business decision.

4. Data mining process: How does it work?
 Data gathering. Relevant data for an analytics
application is identified and assembled.
 The data may be located in different source
systems, a data warehouse or a data lake, an
increasingly common repository in bid data
environments that contain a mix of structured
and unstructured data.
 External data sources may also be used.
Wherever the data comes from, a data scientist
often moves it to a data lake for the remaining
steps in the process.

5. Data mining process…
 Data preparation
 This stage includes a set of steps to get the data
ready to be mined.
 It starts with data exploration, profiling and
pre-processing, followed by data cleansing work
to fix errors and other data quality issues.
 Data transformation is also done to make data
sets consistent, unless a data scientist is
looking to analyze unfiltered raw data for a
particular application.

6. Data mining process…
 Mining the data. Once the data is prepared, a
data scientist chooses the appropriate data
mining technique and then implements one or
more algorithms to do the mining.
 In machine learning applications, the
algorithms typically must be trained on sample
data sets to look for the information being
sought before they're run against the full set of
data.

7. Data mining process…
 Data analysis and interpretation.
 The data mining results are used to create analytical
models that can help drive decision-making and other
business actions.
 The data scientist or another member of a data
science team must communicate the findings to
business executives and users, often through data
visualization and the use of data story telling
techniques

8. Data Mining Process

9. Techniques in Data Mining
 1. Classification:
 2. Clustering:
 3. Regression:
 4. Association Rule Mining
 5.Pattern Mining
 6.Anomaly Detection
 7.Neural Network Classifier
 8. Genetic Algorithms

10. ASSOCIATION RULE MINING

11. APRIORI-Market Basket Analysis

12. Association Rule Mining
 The purchasing of one product when another product is
purchased represents an association rule.
 Association rules are frequently used by retail stores to
assist in marketing, advertising, floor placement, and
inventory control.
 They have direct applicability to retail businesses, they
have been used for other purposes as well, including
predicting faults in telecommunication networks.
 Association rules are used to show the relationships
between data items

25. Mining Multilevel Association
Rules
 For many applications, it is difficult to find strong
associations among data items at low or primitive levels of
abstraction due to the sparsity of data at those levels. Strong
associations discovered at high levels of abstraction may
represent commonsense knowledge.
 . Therefore, data mining systems should provide capabilities
for mining association rules at multiple levels of abstraction,
with sufficient flexibility for easy traversal among different
abstraction spaces.

26. Mining Multilevel Association
Rules
 Mining multilevel association rules. Suppose we are given
the task-relevant set of transactional data in Table for sales
in an AllElectronics store, showing the items purchased
for each transaction.
 A concept hierarchy defines a sequence of mappings from
a set of low-level concepts to higher level, more general
concepts.
 Data can be generalized by replacing low-level
concepts within the data by their higher-level concepts,
or ancestors, from a concept hierarchy


27.  The concept hierarchy for the items is shown in
Figure . A concept hierarchy defines a sequence of
mappings from a set of low-level concepts to higher
level, more general concepts. Data can be generalized
by replacing low-level concepts within the data by
their higher-level concepts, or ancestors, from a
concept hierarchy.

30. Mining Multilevel Association
Rules
 Association rules generated from mining data at
multiple levels of abstraction are called multiple-
level or multilevel association rules.
 Multilevel association rules can be mined
efficiently using concept hierarchies under a
support-confidence framework.
 In general, a top-down strategy is employed, For
each level, any algorithm for discovering frequent
itemsets may be used, such as Apriori or its
variations.

31. Mining Multilevel Association
Rules
 Using uniform minimum support for all levels
(referred to as uniform support): The same
minimum support threshold is used when mining
at each level of abstraction.
 For example, in Figure 5.11, a minimum support
threshold of 5% is used throughout (e.g., for mining
from “computer” down to “laptop computer”).
Both “computer” and “laptop computer” are found
to be frequent, while “desktop computer” is not.

32. Mining Multilevel
Association Rules
 When a uniform minimum support threshold is
used, the search procedure is simplified. The
method is also simple in that users are required to
specify only one minimum support threshold.
 An Apriori-like optimization technique can be
adopted, based on the knowledge that an ancestor
is a superset of its descendants: The search avoids
examining item sets containing any item whose
ancestors do not have minimum support.

34. Using reduced minimum support at lower
levels (referred to as reduced support):
 Each level of abstraction has its own minimum support
threshold. The deeper the level of abstraction, the smaller
the corresponding threshold is.
 For example, in Figure, the minimum support thresholds
for levels 1 and 2 are 5% and 3%, respectively. In this
way, “computer,” “laptop computer,” and “desktop
computer” are all considered frequent.

35. Using item or group-based minimum support
(referred to as group-based support):
 Because users or experts often have insight as to which
groups are more important than others, it is sometimes
more desirable to set up user-specific, item, or group
based minimal support thresholds when mining multilevel
rules.
 For example, a user could set up the minimum support
thresholds based on product price, or on items of interest,
such as by setting particularly low support thresholds
for laptop computers and flash drives in order to pay
particular attention to the association patterns containing
items in these categories.

36. Mining Multidimensional Association Rules from
Relational Databases and Data Warehouses
 We have studied association rules that imply a single
predicate, that is, the predicate buys. For instance, in
mining our AllElectronics database, we may discover
the Boolean association rule

37. Mining Multidimensional
Association Rules
 Following the terminology used in multidimensional
databases, we refer to each distinct predicate in a rule as a
dimension.
 Hence, we can refer to Rule above as a single dimensional
or intra dimensional association rule because it contains a
single distinct predicate (e.g., buys)with multiple
occurrences (i.e., the predicate occurs more than once
within the rule).

38. Mining Multidimensional
Association Rules
 Considering each database attribute or warehouse
dimension as a predicate, we can therefore mine
association rules containing multiple predicates, such
as


39. Mining Multidimensional
Association Rules
 Association rules that involve two or more dimensions or
predicates can be referred to as multidimensional association
rules.
 Rule above contains three predicates (age, occupation,
and buys), each of which occurs only once in the rule. Hence,
we say that it has no repeated predicates.
 Multidimensional association rules with no repeated predicates
are called inter dimensional association rules. We can also mine
multidimensional association rules with repeated predicates,
which contain multiple occurrences of some predicates.
 These rules are called hybrid-dimensional association rules. An
example of such a rule is the following, where the
predicate buys is repeated:

40. Note that database attributes can be categorical or quantitative. Categorical
attributes have a finite number of possible values, with no ordering among the
values (e.g., occupation, brand, color).
 Categorical attributes are also called nominal attributes, because their
values are ―names of things.‖ Quantitative attributes are numeric and have an
implicit ordering among values (e.g., age, income, price).
Techniques for mining multidimensional association rules can be
categorized into two basic approaches regarding the treatment of quantitative
attributes.

41. Mining Quantitative Association Rules
 Quantitative association rules are multidimensional
association rules in which the numeric attributes
are dynamically discretized during the mining process so
as to satisfy some mining criteria, such as maximizing the
confidence or compactness of the rules mined.
 In this section, we focus specifically on how to mine
quantitative association rules having two quantitative
attributes on the left-hand side of the rule and one
categorical attribute on the right-hand side of the rule.
That is,

42. where Aquan1 and Aquan2 are tests on quantitative
attribute intervals (where the intervals are dynamically
determined), and Acat tests a categorical attribute from
the task-relevant data.
Such rules have been referred to as two-dimensional
quantitative association rules, because they contain two
quantitative dimensions.

43. Mining Quantitative Association
Rules
 For instance, suppose you are curious about the
association relationship between pairs of quantitative
attributes, like customer age and income, and the type of
television (such as high-definition TV, i.e., HDTV) that
customers like to buy. An example of such a 2-D
quantitative association rule is


44. Partition Algorithm
 If we are given a database with a small number of
potential large itemsets, say, a few thousand, then the
support for all of them can be tested in one scan by
using a partitioning technique.
 Partitioning divides the database into nonoverlapping
subsets; these are individually considered as separate
databases and all large itemsets for that partition,
called local frequent itemsets, are generated in one
pass.

45. Partition Algorithm
 The Apriori algorithm can then be used efficiently on
each partition if it fits entirely in main memory.
Partitions are chosen in such a way that each partition
can be accommodated in main memory.

46. Partition Algorithm
 As such, a partition is read only once in each pass. The
only limitation with the partition method is that the
minimum support used for each partition has a
slightly different meaning from the original value.
 The minimum support is based on the size of the
partition rather than the size of the database for
determining local frequent (large) itemsets.
 The actual support threshold value is the same as given
earlier, but the support is computed only for a
partition.

47. Partition Algorithm
 At the end of pass one, we take the union of all frequent
itemsets from each partition. This forms the global
candidate frequent itemsets for the entire database. When
these lists are merged, they may contain some false
positives.
 That is, some of the itemsets that are frequent (large) in
one partition may not qualify in several other partitions
and hence may not exceed the minimum support when the
original database is considered. Note that there are no false
negatives; no large itemsets will be missed.

48. Partition Algorithm
 The global candidate large itemsets identified in pass
one are verified in pass two; that is, their actual
support is measured for the entire database. At the end
of phase two, all global large itemsets are identified.
The Partition algorithm lends itself naturally to a
parallel or distributed implementation for better
efficiency.

51. PARALLEL AND DISTRIBUTED
ALGORITHMS

57.  Algorithms can be classified along the following
dimensions [DXGHOO] :
 Target: The algorithms we have examined generate all
rules that satisfy a given support and confidence level.
Alternatives to these types of algorithms are those that
generate some subset of the algorithms based on the
constraints given

58.  Type: Algorithms may generate regular association
rules or more advanced asso ciation rules s ch as those
introduced in section 6.7 and Chapters 8 and 9.

59.  Data type: We have examined rules generated for data
in categorical databases. Rules may also be derived for
other types of data such as plain text. This concept is
further investigated in Section 6.7 and in Chapter 7
when we look at Web usage mining.

60.  Data source: Our investigation has been limited to
the use of association rules for market basket data.
This assumes that data are present in a transaction.
The absence of data may also be important.

61.  Technique: The most common strategy to generate
association rules is that of finding large itemsets.
Other techniques may also be used.

62.  Itemset strategy: Itemsets may be counted in different
ways. The most naive approach is to generate all
itemsets and count them. As this is usually too space
 intensive, the bottom-up approach used by Apriori,
which takes advantage of the large itemset property, is
the most common appro ach. A top-down technique
could also be used.

63.  Transaction strategy: To count the itemsets, the
transactions in the database must be scanned. All
transactions could be counted, only a sample may be
counted, or the transactions could be divided into
partitions.

64.  Itemset data structure: The most common data structure
used to store the can didate itemsets and their counts is a
hash tree. Hash trees provide an effective technique to
store, access, and count itemsets. They are efficient to
search, insert, and delete itemsets . A hash tree is a
multiway search tree where the branch to be taken at
each level in the tree is determined by applying a hash
function as
 opposed to comparing key values to branching points in
the node.

65.  Transaction data structure: Transactions
may be viewed as in a flat file or as a TID
list, which can be viewed as an inverted
file. TI1e items usually are encoded (as
seen in the hash tree example), and the use
of bit maps has also been proposed.

66.  Optimization: These techniques
look at how to improve on the
performance of an algorithm given
data distribution (skewness) or
amount of main memory.

67. Architecture: Sequential, parallel,
and distributed algorithms have
been proposed.
Parallelism strategy: B oth data
parallelism and task parallelism
have been used.

68. Comparing algorithms
 Partitioning Scans Data Structure Parallelism
 Apriori m + 1 hash tree none
 Sampling 2 not specified none
 Partitioning 2 hash table none
 CDA m + l hash tree data
 DDA m + 1 tree t ask

69. Measuring Quality of Rules
Support

70. Confidence

71. LIft

72.  https://www.researchgate.net/publication/284921921_
Analysing_the_Quality_of_Association_Rules_by_Co
mputing_an_Interestingness_Measures