1) The document discusses frequent itemsets, which are products that are often purchased together in stores. Association rule mining and the Apriori algorithm are used to discover these frequent itemsets and generate rules about commonly bought product combinations.
2) The Apriori algorithm employs an iterative approach to first find all frequent individual items, then combinations of two items, and so on, pruning the search space at each iteration.
3) Applications that use these techniques include e-commerce sites like Amazon to provide personalized recommendations and increase sales through related product suggestions.
1. Products Frequently Bought
Together in Stores
Submitted by
Asia abd allah
Nabaa waleed
Hiba Sameer
Haneen haqi
Supervised by
Dr. Amenah dahim
2. Outlines
1.Introduction.
Motivation of frequent itemsets in supermarkets.
2. Association rule.
Association rule disadvantage.
3. priori Algorithm for computing frequent itemsets.
How can the A-priori Algorithm be improved.
What Applications use A-priori Algorithm.
4.Conclusion.
3. Introduction
A Frequent Item set combines elements that often appear
together in market.
Frequently bought together purchase recommendations
are one of the most impactful marketing strategies that
have the potential to maximize the return on investment on
in-house product marketing.
Frequently bought together are the products that your
customers usually purchase with specific items in your
store.
Displaying the right products at the right time can help
drive the discovery and sales of your products.
Stores like Amazon use “frequently bought together” to
increase customer average order value through cross-sells
and upsells.
4. Discounts are one of the most significant tools
used to persuade sales.
Discount would help salesman drive up the
average order value of the purchases.
Smart upselling and cross-selling strategy that
fits into natural shopping behavior.
Introduction
5. Motivation of frequent itemsets in supermarkets
An easy way to offer shopping assistance.
The frequently bought together section act as a
shopping assistant by suggesting the best-
suited complementary products.
Manually curating frequently bought together
products lets you maximize revenue and profits
for your store.
Introduction
6. Motivation of frequent itemsets in supermarkets
products as frequently bought together would help you remind
your customers of the products that they might need.
Products that bought together helps you boost your sales and
profits.
Introduction
7. Association rule
• This concept itself is derived from the terminology of market basket analysis,
namely the search for relationships of several products in a purchase transaction.
• Most machine learning algorithms work with numeric datasets and hence tend to
be mathematical. However, association rule mining is suitable for non-numeric,
categorical data.
• Understanding consumer buying behavior is compulsory in business.
8. Association rule
• The relationship of the association rules formed is denoted in X → Y numbers,
where X and Y are a disjoint item set (X ∩ Y) = ∅.
• An association rule has 2 parts:
an antecedent (if) and
a consequent (then)
An antecedent is something that’s found in data, and a consequent is an item that
is found in combination with the antecedent.
9. Association rule
Depending on the following two parameters, the important relationships are observed:
Support(s): It is the number of transactions that include items from the {X} and {Y} parts of the rule as a percentage of total
transactions. It can be represented in the form of a percentage of all transactions that shows how frequently a group of items
occurs together.
Support = σ(X+Y) ÷ total: It is a fraction of transactions that include both X and Y.
Confidence(c): This ratio represents the total number of transactions of all of the items in {X} and {Y} to the number of
transactions of the items in {X}.
confidence = σ(X+Y) ÷ σ(X)
the goal of association rule mining is to find all rules having
- support ≥ minimum support threshold
- confidence ≥ minimum confidence threshold
10. Example of calculating support and
confidence
To facilitate the calculation, then
the product data in table 1 is coded
and separated by each product as
shown in Table 2 below.
11. Example of calculating support and
confidence
Table 3. Rule Association Candidates
Table 4. Rule Association Calculation
12. Example of calculating support and
confidence
These rules will be implemented by retail owners to regulate the layout of these products
based on patterns or habits of consumers in buying products.
Let’s suppose that the minimum support and confidence
threshold defined by the Subject Matter Expert is 40%.
Assuming that :
- support ≥ 40 support threshold
- confidence ≥ 40 confidence threshold
The calculation results in tables 4 and 5 show that the rules
used are with the highest confidence and support values,
namely:
• If you buy B, you will buy A (If you buy coffee, you will buy
sugar too)
• If you buy E, you will buy F (If you buy toothpaste, you will
buy soap too)
Table 8. Calculation of Support and
Confidence
13. Association rule disadvantage
• The employed algorithms have too many parameters for someone
who is not a data mining expert.
• The disadvantage of association algorithms is that they are trying to
find patterns within a potentially very large search space and, hence,
can require much more time to run than a decision tree algorithm.
14. A- priori Algorithm for computing frequent itemsets
Apriori Algorithim is an significant algorithm for mining frequent itemsets
for boolean association rules.
It contains two processes :-
• Detect all frequent itemsets by scanning DB.
• Form strong association rules in the frequent itemsets.
15. A- priori Algorithm for computing frequent itemsets
Apriori pruning principle: If there is any itemset which is infrequent, its
superset should not be generated/tested!
Method:
Initially, scan DB once to get frequent 1-itemset
Generate length (k+1) candidate itemsets from length k frequent itemsets
Test the candidates against DB
Terminate when no frequent or candidate set can be generated
20. How can the A-priori Algorithm be improved?
• Hash-based Item set Counting: method used to generate a table ,it
contains the items and count the frequent of them.
• Transaction Reduction: used to remove the items which not repeated.
• Partitioning : split the large amount of data into different sets.
• Sampling : select set of data to process it from a large data sets.
• Dynamic Item set Counting : it is a method used to count the items
dynamically.
21. Research Steps
1-Start
2- Data collecting
3-Apply A-priori algorithm
4- Extract pattern
5-Use association algorithm
6-Extract rules
7-End
22. What Applications use this Algorithm?
• Education.
• Medicine.
• Biology.
• E-commerce & Recommendation.
23. Amazon
• Amazon’s recommendations for the Frequently Bought Together
section furthermore help shoppers keep abreast of the latest
ecommerce and marketplace trends.
24. Conclusion
Market Based Analysis is one of the key techniques used by large relations to show
associations between items .
it can generate association rules from the given transactional datasets.
Association rules are useful for analyzing and predicting customer behavior.
The disadvantage of association algorithms is require much more time to run than a decision
tree algorithm.
The Apriori Algorithm is an instrumental algorithm for mining familiar item sets.
The disadvantage is more exploration space and computational cost is too expensive