Introduction to Big

Data Management
Engineer Merna Magdy
Engineer Ahmed Ramadan
 Association Rules

Association rules is a data mining technique used to discover

meaningful relationships, associations, or patterns within a
large dataset.

It helps in determining how frequently items or characteristics

appear together in a dataset.

The Apriori algorithm is the most well-known for mining

association rules.
 Itemset Association Rule
• Collection of one or more • “If itemset A is bought,
items or attributes. then itemset B is bought”
represents the association
• Frequent itemset is the set rule statement
of items that appear
together often enough • It is denoted as A → B,
where A and B are itemsets
• Ex: In retail the items can
be products

Key Concepts
Support Confidence
and Terms
• Measures the frequency of • % of records that contains
occurrence of an itemset in a X which also contains Y
dataset
𝑆𝑢𝑝𝑝𝑜𝑟𝑡(𝑋∩𝑌)
• 𝐶𝑜𝑛𝑓 𝑋 → 𝑌 =
𝐶𝑜𝑢𝑛𝑡 𝑆𝑢𝑝𝑝𝑜𝑟𝑡 (𝑋)
• 𝑆𝑢𝑝𝑝𝑜𝑟𝑡 = 𝑇𝑜𝑡𝑎𝑙 𝑅𝑒𝑐𝑜𝑟𝑑𝑠
• High confidence implies a
• High support indicated that the strong association between
itemset is frequently present in items A and B
the dataset Apriori Property: Any subset of a
frequent itemset is also frequent
 Key Concepts and Terms

Lift Leverage
It provides valuable insights into how the It quantifies the difference between the observed frequency of
presence of one item in a transaction co-occurrence of two items in a dataset and the expected
affects the likelihood of the presence of frequency of co-occurrence if the items were independent of
another item. each other

𝑆𝑢𝑝𝑝𝑜𝑟𝑡 (𝑋 ∩ 𝑌) 𝐿𝑒𝑣𝑒𝑟𝑎𝑔𝑒 𝑋 → 𝑌 = 𝑆𝑢𝑝𝑝𝑜𝑟𝑡 𝑋 ∩ 𝑌 − 𝑆𝑢𝑝𝑝𝑜𝑟𝑡 𝑋 ∗ 𝑆𝑢𝑝𝑝𝑜𝑟𝑡 𝑌

𝐿𝑖𝑓𝑡 𝑋 → 𝑌 =
𝑆𝑢𝑝𝑝𝑜𝑟𝑡 𝑋 ∗ 𝑆𝑢𝑝𝑝𝑜𝑟𝑡(𝑌)
= 0: no association
= 1: no association > 0: positive association
> 1: positive association < 0: negative association
< 1: negative association
Lift and leverage are used to assess the statistical associations
and dependencies between items in data, providing insights
into the presence or absence of meaningful relationships.
The higher the leverage and lift values, the stronger the positive
association.
1. For the given dataset, apply apriori algorithm to discover strong
association rules among image tags. Assume that min support = 40% and
min confidence = 70%. Generate association rules from the freuqent
itemsets. Calculate the confidence of each rule and identify all the strong
association rules

Image ID Associated Tags

1 beach, sunshine, holiday

2 sand, beach

3 sunshine, beach, ocean

4 ocean, people, beach, sunshine

5 holiday, sunshine
 Solution
𝐦𝐢𝐧 𝐬𝐮𝐩𝐩𝐨𝐫𝐭 = 𝟒𝟎%
𝐦𝐢𝐧 𝐬𝐮𝐩𝐩𝐨𝐫𝐭 𝐜𝐨𝐮𝐧𝐭 = 𝐦𝐢𝐧 𝐬𝐮𝐩𝐩𝐨𝐫𝐭 ∗ 𝐭𝐨𝐭𝐚𝐥 𝐜𝐨𝐮𝐧𝐭
𝟒𝟎% ∗ 𝟓 = 𝟐
Image Associated Tags
ID
1-itemset Support
1 beach, sunshine, count
holiday 1- Support
beach 4 Frequent count
2 sand, beach
holiday 2 itemset
3 sunshine, beach,
ocean ocean 2 beach 4

4 ocean, people, beach, people 1 holiday 2

sunshine sand 1 ocean 2
5 holiday, sunshine sunshine 4 sunshine 4
 Solution
𝐦𝐢𝐧 𝐬𝐮𝐩𝐩𝐨𝐫𝐭 = 𝟐
1- Support
Frequent count 2-itemset Support
itemset count 2-Frequent Support
beach 4 beach, holiday 1 itemset count
holiday 2 beach, ocean 2 beach, ocean 2
ocean 2 beach, sunshine 3 beach, sunshine 3
sunshine 4 holiday, ocean 0 holiday, sunshine 2
holiday, sunshine 2 ocean, sunshine 2
ocean, sunshine 2
 Solution
𝐦𝐢𝐧 𝐬𝐮𝐩𝐩𝐨𝐫𝐭 = 𝟐

2-Frequent Support 3-itemset Support count

itemset count
beach, ocean 2 beach, ocean, holiday 0
beach, sunshine 3 beach, ocean, sunshine 2
holiday, sunshine 2 beach, holiday, sunshine 1
ocean, sunshine 2 ocean, holiday, sunshine 0

3-Frequent itemset Support count

beach, ocean, sunshine 2
 Solution
𝐦𝐢𝐧 𝐜𝐨𝐧𝐟𝐢𝐝𝐞𝐧𝐜𝐞 = 𝟕𝟎%

2-itemset Confidence 𝐒𝐮𝐩𝐩𝐨𝐫𝐭(𝐗 ∩ 𝐘)

𝐂𝐨𝐧𝐟 𝐗 → 𝒀 =
𝒃𝒆𝒂𝒄𝒉} → {𝒐𝒄𝒆𝒂𝒏 2ൗ = 0.5 𝐒𝐮𝐩𝐩𝐨𝐫𝐭 (𝐗)
4
𝒐𝒄𝒆𝒂𝒏} → {𝒃𝒆𝒂𝒄𝒉 2ൗ = 1
2 3-itemset Confidence
𝒃𝒆𝒂𝒄𝒉} → {𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆 3ൗ = 0.75 𝒃𝒆𝒂𝒄𝒉} → {𝒐𝒄𝒆𝒂𝒏, 𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆 2ൗ = 0.5
4 4
𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆} → {𝒃𝒆𝒂𝒄𝒉 3ൗ = 0.75 𝒐𝒄𝒆𝒂𝒏, 𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆} → {𝒃𝒆𝒂𝒄𝒉 2ൗ = 1
4 2
𝒉𝒐𝒍𝒊𝒅𝒂𝒚} → {𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆 2ൗ = 1 𝒐𝒄𝒆𝒂𝒏} → {𝒃𝒆𝒂𝒄𝒉, 𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆 2ൗ = 1
2 2
𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆} → {𝒉𝒐𝒍𝒊𝒅𝒂𝒚 2ൗ = 0.5 𝒃𝒆𝒂𝒄𝒉, 𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆} → {𝒐𝒄𝒆𝒂𝒏 2ൗ = 0.67
4 3
𝒐𝒄𝒆𝒂𝒏} → {𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆 2ൗ = 1 𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆} → {𝒃𝒆𝒂𝒄𝒉, 𝒐𝒄𝒆𝒂𝒏 2ൗ = 0.5
2 4
𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆} → {𝒐𝒄𝒆𝒂𝒏 2ൗ = 0.5 𝒃𝒆𝒂𝒄𝒉, 𝒐𝒄𝒆𝒂𝒏} → {𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆 2ൗ = 1
4 2
 Solution 𝐒𝐮𝐩𝐩𝐨𝐫𝐭(𝐗 ∩ 𝐘)
𝐂𝐨𝐧𝐟 𝐗 → 𝒀 =
𝐒𝐮𝐩𝐩𝐨𝐫𝐭 (𝐗)

𝑺𝒖𝒑𝒑𝒐𝒓𝒕 (𝑿 ∩ 𝒀)
𝑳𝒊𝒇𝒕 𝑿 → 𝒀 =
𝑺𝒖𝒑𝒑𝒐𝒓𝒕 𝑿 ∗ 𝑺𝒖𝒑𝒑𝒐𝒓𝒕(𝒀)

𝑳𝒆𝒗𝒆𝒓𝒂𝒈𝒆 𝑿 → 𝒀 = 𝑺𝒖𝒑𝒑𝒐𝒓𝒕 𝑿 ∩ 𝒀 − [𝑺𝒖𝒑𝒑𝒐𝒓𝒕 𝑿 ∗ 𝑺𝒖𝒑𝒑𝒐𝒓𝒕(𝒀)]

2-itemset Confidence Lift Leverage 3-itemset Confidence Lift Leverage

𝒐𝒄𝒆𝒂𝒏} → {𝒃𝒆𝒂𝒄𝒉 1 1.25 0.08 𝒐𝒄𝒆𝒂𝒏, 𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆 → 𝒃𝒆𝒂𝒄𝒉 1 1.25 0.08

𝒃𝒆𝒂𝒄𝒉} → {𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆 0.75 0.938 -0.04 𝒐𝒄𝒆𝒂𝒏 → 𝒃𝒆𝒂𝒄𝒉, 𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆 1 1.667 0.16

𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆} → {𝒃𝒆𝒂𝒄𝒉 0.75 0.938 -0.04 𝒃𝒆𝒂𝒄𝒉, 𝒐𝒄𝒆𝒂𝒏 → 𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆 1 1.25 0.08

𝒉𝒐𝒍𝒊𝒅𝒂𝒚} → {𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆 1 1.25 0.08

𝒐𝒄𝒆𝒂𝒏} → {𝒔𝒖𝒏𝒔𝒉𝒊𝒏𝒆 1 1.25 0.08

2. An online retailer has a database that stores 20,000 transactions of last month. After
analyzing the data, a data science team has identified the following statistics:

{Milk} appears in 18,000 transactions.

{Cheese} appears in 16,000 transactions.
{Rice} appears in 15,000 transactions.
{Yogurt} appears in 14,000 transactions.
{Pasta} appears in 13,500 transactions.
{Oil} appears in 12,000 transactions.
{Cereal} appears in 10,000 transactions.
{Pasta, Oil} appears in 11,500 transactions.
{Rice, Oil} appears in 9,500 transactions.
{Milk, Cheese} appears in 13,000 transactions.
{Milk, Cereal} appears in 10,000 transactions.
{Milk, Yogurt} appears in 8,000 transactions.
{Milk, Cereal, Cheese} appears in 8,500 transactions.
{Milk, Cereal, Yogurt} appears in 7,500 transactions.
{Milk, Cereal, Cheese, Yogurt} appears in 7,350 transactions.
Applying Apriori algorithm, answer the following questions:

a) What are the support values of the preceding itemsets?

b) Assuming the minimum support is 0.4, which itemsets are considered frequent?

c) What are the confidence values of the following rules:

1. {Milk} → {Cereal}
2. {Milk, Cereal} → {Cheese}
3. {Milk, Cereal, Cheese} → {Yogurt}
Which of the three rules is more interesting? Why?

d) List all the candidate rules that can be formed from the statistics. Which rules are
considered interesting at the minimum confidence 0.2? out of these interesting rules, which
rule is considered the most useful (least coincidental)?
 Solution
a) What are the support values of the preceding itemsets?
𝒄𝒐𝒖𝒏𝒕
𝑺𝒖𝒑𝒑𝒐𝒓𝒕 =
𝟏𝟏,𝟓𝟎𝟎 𝒕𝒐𝒕𝒂𝒍
𝑴𝒊𝒍𝒌 =
𝟏𝟖,𝟎𝟎𝟎
= 𝟎. 𝟗 𝑷𝒂𝒔𝒕𝒂, 𝑶𝒊𝒍 = = 𝟎. 𝟓𝟕𝟓
𝟐𝟎,𝟎𝟎𝟎
𝟐𝟎,𝟎𝟎𝟎

𝟗,𝟓𝟎𝟎
𝑪𝒉𝒆𝒆𝒔𝒆 =
𝟏𝟔,𝟎𝟎𝟎
= 𝟎. 𝟖 𝑹𝒊𝒄𝒆, 𝑶𝒊𝒍 = = 𝟎. 𝟒𝟕𝟓
𝟐𝟎,𝟎𝟎𝟎
𝟐𝟎,𝟎𝟎𝟎

𝟏𝟑,𝟎𝟎𝟎
𝑹𝒊𝒄𝒆 =
𝟏𝟓,𝟎𝟎𝟎
= 𝟎. 𝟕𝟓 𝑴𝒊𝒍𝒌, 𝑪𝒉𝒆𝒆𝒔𝒆 = = 𝟎. 𝟔𝟓
𝟐𝟎,𝟎𝟎𝟎
𝟐𝟎,𝟎𝟎𝟎

𝟏𝟎,𝟎𝟎𝟎
𝒀𝒐𝒈𝒖𝒓𝒕 =
𝟏𝟒,𝟎𝟎𝟎
= 𝟎. 𝟕 𝑴𝒊𝒍𝒌, 𝑪𝒆𝒓𝒆𝒂𝒍 = = 𝟎. 𝟓
𝟐𝟎,𝟎𝟎𝟎
𝟐𝟎,𝟎𝟎𝟎

𝟖,𝟎𝟎𝟎
𝑷𝒂𝒔𝒕𝒂 =
𝟏𝟑,𝟓𝟎𝟎
= 𝟎. 𝟔𝟕𝟓 𝑴𝒊𝒍𝒌, 𝒀𝒐𝒈𝒖𝒓𝒕 = = 𝟎. 𝟒
𝟐𝟎,𝟎𝟎𝟎
𝟐𝟎,𝟎𝟎𝟎

𝟖,𝟓𝟎𝟎
𝑶𝒊𝒍 =
𝟏𝟐,𝟎𝟎𝟎
= 𝟎. 𝟔 𝑴𝒊𝒍𝒌, 𝑪𝒆𝒓𝒆𝒂𝒍, 𝑪𝒉𝒆𝒆𝒔𝒆 = = 𝟎. 𝟒𝟐5
𝟐𝟎,𝟎𝟎𝟎
𝟐𝟎,𝟎𝟎𝟎

𝟕,𝟓𝟎𝟎
𝑪𝒆𝒓𝒆𝒂𝒍 =
𝟏𝟎,𝟎𝟎𝟎
= 𝟎. 𝟓 𝑴𝒊𝒍𝒌, 𝑪𝒆𝒓𝒆𝒂𝒍, 𝒀𝒐𝒈𝒖𝒓𝒕 = = 𝟎. 𝟑𝟕𝟓
𝟐𝟎,𝟎𝟎𝟎
𝟐𝟎,𝟎𝟎𝟎

𝟕,𝟑𝟓𝟎
𝑴𝒊𝒍𝒌, 𝑪𝒆𝒓𝒆𝒂𝒍, 𝑪𝒉𝒆𝒆𝒔𝒆, 𝒀𝒐𝒈𝒖𝒓𝒕 = = 𝟎. 𝟑𝟔𝟖
𝟐𝟎,𝟎𝟎𝟎
 Solution
b) Assuming the minimum support is 0.4, which itemsets are considered frequent?

𝟏𝟖,𝟎𝟎𝟎
𝑴𝒊𝒍𝒌 = = 𝟎. 𝟗 𝑹𝒊𝒄𝒆, 𝑶𝒊𝒍 =
𝟗,𝟓𝟎𝟎
= 𝟎. 𝟒𝟕𝟓
𝟐𝟎,𝟎𝟎𝟎
𝟐𝟎,𝟎𝟎𝟎

𝟏𝟔,𝟎𝟎𝟎
𝑪𝒉𝒆𝒆𝒔𝒆 = = 𝟎. 𝟖 𝑴𝒊𝒍𝒌, 𝑪𝒉𝒆𝒆𝒔𝒆 =
𝟏𝟑,𝟎𝟎𝟎
= 𝟎. 𝟔𝟓
𝟐𝟎,𝟎𝟎𝟎
𝟐𝟎,𝟎𝟎𝟎

𝟏𝟓,𝟎𝟎𝟎
𝑹𝒊𝒄𝒆 = = 𝟎. 𝟕𝟓 𝑴𝒊𝒍𝒌, 𝑪𝒆𝒓𝒆𝒂𝒍 =
𝟏𝟎,𝟎𝟎𝟎
= 𝟎. 𝟓
𝟐𝟎,𝟎𝟎𝟎
𝟐𝟎,𝟎𝟎𝟎

𝟏𝟒,𝟎𝟎𝟎
𝒀𝒐𝒈𝒖𝒓𝒕 = = 𝟎. 𝟕 𝑴𝒊𝒍𝒌, 𝒀𝒐𝒈𝒖𝒓𝒕 =
𝟖,𝟎𝟎𝟎
= 𝟎. 𝟒
𝟐𝟎,𝟎𝟎𝟎
𝟐𝟎,𝟎𝟎𝟎

𝟏𝟑,𝟓𝟎𝟎
𝑷𝒂𝒔𝒕𝒂 = = 𝟎. 𝟔𝟕𝟓 𝑴𝒊𝒍𝒌, 𝑪𝒆𝒓𝒆𝒂𝒍, 𝑪𝒉𝒆𝒆𝒔𝒆 =
𝟖,𝟓𝟎𝟎
= 𝟎. 𝟒𝟐
𝟐𝟎,𝟎𝟎𝟎
𝟐𝟎,𝟎𝟎𝟎

𝟏𝟐,𝟎𝟎𝟎
𝑶𝒊𝒍 = = 𝟎. 𝟔
𝟐𝟎,𝟎𝟎𝟎

𝟏𝟎,𝟎𝟎𝟎
𝑪𝒆𝒓𝒆𝒂𝒍 = = 𝟎. 𝟓
𝟐𝟎,𝟎𝟎𝟎

𝟏𝟏,𝟓𝟎𝟎
𝑷𝒂𝒔𝒕𝒂, 𝑶𝒊𝒍 = = 𝟎. 𝟓𝟕𝟓
𝟐𝟎,𝟎𝟎𝟎
 Solution
c) What are the confidence values of the following rules:
1. {Milk} → {Cereal}
2. {Milk, Cereal} → {Cheese} 𝐒𝐮𝐩𝐩𝐨𝐫𝐭(𝐗 ∩ 𝐘)
3. {Milk, Cereal, Cheese} → {Yogurt} 𝐂𝐨𝐧𝐟 𝐗 → 𝒀 =
𝐒𝐮𝐩𝐩𝐨𝐫𝐭 (𝐗)
Which of the three rules is more interesting? Why?
𝑺𝒖𝒑𝒑𝒐𝒓𝒕 (𝑿 ∩ 𝒀)
𝑳𝒊𝒇𝒕 𝑿 → 𝒀 =
𝑺𝒖𝒑𝒑𝒐𝒓𝒕 𝑿 ∗ 𝑺𝒖𝒑𝒑𝒐𝒓𝒕(𝒀)

{Milk} → {Cereal}: 𝑳𝒆𝒗𝒆𝒓𝒂𝒈𝒆 𝑿 → 𝒀 = 𝑺𝒖𝒑𝒑𝒐𝒓𝒕 𝑿 ∩ 𝒀 − [𝑺𝒖𝒑𝒑𝒐𝒓𝒕 𝑿 ∗ 𝑺𝒖𝒑𝒑𝒐𝒓𝒕(𝒀)]

𝟎.𝟓
𝑪𝒐𝒏𝒇𝒊𝒅𝒆𝒏𝒄𝒆 = 𝟎.𝟗 = 𝟎. 𝟓𝟓𝟔
𝟎.𝟓
𝑳𝒊𝒇𝒕 = 𝟎.𝟗 ∗ 𝟎.𝟓 = 𝟏. 𝟏𝟏 {Milk, Cereal, Cheese} → {Yogurt}:
𝟎.𝟑𝟔𝟖
𝑳𝒆𝒗𝒆𝒓𝒂𝒈𝒆 = 𝟎. 𝟓 − (𝟎. 𝟗 ∗ 𝟎. 𝟓) = 𝟎. 𝟎𝟓 𝑪𝒐𝒏𝒇𝒊𝒅𝒆𝒏𝒄𝒆 = 𝟎.𝟒𝟐𝟓 = 𝟎. 𝟖𝟔𝟓
𝟎.𝟑𝟔𝟖
𝑳𝒊𝒇𝒕 = 𝟎.𝟒𝟐𝟓 ∗ 𝟎.𝟕 = 𝟏. 𝟐𝟑𝟔
{Milk, Cereal} → {Cheese}: 𝑳𝒆𝒗𝒆𝒓𝒂𝒈𝒆 = 𝟎. 𝟑𝟔𝟖 − 𝟎. 𝟒𝟐𝟓 ∗ 𝟎. 𝟕 = 𝟎. 𝟎𝟕
𝟎.𝟒𝟐𝟓
𝑪𝒐𝒏𝒇𝒊𝒅𝒆𝒏𝒄𝒆 = 𝟎.𝟓 = 𝟎. 𝟖𝟓
𝟎.𝟒𝟐𝟓
𝑳𝒊𝒇𝒕 = 𝟎.𝟓 ∗ 𝟎.𝟖 = 𝟏. 𝟎𝟔𝟐𝟓 Rule 3 has the largest confidence and lift thus it is
𝑳𝒆𝒗𝒆𝒓𝒂𝒈𝒆 = 𝟎. 𝟒𝟐𝟓 − (𝟎. 𝟓 ∗ 𝟎. 𝟖) = 𝟎. 𝟎𝟐𝟓 more interesting
 Solution
d) List all the candidate rules that can be formed from the statistics. Which rules are
considered interesting at the minimum confidence 0.2? out of these interesting rules,
which rule is considered the most useful (least coincidental)?

𝐒𝐮𝐩𝐩𝐨𝐫𝐭(𝐗 ∩ 𝐘)
𝐂𝐨𝐧𝐟 𝐗 → 𝒀 =
𝐒𝐮𝐩𝐩𝐨𝐫𝐭 (𝐗)
2- Frequent Support
𝑺𝒖𝒑𝒑𝒐𝒓𝒕 (𝑿 ∩ 𝒀)
itemset 𝑳𝒊𝒇𝒕 𝑿 → 𝒀 =
𝑺𝒖𝒑𝒑𝒐𝒓𝒕 𝑿 ∗ 𝑺𝒖𝒑𝒑𝒐𝒓𝒕(𝒀)
Pasta, Oil 0.575
𝑳𝒆𝒗𝒆𝒓𝒂𝒈𝒆 𝑿 → 𝒀 = 𝑺𝒖𝒑𝒑𝒐𝒓𝒕 𝑿 ∩ 𝒀 − [𝑺𝒖𝒑𝒑𝒐𝒓𝒕 𝑿 ∗ 𝑺𝒖𝒑𝒑𝒐𝒓𝒕(𝒀)]
Rice, Oil 0.475
Milk, Cheese 0.65
Milk, Cereal 0.5 3-Frequent itemset Support
Milk, Yogurt 0.4 Milk, Cereal, Cheese 0.42
 Solution
d) List all the candidate rules that can be formed from the statistics. Which rules are
considered interesting at the minimum confidence 0.2? out of these interesting rules,
which rule is considered the most useful (least coincidental)?

2-itemset Confidence Lift Leverage 3-itemset Confidence Lift Leverage

𝑷𝒂𝒔𝒕𝒂} → {𝑶𝒊𝒍 0.85 1.419 0.17 𝑴𝒊𝒍𝒌 → 𝑪𝒆𝒓𝒆𝒂𝒍, 𝑪𝒉𝒆𝒆𝒔𝒆 0.467 - -

𝑶𝒊𝒍} → {𝑷𝒂𝒔𝒕𝒂 0.958 1.419 0.17 𝑪𝒆𝒓𝒆𝒂𝒍, 𝑪𝒉𝒆𝒆𝒔𝒆 → 𝑴𝒊𝒍𝒌 - - -

𝑹𝒊𝒄𝒆} → {𝑶𝒊𝒍 0.63 1.056 0.025 𝑪𝒉𝒆𝒆𝒔𝒆 → 𝑴𝒊𝒍𝒌, 𝑪𝒆𝒓𝒆𝒂𝒍 0.525 1.05 0.02

𝑶𝒊𝒍} → {𝑹𝒊𝒄𝒆 0.79 1.056 0.025 𝑴𝒊𝒍𝒌, 𝑪𝒆𝒓𝒆𝒂𝒍 → 𝑪𝒉𝒆𝒆𝒔𝒆 0.84 1.05 0.02

𝑴𝒊𝒍𝒌} → {𝑪𝒉𝒆𝒆𝒔𝒆 0.72 0.903 -0.07 𝑪𝒆𝒓𝒆𝒂𝒍 → 𝑴𝒊𝒍𝒌, 𝑪𝒉𝒆𝒆𝒔𝒆 0.84 1.292 0.095

𝑪𝒉𝒆𝒆𝒔𝒆} → {𝑴𝒊𝒍𝒌 0.813 0.903 -0.07 𝑴𝒊𝒍𝒌, 𝑪𝒉𝒆𝒆𝒔𝒆 → 𝑪𝒆𝒓𝒆𝒂𝒍 0.646 1.292 0.095

𝑴𝒊𝒍𝒌} → {𝑪𝒆𝒓𝒆𝒂𝒍 0.556 1.111 0.05

𝑪𝒆𝒓𝒆𝒂𝒍} → {𝑴𝒊𝒍𝒌 1 1.111 0.05

𝑶𝒊𝒍} → {𝑷𝒂𝒔𝒕𝒂
𝑴𝒊𝒍𝒌} → {𝒀𝒐𝒈𝒖𝒓𝒕 0.444 0.635 -0.23

𝒀𝒐𝒈𝒖𝒓𝒕} → {𝑴𝒊𝒍𝒌 0.571 0.635 -0.23

Thank you!☺
[email protected]
[email protected]