SAP- 04 - Titanic Analysis - Answer By AA

docx

School

Lamar University *

*We aren’t endorsed by this school

Course

5370

Subject

Computer Science

Date

Dec 6, 2023

Type

docx

Pages

5

Uploaded by Ren2vikky

Report
Answer Sheet / AA Titanic Association Analysis Provide screenshots to support your answers. estion 1: Which Rule occurs most frequently in the data set? Include a screenshot to support your answer. Crew, Male, Adult, No occurs most frequent in this data set. estion 2: What is meant by Support, Confidence, and Lift? Support measures the frequency of a rule or occurrence of a specific itemset (a set of one or more items) in the dataset. Support helps to answers the question: "How often does this itemset appear in the dataset relative to the total number of transactions?" The higher the support of an itemset, the more frequently they are bought together, while a lower support value suggests that the itemset is relatively rare. 1 of 5
Confidence measures the strength of the association or the likelihood that an item (or itemset) B is purchased when item (or itemset) A is purchased. It answers the question: "Given that a customer buys A, how likely are they to buy B as well?" It measures how often the consequent (RHS) occurs when the antecedent (LHS) is present. Confidence values range from 0 to 1, where 1 indicates a perfect association, meaning that whenever A is bought, B is also bought. Lift assesses the strength of the association between two items (or itemset) while considering the baseline probability of buying item B. It answers the question: "How much more likely is B to be purchased when A is purchased, compared to its likelihood without the influence of A?" Lift values >1 indicate that the presence of A has a positive effect on the purchase of B (i.e., a stronger association than random), while values < 1 suggest a negative or weaker association. A lift value = 1 means there is no association between A and B beyond what would be expected by chance. estion 3: Place a screenshot of the Bar chart and the Bubble chart here. Bar chart 2 of 5
Bubble chart estion 4: Which Rule(s) would be considered the strongest (most important) Rules? Why? Support your answer with a screenshot. From the Bar Chart, Rule: 2 nd , Male, Child, Yes, is considered the strongest Rule has it has a Confidence of 1. 3 of 5
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
estion 5: Take a screenshot of the filtered Bubble chart. estion 6: What happens to the Association Analysis if both Confidence and Support values are increased in the filters? Support your answer with a screenshot. Indicate your new filter values. increasing both confidence and support values in association analysis resulted in a smaller set of highly reliable and significant association rules. Which will ultimately help in the discovery of stronger and more significant associations or patterns in the dataset. Support is > 0.03, Confidence > 0.9. 4 of 5
estion 7: What if both Confidence and Support values are decreased in the filters? Support your answer with a screenshot. Indicate your new filter values. Whereas, if both the confidence and support values are decreased as filters in association analysis, it will have the opposite effect compared to increasing these thresholds. It would lead to a larger set of association rules, including weaker and potentially less reliable associations. Support is > 0.006, Confidence > 0.4. 5 of 5