Apriori Association Rule Excel VBA Algorithm Association rule Support Confidence Lift Excel VBA
#Apriori_association_rule
#association_rule
#support
#confidence
#liftupchallenge
#excel_vba
email address
[email protected]
Apriori Association Rule
Association rule learning is a machine learning approach that uses rules to uncover interesting relationships between variables in huge databases. Its goal is to uncover strong rules identified in databases using various interestingness criteria.
Rakesh Agrawal, Tomasz Imieliski, and Arun Swam developed association rules based on the notion of strong rules to uncover regularities between items in large-scale transaction data captured by point-of-sale (POS) systems in supermarkets. For example, the rule (onions, potatoes hamburger) seen in a supermarket's sales data would show that if a client buys onions and potatoes together, they are more likely to buy hamburger meat as well. Such data may be utilised to make judgments about marketing operations such as special pricing or product positioning.
Association rule plays a major role in re-locating and re-positing various items in the supermarket to minimize the travelling distance across various shopping aisle in a supermarket. For example, after thoroughly applying the apriori association rule, we obtain a list of items that are favourably to be purchased together when customers do their weekly shopping. Therefore, those items must be stacked on shelves adjacent to each other. First and foremost, we must define several terms related to Association Rules.
Support: indicates how many times the itemset appears on the customers receipts. Support plays a major role indicating the most sold items appearing on most of the customers’ digital receipts. However, the drawback of support is the issue of rare items. Items that appear infrequently in the data set are trimmed, even though they might still yield interesting and potentially valuable rules.