Association Rule Mining (ARM)

Overview

Association Rule Mining is a technique used in data mining that helps identify interesting relationships, patterns, or associations between variables in a dataset. It works by analyzing transactional data to discover interesting relationships or patterns that can provide insights into customer behavior, market trends, and business opportunities.

Association Rule Mining techniques can be employed to identify patterns and associations between different shoe brands and customer preferences. This analysis can reveal specific shoe features or attributes that customers prefer in Nike shoes compared to other brands, as well as patterns in customer demographics, such as age, gender, location, or income, and their preferences for different shoe brands.

Through this analysis, insights can be gained into the factors that drive customer appeal and brand recognition in the global footwear market. These insights can be used to develop strategies to improve brand recognition and customer appeal for Nike and other leading shoe brands, ultimately leading to increased market share and profitability.

Some of the important terms related to association rule are :

Support is calculated as the percentage of transactions that include items in the {X} and {Y} parts of the rule out of the total number of transactions, and it measures how frequently the collection of items occur together.
Confidence is the ratio of the number of transactions that includes all items in {B} as well as all items in {A} to the number of transactions that includes all items in {A}, and it indicates how often item B appears in transactions that also contain item A.
Lift is the ratio of the confidence of the rule X=>Y to the expected confidence, which assumes that the item sets X and Y are independent of each other. The expected confidence is calculated by dividing the confidence by the frequency of {Y}.

Data Preparation

Association Rule Mining (ARM) is a data mining technique that requires transaction data to identify patterns and associations between variables. Unlike other machine learning methods, ARM does not require labeled data for training. This makes it a useful tool for analyzing datasets where labeled data is not available or difficult to obtain. Transaction data typically includes records of customer purchases, website visits, or other interactions that capture important information about customer behavior and preferences.

Using ARM on this dataset, it would be possible to identify if there are any specific shoe features or attributes that customers prefer in Nike shoes compared to other brands. This information could be used to develop strategies to improve brand recognition and customer appeal for Nike and other leading shoe brands, ultimately leading to increased market share and profitability.

Overall, the use of ARM on unlabeled transaction data can provide valuable insights into customer behavior, market trends, and business opportunities, without requiring labeled data.

Transaction Data file

Code

GitHub Link: https://github.com/poonamthakur08/Nike-Footwear-Market-Analysis/blob/main/associationRuleMining.rmd

Results

Top 15 rules
The rules extracted from the Apriori Algorithm where the rules are sorted by :

Visualization

Conclusion

In conclusion, the Association Rule Mining analysis suggests that Nike is a highly popular brand among consumers, with its products frequently purchased alongside those of other leading footwear brands. While this analysis provides insights into the purchasing patterns of customers, it does not definitively establish Nike's position as the top-ranked brand in the global footwear market. Other factors such as brand recognition, marketing strategies, and product quality are also important determinants of a brand's success in this highly competitive industry.