Business Case: Data Mining and Association Rule

In the current competitive retail business, traditional brick$-$mortar business model has slowly lost out to e$-$commerce. When trading is done online, it$$s important to understand customer buying patterns. In return, the ability to predict this pattern into potential marketing solutions to increase sales and profit. Business owners need to know their customers and understand their needs and behaviors. In current business settings, customers purchasing patterns are recorded within big data. Big data when adequately used serve good and formidable business competitive advantage. To do this, retailers use a technique called market basket analysis.

Market basket analysis consists of analyzing large data sets that include purchase history, revealing product groupings, and products that are likely to be purchased together. The simulated case $($see table $1)$ below illustrates a retail purchasing pattern for garments collected over $19$ cluster retails. The recorded purchasing combination serves to provide data analytics to predict future marketing patterns. The key question in the market basket analysis is what products are most frequently purchased together.

Cust No Jeans Shirt Jacket Shoes

$11101$

$20001$

$30101$

$40111$

$51010$

$61010$

$71010$

$81000$

$90101$

$100101$

$110011$

$120010$

$130110$

$141110$

$151001$

$161001$

$171101$

$181101$

$190101$

Table $1$: Buying Pattern from $19$ Cluster Retail Stores

Question $1$

Using market basket analysis, construct a combination of two purchased items into an appropriate table or matrix. Record the following:

$($i$)$ Frequency

$($ii$)$ Support

$($iii$)$ Confidence

$($iv$)$ Lift

Which of the following $3$ combinations would you prioritize? Justify the reason.