Extracting interesting patterns from e-commerce databases to ensure customer loyalty

In recent years with the rapid growth of e-commerce and the large amounts of data collected through operational transactions, data mining techniques are becoming more useful to discover and understand unknown customer patterns. In the past, data mining has been used to find out which products are related in terms of having high sales and also ascertain which customers deserve credit facilities. There has not been much work done in the use of data mining to ensure customer loyalty in the e-commerce business and also have strategies of increasing retail companies to use e-commerce as a profitable mode of doing business. The aim of this paper is to study the customer´s behavior through data mining techniques used in deriving association rules from an e-commerce database so as to ensure customer loyalty and also assist in having strategies of luring businesses to use e-commerce for conducting highly profitable business. From our results the association rules reveal that if a product stays online for a long time (more than 550 days), it is 78% highly likely it will not be bought. The association rules also indicate that the number of products bought are linked to the number of times customers view the products online and the selling price of the product.