| dc.description.abstract | “Acquiring a new customer is five/six times more costly than retaining an existing one.” “Increasing customer retention rate by 5% increases profits by 25% to 95%.” Given these statistics, seller has to focus on existing customers to increase profitability in a cost-effective way. Due to the convenience of Internet shopping and unlimited choices for online consumers, accurate prediction of the repurchase behavior of existing customers would undoubtedly become its competitive advantage of e-commerce business.
In this study, we use web content mining technique to collect real transaction records between buyer and seller at online shopping website, analyze the loyalty repurchase type of consumer, and establish a comprehensive repurchase behavior prediction model containing RFM, rating and loyalty type. We collected the buyers who had rating records of women’’s shirt category from Taiwan’s Yahoo! Auction website in March 2012, and collected their historical transaction data with all sellers of women’s shirt category before the April 1st of 2012, with which we analyze the loyalty type of these buyers. Then we collected repurchase data in the following two months for those buyer-seller pairs traded before April. Logistic regression analysis showed that the more recent the last transaction, the higher the frequency of past transactions, the higher the cumulative transaction amount, the lower the average transaction amount, the better the rating of the last transaction, the higher the ranking of cumulative rating of the seller, and the buyer is loyalty to one seller, the probability is higher for the buyer to repurchase from the same seller in next one and two months. Given the prediction model can effectively predict the repurchase behavior of online consumers, this model provides useful guidelines of business strategy for online shopping platform providers and online sellers.
| en_US |