Weighted Aggregate Reverse Rank Queries

Abstract

In marketing, helping manufacturers to find the matching preferences of potential customers for their products is an essential work, especially in e-commerce analyzing with big data. The aggregate reverse rank query has been proposed to return top- k customers who have more potential to buy a given product bundling than other customers, where the potential is evaluated by the aggregate rank, which is defined as the sum of each product’s rank. This query correctly reflects the request only when the customers consider the products in the product bundling equally. Unfortunately, rather than thinking products equally, in most cases, people buy a product bundling because they appreciate a special part of the bundling. Manufacturers, such as video games companies and cable television industries, are also willing to bundle some attractive products with less popular products for the purpose of maximum benefits or inventory liquidation. Inspired by the necessity of general aggregate reverse rank query for unequal thinking, we propose a weighted aggregate reverse rank query, which treats the elements in product bundling with different weights to target customers from all aspects of thought. To solve this query efficiently, we first try a straightforward extension. Then, we rebuild the bound-and-filter framework for the weighted aggregate reverse rank query. We prove, theoretically, that the new approach finds the optimal bounds, and we develop the highly efficient algorithm based on these bounds. The theoretical analysis and experimental results demonstrated the efficacy of the proposed methods.