MOBILE APP FOR HIDDEN DATA ANALYTICS OF ONLINE MARKETPLACE SYSTEMS

Abstract

In this project, an extensive analysis and evaluation of the existing e-marketplaces is performed. The aim of this analysis is to improve the experience of end-users through an Android application that is capable of summarizing multiple heterogeneous hidden data sources and unify received responses to one single, structured and homogenous source. The proposed Android application is based on the multi-level conceptual analysis and modeling strategy. In which, the data is analyzed in a way that helps discovering the main entities of any unknown dataset captured from hidden web sources. Several experiments have been conducted that depend on static data analytics for discovering entities. The results showed that query results analysis and re-structuring the output before displaying to the end-user in conceptual multilevel mechanism are reasonably effective in response time to the user interaction with minimal number of screens and clicks. The proposed application can also predict user requirements from the initial query that built on the results obtained from different e-commerce marketplaces. Based on the proposed intelligent application that predict user required products, the interface is minimized to only two navigation screens, and the approximated time needed is 8 seconds to reach the targeted product. This solution is faster and easier to use than the current available application solutions by comparing the response time and the user interaction for the obtained results that met user requirements.