LITERATURE SURVEY ON HIGH UTILITY ITEM- SET MINING AND CUSTOMER PURCHASING BEHAVIOUR USING HYBRID MODEL

Abstract

High profitable rare item sets, is an approach to extract out all the products that emerges high profit over selling. Data mining is a technique that collects data and figure out all relevant products which urges high profit over selling and having high margins. In this chapter, keeping in mind customers’ purchasing behavior, profitable rare item sets, actually want to figure out all those products which can earn us high margin profit, selling of these products through e-trade can lead us with high profit. Rare item sets mining is a challenging task where the key issues are- identifying interesting rare patterns and efficiently discovering them in large datasets, This data can contribute to have high access to all those products which are rarely purchased but consuming high margins, which in future can lead to high business utilities in e-trade .The development of a sequential pattern mining framework based on LSTM networks, enhancing the deep learning framework with advanced techniques, evaluating the proposed approach's performance, and providing valuable insights and recommendations based on the discovered high utility item sets. By achieving these objectives, this research aims to contribute to the advancement of high utility item set mining techniques and provides practical solutions for businesses to extract valuable insights from their transactional datasets & samples.