Image content-based user preference elicitation for personalised mobile recommendation of shopping items

Abstract

Personalised recommendation of product items has been recognised as an exciting snug suggestion for an individual customer. This is required to meet the preferences of an individual customer and improve the sales of merchants. Most current research works in content-based recommendation heavily relied on an orthodox 2-dimensional “user by item” data structure has been used extensively in different application areas for product items recommendation. However, this structure is limited in delivering personalised recommendations to mobile customers because of the inherent “problem of concept drift” that can result in degrading the performance of a recommendation system. This research work introduces an image content-based preference elicitation model based on the approach of supervised machine learning to deliver personalised product items recommendation to mobile customers. This model of product items recommendation leverages the extraction of multiple aspects of item dynamic features to characterise the preferences of mobile customers. This will help mobile customers and nomadic to pervasively discover product items that are most relevant to their interests and reduce barriers to purchase. To start with, a new image-based item classification framework that leverages a novel 4-dimensional colour image representation and Eigen-colour features is built to realise efficient item-class features. The framework is devised to realise a timedependent item relevance score for selecting a set of product items of interest. These features were integrated with other features such as price, location, and incentive associated with a product item to improve the performance of a shopping recommendation system. This is to build the proposed design towards addressing the concept drift problem and large recommendation space problems often associated with the orthodox items recommendation systems. Experimental results of testing an implementation of the proposed item classification framework have shown a recommendation system to produce low-dimensional item features and an implicit shortterm preference profile for a new system user with recommendation accuracy of 92.2% on popular PI100 e-commerce shopping items corpus. Moreover, another experiment on item-based multiple criteria decision-making techniques has revealed that multiple factors can adequately address the concept drift problem. The proposed technique spawns better top-5, top-10, and top-15 rank personalised recommendation accuracy results when compared to the orthodox content-based approach. Finally, as a proof of concept, an imaging interface that anchors the proposed framework in a client-server system was simulated on a mobile phone