Analysis of GA Optimized ANN for Proactive Context Aware Recommender System

A Recommender System essentially focusses on recommending the most significant items to the users based on their preferences. The objective of a recommender system is to create relevant suggestions to the users for the items like foods for a restaurant etc. based on their interests. The traditional recommender systems put forward recommendations to the users without taking in account any of the considerations about the contextual information like time and place etc. This paper explicates a way to deal with restaurant based recommender system by utilizing a hybrid approach namely ‘genetic algorithm optimized artificial neural network’ to yield higher precision and accuracy in prescribing relevant items to the users based on their preferences and interests. Here, a system of a ‘context aware recommender system’ is implemented that suggests diverse sorts of things proactively to the users. This system involves implementation of the artificial neural network technique that will do the reasoning of the context to figure out whether to throw a recommendation or not and what kind of items to prescribe to the users proactively depending on their interests. The artificial neural network inputs are virtually taken from the Internet of things and its outputs are the scores based on the type of recommendations. These scores have been utilized to choose whether to throw a recommendation or not. This study represents strong potential for prescribing relevant items to the users utilizing the hybrid methodology of “genetic algorithm optimized artificial neural network” for ‘context aware recommender system’ with higher precision and accuracy.

[1]  Jöran Beel,et al.  A comparative analysis of offline and online evaluations and discussion of research paper recommender system evaluation , 2013, RepSys '13.

[2]  George D. C. Cavalcanti,et al.  A graph-based friend recommendation system using Genetic Algorithm , 2010, IEEE Congress on Evolutionary Computation.

[3]  Haohan Liu,et al.  Overview Of Context-aware Recommender System Research , 2015, ICM 2015.

[4]  Madjid Tavana,et al.  A secured context-aware tourism recommender system using artificial bee colony and simulated annealing , 2016 .

[5]  Sarah S. Lam,et al.  Customers' Behavior Prediction Using Artificial Neural Network , 2013 .

[6]  Chein-Shung Hwang,et al.  Using Genetic Algorithms for Personalized Recommendation , 2010, ICCCI.

[7]  Pradip N. Shendage.  Review on Collaborative Filtering and Web Services Recommendation , 2014 .

[8]  P. A. Khodke,et al.  Genetic Algorithm Based Similarity Transitivity in Collaborative Filtering , 2013 .

[9]  akumar,et al.  A Survey on Methodologies for PersonalizedE-learning Recommender Systems , 2014 .

[10]  Jianfeng Ma,et al.  FCT: a fully-distributed context-aware trust model for location based service recommendation , 2017, Science China Information Sciences.

[11]  Kyoung-jae Kim,et al.  Using a Clustering Genetic Algorithm to Support Customer Segmentation for Personalized Recommender Systems , 2004, AIS.

[12]  Yi Zhang,et al.  Contextual Recommendation based on Text Mining , 2010, COLING.

[13]  Gediminas Adomavicius,et al.  Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.

[14]  Iyad Tumar,et al.  A Proactive Multi-type Context-Aware Recommender System in the Environment of Internet of Things , 2015, 2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing.

[15]  Erik Duval,et al.  Context-Aware Recommender Systems for Learning: A Survey and Future Challenges , 2012, IEEE Transactions on Learning Technologies.

[16]  Gediminas Adomavicius,et al.  Context-aware recommender systems , 2008, RecSys '08.