A Novel Approach for Product Prediction Using Artificial Neural Networks

E-commerce business has grown at a rapid pace and buying products from E-commerce websites has become a very popular trend in modern society. Preferences of customers on various products can now be readily obtained on-line through various E-commerce Websites. As these E-commerce sites provide their customers with many choices they get in dilemma with this information and hence find it difficult to locate items of their interest. These E-commerce systems cannot offer one to one recommendation like a salesperson does and that’s why customers are not able to choose products of their choice and hence there is a risk of losing loyal customers. Our main concern is to fulfill the needs of every customer and increase the product sales. Efficiently mining this information can generate useful data for providing personalized product recommendation services. Artificial neural network (ANN) is one of the preferred tool for data mining and it’s a computational model based on biological neural networks, which consists of an interconnected group of neurons and it processes the information using a connection based approach. This paper presents a new approach using ANN that can be used to generate recommendations and help customers to satisfy their requirements. In this work the buying pattern of the students appearing for campus interviews has been taken into consideration and recommends the similar type of items to other student groups. The predicted values obtained by giving input data set and target (desired output) to ANN are quite satisfactory.

[1]  Norjihan Abdul Ghani,et al.  AN ARTIFICIAL NEURAL NETWORK CLASSIFICATION APPROACH FOR IMPROVING ACCURACY OF CUSTOMER IDENTIFICATION IN E-COMMERCE , 2014 .

[2]  Chetan Kalyan,et al.  Recommendation of High Quality Representative Reviews in e-commerce , 2017, RecSys.

[3]  Hoang Pham.  Reliability management and computing , 2016, Ann. Oper. Res..

[4]  John Riedl,et al.  Is seeing believing?: how recommender system interfaces affect users' opinions , 2003, CHI '03.

[5]  Loriene Roy,et al.  Content-based book recommending using learning for text categorization , 1999, DL '00.

[6]  Haitao Li,et al.  A hybrid collaborative filtering recommendation mechanism for P2P networks , 2010, Future Gener. Comput. Syst..

[7]  Donghee Yoo,et al.  A hybrid online-product recommendation system: Combining implicit rating-based collaborative filtering and sequential pattern analysis , 2012, Electron. Commer. Res. Appl..

[8]  Hsinchun Chen,et al.  A graph model for E-commerce recommender systems , 2004, J. Assoc. Inf. Sci. Technol..

[9]  Paul Jen-Hwa Hu,et al.  A cost-sensitive technique for positive-example learning supporting content-based product recommendations in B-to-C e-commerce , 2012, Decis. Support Syst..

[10]  Sean M. McNee,et al.  Being accurate is not enough: how accuracy metrics have hurt recommender systems , 2006, CHI Extended Abstracts.

[11]  Greg Linden,et al.  Amazon . com Recommendations Item-to-Item Collaborative Filtering , 2001 .

[12]  S. M. Kamruzzaman,et al.  A Constructive Algorithm for Feedforward Neural Networks for Medical Diagnostic Reasoning , 2010, ArXiv.

[13]  Kuang-Ku Chen,et al.  Integrating web mining and neural network for personalized e-commerce automatic service , 2010, Expert Syst. Appl..

[14]  Dietmar Jannach,et al.  Adaptation and Evaluation of Recommendations for Short-term Shopping Goals , 2015, RecSys.

[15]  Ling Guan,et al.  A hybrid approach for personalized recommendation of news on the Web , 2012, Expert Syst. Appl..

[16]  Robin D. Burke,et al.  Hybrid Recommender Systems: Survey and Experiments , 2002, User Modeling and User-Adapted Interaction.

[17]  Bart P. Knijnenburg,et al.  Explaining the user experience of recommender systems , 2012, User Modeling and User-Adapted Interaction.

[18]  Sean M. McNee,et al.  Improving recommendation lists through topic diversification , 2005, WWW '05.

[19]  Prakash P. Shenoy,et al.  A new heuristic for learning Bayesian networks from limited datasets: a real-time recommendation system application with RFID systems in grocery stores , 2012, Annals of Operations Research.