Improvement of E-Commerce Recommendation Systems with Deep Hybrid Collaborative Filtering with Content: A Case Study

Abstract This paper presents a proposition to utilize flexible neural network architecture called Deep Hybrid Collaborative Filtering with Content (DHCF) as a product recommendation engine. Its main goal is to provide better shopping suggestions for customers on the e-commerce platform. The system was tested on 2018 Amazon Reviews Dataset, using repeated cross validation and compared with other approaches: collaborative filtering (CF) and deep collaborative filtering (DCF) in terms of mean squared error (MSE), mean absolute error (MAE) and mean absolute percentage error (MAPE). DCF and DHCF were proved to be significantly better than the CF. DHCF proved to be better than DCF in terms of MAE and MAPE, it also scored the best on separate test data. The significance of the differences was checked by means of a Friedman test, followed by post-hoc comparisons to control p-value. The experiment shows that DHCF can outperform other approaches considered in the study, with more robust scores.

[1]  Julian J. McAuley,et al.  Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering , 2016, WWW.

[2]  Florian Strub,et al.  Hybrid Recommender System based on Autoencoders , 2018 .

[3]  Anabela Afonso,et al.  Overview of Friedman’s Test and Post-hoc Analysis , 2015, Commun. Stat. Simul. Comput..

[4]  Eibe Frank,et al.  Evaluating the Replicability of Significance Tests for Comparing Learning Algorithms , 2004, PAKDD.

[5]  Andrew W. Moore,et al.  Efficient Algorithms for Minimizing Cross Validation Error , 1994, ICML.

[6]  Anh Duc Duong,et al.  Addressing cold-start problem in recommendation systems , 2008, ICUIMC '08.

[7]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[8]  James She,et al.  Collaborative Variational Autoencoder for Recommender Systems , 2017, KDD.

[9]  Jianmo Ni,et al.  Justifying Recommendations using Distantly-Labeled Reviews and Fine-Grained Aspects , 2019, EMNLP.

[10]  S. Holm.  A Simple Sequentially Rejective Multiple Test Procedure , 1979 .

[11]  Richard A Armstrong,et al.  When to use the Bonferroni correction , 2014, Ophthalmic & physiological optics : the journal of the British College of Ophthalmic Opticians.

[12]  Fabrice Rossi,et al.  Reducing Offline Evaluation Bias in Recommendation Systems , 2014, ArXiv.

[13]  Tat-Seng Chua,et al.  Neural Collaborative Filtering , 2017, WWW.

[14]  H. Cabral,et al.  Multiple Comparisons Procedures , 2008, Circulation.

[15]  Vasudeva Varma,et al.  Neural Content-Collaborative Filtering for News Recommendation , 2018, NewsIR@ECIR.

[16]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[17]  Anton van den Hengel,et al.  Image-Based Recommendations on Styles and Substitutes , 2015, SIGIR.

[18]  Shawn P. Curley,et al.  De-biasing user preference ratings in recommender systems completed research paper , 2014, RecSys 2014.

[19]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[20]  Pattie Maes,et al.  Social information filtering: algorithms for automating “word of mouth” , 1995, CHI '95.

[21]  Sophie Ahrens,et al.  Recommender Systems , 2012 .

[22]  Sameer Singh,et al.  “Why Should I Trust You?”: Explaining the Predictions of Any Classifier , 2016, NAACL.

[23]  M. Tim Jones.  Recommender systems , Part 1 : Introduction to approaches and algorithms Learn about the concepts that underlie web recommendation engines , 2015 .

[24]  Janez Demsar,et al.  Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

[25]  Nonparametric Statistical Analysis. , 2020, JAMA.

[26]  Guy Shani,et al.  Evaluating Recommendation Systems , 2011, Recommender Systems Handbook.

[27]  Cullen Schaffer,et al.  Selecting a classification method by cross-validation , 1993, Machine Learning.

[28]  Xiaoyu Du,et al.  Outer Product-based Neural Collaborative Filtering , 2018, IJCAI.

[29]  Huanbo Luan,et al.  Discrete Collaborative Filtering , 2016, SIGIR.

[30]  Francisco Herrera,et al.  A study of statistical techniques and performance measures for genetics-based machine learning: accuracy and interpretability , 2009, Soft Comput..

[31]  Lars Schmidt-Thieme,et al.  BPR: Bayesian Personalized Ranking from Implicit Feedback , 2009, UAI.

[32]  Michael Marien,et al.  Book Review: The Second Machine Age: Work, Progress, and Prosperity in a Time of Brilliant Technologies , 2014 .

[33]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[34]  Chin-Hui Lee,et al.  On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression , 2020, IEEE Signal Processing Letters.

[35]  John Riedl,et al.  Item-based collaborative filtering recommendation algorithms , 2001, WWW '01.

[36]  Zbigniew Telec,et al.  Nonparametric statistical analysis for multiple comparison of machine learning regression algorithms , 2012, Int. J. Appl. Math. Comput. Sci..

[37]  Mehrbakhsh Nilashi,et al.  Collaborative filtering recommender systems , 2013 .

[38]  Douglas B. Terry,et al.  Using collaborative filtering to weave an information tapestry , 1992, CACM.

[39]  Sanjay Krishnan,et al.  A methodology for learning, analyzing, and mitigating social influence bias in recommender systems , 2014, RecSys '14.

[40]  John Riedl,et al.  GroupLens: an open architecture for collaborative filtering of netnews , 1994, CSCW '94.

[41]  Scott Sanner,et al.  AutoRec: Autoencoders Meet Collaborative Filtering , 2015, WWW.