Mobile recommendations based on interest prediction from consumer's installed apps-insights from a large-scale field study

Abstract Recommender systems are essential in mobile commerce to benefit both companies and individuals by offering highly personalized products and services. One key pre-requirement of applying such systems is to gain decent knowledge about each individual consumer through user profiling. However, most existing profiling approaches on mobile suffer problems such as non-real-time, intrusive, cold-start, and non-scalable, which prevents them from being adopted in reality. To tackle the problems, this work developed real-time machine-learning models to predict user profiles of smartphone users from openly accessible data, i.e. app installation logs. Results from a study with 904 participants showed that the models are able to predict interests on average 48.81% better than a random guess in terms of precision and 13.80% better in terms of recall. Since the effectiveness of such predictive models is unknown in practice, the predictive models were evaluated in a large-scale field experiment with 73,244 participants. Results showed that by leveraging our models, personalized mobile recommendations can be enabled and the corresponding click-through-rate can be improved by up to 228.30%. Supplementary information, study data, and software can be found at https://www.autoidlabs.ch/mobile-analytics .

[1]  Elgar Fleisch,et al.  Understanding the impact of personality traits on mobile app adoption - Insights from a large-scale field study , 2016, Comput. Hum. Behav..

[2]  John Riedl,et al.  Analysis of recommendation algorithms for e-commerce , 2000, EC '00.

[3]  Yinghui Yang,et al.  Web user behavioral profiling for user identification , 2010, Decis. Support Syst..

[4]  Taghi M. Khoshgoftaar,et al.  Machine prediction of personality from Facebook profiles , 2012, 2012 IEEE 13th International Conference on Information Reuse & Integration (IRI).

[5]  Hamido Fujita,et al.  Personality Estimation Application for Social Media , 2012, SoMeT.

[6]  Tu Minh Phuong,et al.  Gender Prediction Using Browsing History , 2013, KSE.

[7]  Michel Wedel,et al.  Up close and personalized: a marketing view of recommendation systems , 2009, RecSys '09.

[8]  Zachary Miller,et al.  Author Gender Prediction in an Email Stream Using Neural Networks , 2012 .

[9]  Barry Smyth,et al.  A personalised TV listings service for the digital TV age , 2000, Knowl. Based Syst..

[10]  Jonathan L. Herlocker,et al.  Evaluating collaborative filtering recommender systems , 2004, TOIS.

[11]  Alex Pentland,et al.  Predicting Personality Using Novel Mobile Phone-Based Metrics , 2013, SBP.

[12]  Hua Li,et al.  Demographic prediction based on user's browsing behavior , 2007, WWW '07.

[13]  Boi Faltings,et al.  Offline and online evaluation of news recommender systems at swissinfo.ch , 2014, RecSys '14.

[14]  Hyunju Lee,et al.  Characterizing user interest using heterogeneous media , 2014, WWW '14 Companion.

[15]  Sung-Shun Weng,et al.  Personalized product recommendation in e-commerce , 2004, IEEE International Conference on e-Technology, e-Commerce and e-Service, 2004. EEE '04. 2004.

[16]  Alexander Ilic,et al.  Towards Understanding the Impact of Personality Traits on Mobile App Adoption - A Scalable Approach , 2015, ECIS.

[17]  Chris Hand,et al.  Internet advertising effectiveness , 2007 .

[18]  Martin Wetzels,et al.  The personalization-privacy paradox: implications for new media , 2016 .

[19]  Philip K. Chan,et al.  Learning implicit user interest hierarchy for context in personalization , 2003, IUI.

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

[21]  Zachary Miller,et al.  Gender Prediction on Twitter Using Stream Algorithms with N-Gram Character Features , 2012 .

[22]  Victor C. S. Lee,et al.  Exploring cell tower data dumps for supervised learning-based point-of-interest prediction , 2014, SIGSPATIAL/GIS.

[23]  Prasant Mohapatra,et al.  Your Installed Apps Reveal Your Gender and More! , 2015, MOCO.

[24]  Félix Hernández-del-Olmo,et al.  Evaluation of recommender systems: A new approach , 2008, Expert Syst. Appl..

[25]  Prasant Mohapatra,et al.  Predicting user traits from a snapshot of apps installed on a smartphone , 2014, MOCO.

[26]  Dietmar Jannach,et al.  Effectiveness of Different Recommender Algorithms in the Mobile Internet: A Case Study , 2009, ITWP.

[27]  Xia Wang,et al.  Collaborative Topic Prediction Model for User Interest Recommendation in Online Social Networks , 2012 .

[28]  Jason J. Jung Collaborative Web Browsing Based on Semantic Extraction of User Interests with Bookmarks , 2005, J. Univers. Comput. Sci..

[29]  Daniel Gatica-Perez,et al.  Mining large-scale smartphone data for personality studies , 2013, Personal and Ubiquitous Computing.

[30]  Daniela M. Witten,et al.  An Introduction to Statistical Learning: with Applications in R , 2013 .

[31]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[32]  Nadia Mana,et al.  Multimodal recognition of personality traits in social interactions , 2008, ICMI '08.

[33]  David N. Chin,et al.  Social Media Sources for Personality Profiling , 2014, UMAP Workshops.

[34]  Michael J. Pazzani,et al.  A Framework for Collaborative, Content-Based and Demographic Filtering , 1999, Artificial Intelligence Review.

[35]  Keith W. Ross,et al.  What's in a Name: A Study of Names, Gender Inference, and Gender Behavior in Facebook , 2011, DASFAA Workshops.

[36]  O. J. Dunn Multiple Comparisons Using Rank Sums , 1964 .

[37]  Berkant Barla Cambazoglu,et al.  Chat Mining for Gender Prediction , 2006, ADVIS.

[38]  A. M. Madni,et al.  Recommender systems in e-commerce , 2014, 2014 World Automation Congress (WAC).

[39]  Li Shang,et al.  Interest-based real-time content recommendation in online social communities , 2012, Knowl. Based Syst..

[40]  S. Thompson,et al.  Frazzled by Facebook? An Exploratory Study of Gender Differences in Social Network Communication among Undergraduate Men and Women , 2012 .

[41]  Rich Caruana,et al.  An empirical evaluation of supervised learning in high dimensions , 2008, ICML '08.

[42]  H. Jeff Smith,et al.  Information Privacy: Measuring Individuals' Concerns About Organizational Practices , 1996, MIS Q..

[43]  Changjun Jiang,et al.  User Interest Detection on Web Pages for Building Personalized Information Agent , 2004, WAIM.

[44]  Liangrui Peng,et al.  XFace: A Face Recognition System for Android Mobile Phones , 2015, 2015 IEEE 3rd International Conference on Cyber-Physical Systems, Networks, and Applications.

[45]  Jacob Cohen,et al.  A power primer. , 1992, Psychological bulletin.

[46]  Chi-Yin Chow,et al.  GeoSoCa: Exploiting Geographical, Social and Categorical Correlations for Point-of-Interest Recommendations , 2015, SIGIR.

[47]  Rung Ching Chen,et al.  A Domain Ontology in Social Networks for Identifying User Interest for Personalized Recommendations , 2016, J. Univers. Comput. Sci..

[48]  Javed Mostafa,et al.  Topic detection and interest tracking in a dynamic online news source , 2003, 2003 Joint Conference on Digital Libraries, 2003. Proceedings..

[49]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[50]  William W. Cohen,et al.  Recommendation as Classification: Using Social and Content-Based Information in Recommendation , 1998, AAAI/IAAI.

[51]  R. Rosenthal Parametric measures of effect size. , 1994 .

[52]  Saul Vargas,et al.  Rank and relevance in novelty and diversity metrics for recommender systems , 2011, RecSys '11.

[53]  Duc Duong,et al.  Customer gender prediction based on E-commerce data , 2016, 2016 Eighth International Conference on Knowledge and Systems Engineering (KSE).

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

[55]  Michael Roberts,et al.  Unsupervised Modeling of Users' Interests from their Facebook Profiles and Activities , 2015, IUI.

[56]  Victor C. S. Lee,et al.  Exploring cell tower data dumps for supervised learning-based point-of-interest prediction (industrial paper) , 2016, GeoInformatica.

[57]  Peng-Ting Chen,et al.  Personalized mobile advertising: Its key attributes, trends, and social impact , 2012 .

[58]  D. Bamber The area above the ordinal dominance graph and the area below the receiver operating characteristic graph , 1975 .

[59]  Cyril W. Cleverdon,et al.  Factors determining the performance of indexing systems , 1966 .

[60]  Mark Claypool,et al.  Combining Content-Based and Collaborative Filters in an Online Newspaper , 1999, SIGIR 1999.

[61]  Alexander Ilic,et al.  Reality-Mining with Smartphones: Detecting and Predicting Life Events based on App Installation Behavior , 2015, ICIS.

[62]  M. Wedel,et al.  The Effectiveness of Customized Promotions in Online and Offline Stores , 2009 .

[63]  Tao Luo,et al.  Discovery and Evaluation of Aggregate Usage Profiles for Web Personalization , 2004, Data Mining and Knowledge Discovery.

[64]  Tim O'Reilly,et al.  What is Web 2.0: Design Patterns and Business Models for the Next Generation of Software , 2007 .

[65]  W. Kruskal,et al.  Use of Ranks in One-Criterion Variance Analysis , 1952 .

[66]  Xiaoming Liu,et al.  Demographic Estimation from Face Images: Human vs. Machine Performance , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[67]  Alexander Ilic,et al.  Individual Differences and Mobile Service Adoption: An Empirical Analysis , 2016, 2016 IEEE Second International Conference on Big Data Computing Service and Applications (BigDataService).