No more ready-made deals: constructive recommendation for telco service bundling

We propose a new recommendation system for service and product bundling in the domain of telecommunication and multimedia. Using this system, users can easily generate a combined service plan that best suits their needs within a vast range of candidates. The system exploits the recent constructive preference elicitation framework, which allows us to flexibly model the exponentially large domain of bundle offers as an implicitly defined set of variables and constraints. The user preferences are modeled by a utility function estimated via coactive learning interaction, while iteratively generating high-utility recommendations through constraint optimization. In this paper, we detail the structure of our system, as well as the methodology and results of an empirical validation study which involved more than 130 participants. The system turned out to be highly usable with respect to both time and number of interactions, and its outputs were found much more satisfactory than those obtained with standard techniques used in the market.

[1]  Thorsten Joachims,et al.  Coactive Learning , 2015, J. Artif. Intell. Res..

[2]  Junjun Li,et al.  Bundle recommendation in ecommerce , 2014, SIGIR.

[3]  A. Herrmann,et al.  Product and Service Bundling Decisions and their Effects on Purchase Intention , 1997 .

[4]  Gökhan BakIr,et al.  Predicting Structured Data , 2008 .

[5]  Markus Stumptner,et al.  Configuration Knowledge Representation and Reasoning , 2014 .

[6]  Liu Guo-rong,et al.  Collaborative Filtering Based Recommendation System for Product Bundling , 2006, 2006 International Conference on Management Science and Engineering.

[7]  Nathan Ratliff,et al.  Online) Subgradient Methods for Structured Prediction , 2007 .

[8]  Andrea Passerini,et al.  Constructive Preference Elicitation , 2018, Front. Robot. AI.

[9]  Scott Sanner,et al.  Real-time Multiattribute Bayesian Preference Elicitation with Pairwise Comparison Queries , 2010, AISTATS.

[10]  Gabriella Pigozzi,et al.  Preferences in artificial intelligence , 2016, Annals of Mathematics and Artificial Intelligence.

[11]  Xavier Martinez-Giralt,et al.  Bundling in telecommunications , 2008 .

[12]  Andrea Passerini,et al.  Decomposition Strategies for Constructive Preference Elicitation , 2017, AAAI.

[13]  Dietmar Jannach,et al.  Constraint-Based Recommendation in Tourism: A Multiperspective Case Study , 2009, J. Inf. Technol. Tour..

[14]  Lior Rokach,et al.  Recommender Systems for Product Bundling , 2016, RecSys Posters.

[15]  Alan Fern,et al.  Multitask Coactive Learning , 2015, IJCAI.

[16]  Andrea Passerini,et al.  Coactive Critiquing: Elicitation of Preferences and Features , 2016, AAAI.

[17]  Boi Faltings,et al.  Conversational recommenders with adaptive suggestions , 2007, RecSys '07.

[18]  Martin Zinkevich,et al.  Online Convex Programming and Generalized Infinitesimal Gradient Ascent , 2003, ICML.

[19]  Ronen I. Brafman,et al.  Reasoning With Conditional Ceteris Paribus Preference Statements , 1999, UAI.

[20]  Andrea Passerini,et al.  Constructive Preference Elicitation for Multiple Users with Setwise Max-margin , 2017, ADT.

[21]  Alan Fern,et al.  Coactive Learning for Locally Optimal Problem Solving , 2014, AAAI.

[22]  Eyke Hüllermeier,et al.  Preferences in AI: An overview , 2011, Artif. Intell..

[23]  Xuehong Du,et al.  Understanding customer satisfaction in product customization , 2006 .

[24]  Markus Zanker,et al.  Case-studies on exploiting explicit customer requirements in recommender systems , 2009, User Modeling and User-Adapted Interaction.

[25]  Thorsten Joachims,et al.  Online Learning with Preference Feedback , 2011, ArXiv.

[26]  Markus Zanker,et al.  Constraint-based personalised configuring of product and service bundles , 2010 .

[27]  Cipriano Forza,et al.  Sales configurator capabilities to avoid the product variety paradox: Construct development and validation , 2013, Comput. Ind..

[28]  Ching-I Teng,et al.  Customization, immersion satisfaction, and online gamer loyalty , 2010, Comput. Hum. Behav..

[29]  Darius Braziunas,et al.  Computational Approaches to Preference Elicitation , 2006 .

[30]  Eric J. Johnson,et al.  The adaptive decision maker , 1993 .

[31]  Sriram Thirumalai,et al.  Customization of the online purchase process in electronic retailing and customer satisfaction: An online field study , 2011 .

[32]  Ronen I. Brafman,et al.  Preference‐Based Constrained Optimization with CP‐Nets , 2004, Comput. Intell..

[33]  Peter J. Stuckey,et al.  MiniZinc: Towards a Standard CP Modelling Language , 2007, CP.

[34]  Andrea Passerini,et al.  Constructive Preference Elicitation over Hybrid Combinatorial Spaces , 2017, AAAI.

[35]  Andrea Passerini,et al.  Constructive Preference Elicitation by Setwise Max-Margin Learning , 2016, IJCAI.

[36]  Joshua S. Gans,et al.  Paying for Loyalty: Product Bundling in Oligopoly , 2004 .

[37]  Miroslaw McIlraith,et al.  Creating Customer Loyalty Through Service Customization , 2014 .

[38]  Jan Krämer.  Bundling telecommunications services : competitive strategies for converging markets , 2009 .

[39]  Alexander Felfernig,et al.  Constraint-based recommender systems: technologies and research issues , 2008, ICEC.

[40]  Markus Zanker,et al.  Preference reasoning with soft constraints in constraint-based recommender systems , 2010, Constraints.

[41]  Carmel Domshlak,et al.  Reasoning about soft constraints and conditional preferences: complexity results and approximation techniques , 2003, IJCAI.

[42]  R. L. Keeney,et al.  Decisions with Multiple Objectives: Preferences and Value Trade-Offs , 1977, IEEE Transactions on Systems, Man, and Cybernetics.

[43]  Craig Boutilier,et al.  Optimal Bayesian Recommendation Sets and Myopically Optimal Choice Query Sets , 2010, NIPS.

[44]  Yoram Singer,et al.  Efficient projections onto the l1-ball for learning in high dimensions , 2008, ICML '08.

[45]  Brian Roark,et al.  Incremental Parsing with the Perceptron Algorithm , 2004, ACL.

[46]  Craig Boutilier,et al.  A POMDP formulation of preference elicitation problems , 2002, AAAI/IAAI.

[47]  Paolo Dragone.  Constructive Layout Synthesis via Coactive Learning , 2016 .

[48]  Gerhard Friedrich,et al.  Constraint-Based Recommender Systems , 2015, Recommender Systems Handbook.

[49]  John W. Payne,et al.  The adaptive decision maker: Name index , 1993 .