Paper Session 4: Travel and Entertainment

Date: Thursday, Oct 4, 2018, 16:00-17:30
Location: Parq D/E/F
Chair: Alan Hanjalic

  • LPNo More Ready-made Deals: Constructive Recommendation for Telco Service Bundling
    by Paolo Dragone, Giovanni Pellegrini, Michele Vescovi, Katya Tentori, Andrea Passerini

    We propose a new constraint-based recommendation system for service and product bundling in the domain of telecommunication and multimedia. Using this system, users can easily generate the combined service plan (including broadband, mobile connection, media content subscription, and device leasing, akin to those commonly offered by telco operators) that best suits their needs within a vast range of candidates. The system exploits the recent constructive preference elicitation framework, which brings together the benefits of constraint-based recommenders and data-driven preference learning algorithms. The feasible space of possible plans is implicitly defined by a set of variables (components) and constraints, which allows us to flexibly model an exponentially large solution domain (bundle offers) without the need of explicitly enumerating a-priori all admissible configurations. The preferences of the user are modeled by a utility function over the components of the plan. The utility parameters are estimated by interacting with the user via coactive learning. Recommendations are generated by structured-output prediction, which in our case translates into solving a constraint optimization problem to find the feasible configuration with the highest utility. In this paper, we detail the structure of our system, the underlying learning technique, 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.

    Full text in ACM Digital Library

  • LPPreference Elicitation as an Optimization Problem
    by Anna Sepliarskaia, Julia Kiseleva, Filip Radlinski, Maarten de Rijke

    The new user cold-start problem arises when a recommender system does not yet have any information about a user. A common solution to this problem is to generate a user profile as part of the sign-up process, by asking the user to rate several items. We propose a new elicitation method to generate a static preference questionnaire (SPQ) that asks a new user to make pairwise comparisons between items by posing relative preference questions. Using a latent factor model, SPQ improves personalized recommendations by choosing a minimal and diverse set of static preference questions to ask any new user. We are the first to rigorously prove which optimization task should be solved in order to select the next preference question for static questionnaires. Our theoretical results are confirmed by extensive experimentation. We test the performance of SPQ on two real-world datasets, under two experimental conditions: simulated, when users behave according to LFM, and real, in which there is no user rating model. SPQ reduces the questionnaire length that is necessary to make accurate recommendations for new users by up to a factor of three compared to state-of-the-art preference elicitation methods. Moreover, solving the right optimization task, SPQ shows better performance than baselines with dynamically generated questions.

    Full text in ACM Digital Library

  • LPComfRide: A Smartphone based System for Comfortable Public Transport Recommendation
    by Rohit Verma, Surjya Ghosh, Saketh Mahankali, Niloy Ganguly, Bivas Mitra, Sandip Chakraborty

    Passenger comfort is a major factor influencing a commuter’s decision to avail public transport. Existing studies suggest that factors like overcrowding, jerkiness, traffic congestion etc. correlate well to passenger’s (dis)comfort. An online survey conducted with more than 300 participants from 12 different countries reveals that different personalized and context dependent factors influence passenger comfort during a travel by public transport. Leveraging on these findings, we identify correlations between comfort level and these dynamic parameters, and implement a smartphone based application, ComfRide, which recommends the most comfortable route based on user’s preference honoring her travel time constraint. We use a ‘Dynamic Input/Output Automata’ based composition model to capture both the wide varieties of comfort choices from the commuters and the impact of environment on the comfort parameters. Evaluation of ComfRide, involving 50 participants over 28 routes in a state capital of India, reveals that recommended routes have on average 30% better comfort level than Google map recommended routes, when a commuter gives priority to specific comfort parameters of her choice.

    Full text in ACM Digital Library

  • SPOUnderstanding User Interactions with Podcast Recommendations Delivered Via Voice
    by Longqi Yang, Michael Sobolev, Christina Tsangouri, Deborah Estrin

    Voice interfaces introduced by smart speakers present new opportunities and challenges for podcast content recommendations. Understanding how users interact with voice-based recommendations has the potential to inform better design of vocal recommenders. However, existing knowledge about user behavior is mostly for visual interfaces, such as the web, and is not directly transferable to voice interfaces, which rely on user listening and do not support skimming and browsing. To fill in the gap, in this paper, we conduct a controlled study to compare user interactions with recommendations delivered visually and vocally. Through an online A-B testing with 100 participants, we find that, when recommendations are vocally conveyed, users consume more slowly, explore less, and choose fewer long-tail items. The study also reveals the correlation between user choices and exploration via the voice interface. Our findings provide challenges to the design of voice interfaces, such as increasing the diversity of the top-ranked recommendations and designing better navigation mechanisms.

    Full text in ACM Digital Library

  • SPODeep Inventory Time Translation to Improve Recommendations for Real-World Retail
    by Bobby Prévost, Jonathan Laflamme Janssen, Jaime R. Camacaro, Carolina Bessega

    Recommender systems are an important component in the retail industry, but the constantly renewed inventory of many companies makes it di cult to aggregate enough data to fully harness the bene ts of such systems. In this paper, we describe a technique that significantly improves the accuracy of the recommendations, validated on real store transaction history, by performing a time translation that maps out-of-stock items to similar items that are currently in stock using deep features of the products. This reduces greatly the dimension of the item–item interactions matrix while preserving all the dataset entries, which mitigates the sparsity of the dataset, and provides an original solution to the cold-start problem. We also improve the coverage at no accuracy cost by favouring less popular items within a small radius in the feature space while applying the time translation mapping. Finally, by modelling item–item rather that user–item correlations, we are able to update item recommendations for a given user in real-time, without re-training, as the user’s history receives new entries.

    Full text in ACM Digital Library

  • LPThe Art of Drafting: A Team-Oriented Hero Recommendation System for Multiplayer Online Battle Arena Games
    by Zhengxing Chen, Truong-Huy D. Nguyen, Yuyu Xu, Chris Amato, Seth Cooper, Yizhou Sun, Magy Seif El-Nasr

    Multiplayer Online Battle Arena (MOBA) games have received increasing popularity recently. In a match of such games, players compete in two teams of five, each controlling an in-game avatars, known as heroes, selected from a roster of more than 100. The selection of heroes, also known as pick or draft, takes place before the match starts and alternates between the two teams until each player has selected one hero. Heroes are designed with different strengths and weaknesses to promote team cooperation in a game. Intuitively, heroes in a strong team should complement each other’s strengths and suppressing those of opponents. Hero drafting is therefore a challenging problem due to the complex hero-to-hero relationships to consider. In this paper, we propose a novel hero recommendation system that suggests heroes to add to an existing team while maximizing the team’s prospect for victory. To that end, we model the drafting between two teams as a combinatorial game and use Monte Carlo Tree Search (MCTS) for estimating the values of hero combinations. Our empirical evaluation shows that hero teams drafted by our recommendation algorithm have significantly higher win rate against teams constructed by other baseline and state-of-the-art strategies.

    Full text in ACM Digital Library

Back to Program

Diamond Supporter
Platinum Supporters
Gold Supporters
Silver Supporters
Special Supporter