Accepted Contributions

List of all papers accepted for RecSys 2015 (in alphabetical order).

No matches were found!
  • A Probabilistic Model for Using Social Networks in Personalized Item Recommendation
    by Allison J.B. Chaney, David M. Blei and Tinpa Eliassi-Rad

    Preference-based recommendation systems have transformed how we consume media. By analyzing usage data, these methods uncover our latent preferences for items (such as articles or movies) and form recommendations based on the behavior of others with similar tastes. But traditional preference-based recommendations do not account for the social aspect of consumption, where a trusted friend might point us to an interesting item that does not match our typical preferences. In this work, we aim to bridge the gap between preference- and social-based recommendations. We develop social Poisson factorization (SPF), a probabilistic model that incorporates social network information into a traditional factorization method; SPF introduces the social aspect to algorithmic recommendation. We develop a scalable algorithm for analyzing data with SPF, and demonstrate that it outperforms competing methods on six real-world datasets; data sources include a social reader and Etsy.

    Session 1b: Recommender Systems and Social Networks

  • Adaptation and Evaluation of Recommendations for Short-term Shopping Goals
    by Dietmar Jannach, Lukas Lerche and Michael Jugovac

    An essential characteristic in many of e-commerce settings is that website visitors can have very specific short-term shopping goals when they browse the site. Relying solely on long-term user models that are pre-trained on historical data can therefore be insufficient for recommendation. Simple “real-time” recommendation approaches based, e.g., on unpersonalized co-occurrence patterns, on the other hand do not fully exploit the available information about the user’s long-term preference profile.

    In this work, we aim to explore and quantify the effectiveness of using and combining long-term models and short-term adaptation strategies. We conducted an empirical evaluation based on a novel evaluation design and two real-world datasets. The results indicate that maintaining short-term content-based and recency-based profiles of the visitors can lead to significant accuracy increases. At the same time, the experiments show that the choice of the algorithm for learning the long term preferences is particularly important at the beginning of new shopping sessions.

    Session 5b: E-commerce & Ads

  • Applying Differential Privacy to Matrix Factorization
    by Arnaud Berlioz, Arik Friedman, Mohamed Ali Kafaar, Roksana Boreli and Shlomo Berkovsky

    Recommender systems are increasingly becoming an integral part of on-line services. As the recommendations rely on personal user information, there is an inherent loss of privacy resulting from the use of such systems. While several works studied privacy-enhanced neighborhood-based recommendations, little attention has been paid to privacy preserving latent factor models, like those represented by matrix factorization techniques. In this paper, we address the problem of privacy preserving matrix factorization by utilizing differential privacy, a rigorous and provable privacy preserving method. We propose and study several approaches for applying differential privacy to matrix factorization, and evaluate the privacy-accuracy trade-offs offered by each approach. We show that input perturbation yields the best recommendation accuracy, while guaranteeing a solid level of privacy protection.

    Session 3: Distinguished Papers

  • Beyond ‘Hitting the Hits’ – Generating Coherent Music Playlist Continuations with the Right Tracks
    by Dietmar Jannach, Lukas Lerche and Iman Kamehkhosh

    Automated playlist generation is a special form of music recommendation and a common feature of digital music playing applications. A particular challenge of the task is that the recommended items should not only match the general listener’s preference but should also be coherent with the most recently played tracks. In this work, we propose a novel algorithmic approach and optimization scheme to generate playlist continuations that address these requirements. In our approach, we first use collections of shared music playlists, music metadata, and user preferences to select suitable tracks with high accuracy. Next, we apply a generic re-ranking optimization scheme to generate playlist continuations that match the characteristics of the last played tracks. An empirical evaluation on three collections of shared playlists shows that the combination of different input signals helps us to achieve high accuracy during track selection and that the re-ranking technique can both help to balance different quality optimization goals and to further increase accuracy.

    Session 5a: News and Media

  • Blockbusters and Wallflowers: Accurate, Diverse, and Scalable Recommendations with Random Walks
    by Fabian Christoffel, Bibek Paudel, Chris Newell and Abraham Bernstein

    User satisfaction is often dependent on providing accurate and diverse recommendations. In this paper, we explore scalable algorithms that exploit random walks as a sampling technique to obtain diverse recommendations without compromising on accuracy. Specifically, we present a novel graph vertex ranking recommendation algorithm called RP3beta that re-ranks items based on 3-hop random walk transition probabilities. We show empirically, that RP3beta provides accurate recommendations with high long-tail item frequency at the top of the recommendation list. We also present scalable approximate versions of RP3beta and the two most accurate previously published vertex ranking algorithms based on random walk transition probabilities and show that these approximations converge with increasing number of samples.

    Session 4b: Algorithms

  • Cold-Start Item and User Recommendation with Decoupled Completion and Transduction
    by Iman Barjasteh, Rana Forsati, Farzan Masrour, Abdol-Hossein Esfahanian and Hayder Radha

    A major challenge in collaborative filtering based recommender systems is how to provide recommendations when rating data is sparse or entirely missing for a subset of users or items, commonly known as the cold-start problem. In recent years, there has been considerable interest in developing new solutions that address the cold-start problem. These solutions are mainly based on the idea of exploiting other sources of information to compensate for the lack of rating data. In this paper, we propose a novel algorithmic framework based on matrix factorization that simultaneously exploits the similarity information among users and items to alleviate the cold-start problem. In contrast to existing methods, the proposed algorithm decouples the following two aspects of the cold-start problem: (a) the completion of a rating sub-matrix, which is generated by excluding cold-start users and items from the original rating matrix; and (b) the transduction of knowledge from existing ratings to cold-start items/users using side information. This crucial difference significantly boosts the performance when appropriate side information is incorporated. We provide theoretical guarantees on the estimation error of the proposed two-stage algorithm based on the richness of similarity information in capturing the rating data. To the best of our knowledge, this is the first algorithm that addresses the cold-start problem with provable guarantees. We also conduct thorough experiments on synthetic and real datasets that demonstrate the effectiveness of the proposed algorithm and highlights the usefulness of auxiliary information in dealing with both cold-start users and items.

    Session 2b: Cold Start and Hybrid Recommender Systems

  • Content Driven User Profiling for Comment-Worthy Recommendations of News and Blog Articles
    by Trapit Bansal, Mrinal Das and Chiranjib Bhattacharyya

    We consider the problem of recommending comment-worthy articles such as news and blog-posts. An article is defined to be comment-worthy for a particular user if that user is interested to leave a comment on it. We note that recommending comment-worthy articles calls for elicitation of commenting-interests of the user from the content of both the articles and the past comments made by users. We thus propose to develop content-driven user profiles to elicit these latent interests of users in commenting and use them to recommend articles for future commenting. The difficulty of modeling comment content and the varied nature of users’ commenting interests make the problem technically challenging.

    The problem of recommending comment-worthy articles is resolved by leveraging article and comment content through topic modeling and the co-commenting pattern of users through collaborative filtering, combined within a novel hierarchical Bayesian modeling approach. Our solution, Collaborative Correspondence Topic Models (CCTM), generates user profiles which are leveraged to provide a personalized ranking of comment-worthy articles for each user. Through these content-driven user profiles, CCTM effectively handle the ubiquitous problem of cold-start without relying on additional meta-data. The inference problem for the model is intractable with no off-the-shelf solution and we develop an efficient Monte Carlo EM algorithm. CCTM is evaluated on three real world data-sets, crawled from two blogs, ArsTechnica (AT) Gadgets (102,087 comments) and AT-Science (71,640 comments), and a news site, DailyMail (33,500 comments). We show average improvement of 14% (warm-start) and 18% (cold-start) in AUC, and 80% (warm-start) and 250% (cold-start) in Hit-Rank@5, over state of the art.

    Session 5a: News and Media

  • Context-Aware Event Recommendation in Event-based Social Networks
    by Augusto Q. Macedo, Leandro B. Marinho and Rodrygo L. T. Santos

    The Web has grown into one of the most important channels to communicate social events nowadays. However, the sheer volume of events available in event-based social networks (EBSNs) often undermines the users’ ability to choose the events that best fit their interests. Recommender systems appear as a natural solution for this problem, but differently from classic recommendation scenarios (e.g. movies, books), the event recommendation problem is intrinsically cold-start. Indeed, events published in EBSNs are typically short-lived and, by definition, are always in the future, having little or no trace of historical attendance. To overcome this limitation, we propose to exploit several contextual signals available from EBSNs. In particular, besides content-based signals based on the events’ description and collaborative signals derived from users’ RSVPs, we exploit social signals based on group memberships, location signals based on the users’ geographical preferences, and temporal signals derived from the users’ time preferences. Moreover, we combine the proposed signals for learning to rank events for personalized recommendation. Thorough experiments using a large crawl of demonstrate the effectiveness of our proposed contextual learning approach in contrast to state-of-the-art event recommenders from the literature.

    Session 3: Distinguished Papers

  • Dynamic Poisson Factorization
    by Laurent Charlin, Rajesh Ranganath, James McInerney and David M. Blei

    Models for recommender systems use latent factors to explain the preferences and behaviors of users with respect to a set of items (e.g., movies, books, academic papers). Typically, the latent factors are assumed to be static and, given these factors, the observed preferences and behaviors of users are assumed to be generated without order. These assumptions limit the explorative and predictive capabilities of such models, since users’ interests and item popularity may evolve over time. To address this, we propose dPF, a dynamic matrix factorization model based on the recent Poisson factorization model for recommendations. dPF models the time evolving latent factors with a Kalman filter and the actions with Poisson distributions. We derive a scalable variational inference algorithm to infer the latent factors. Finally, we demonstrate dPF on 10 years of user click data from, one of the largest repository of scientific papers and a formidable source of information about the behavior of scientists. Empirically we show performance improvement over both static and, more recently proposed, dynamic recommendation models. We also provide a thorough exploration of the inferred posteriors over the latent variables.

    Session 4b: Algorithms

  • E-commerce Recommendation with Personalized Promotion
    by Qi Zhao, Yi Zhang, Daniel Friedman and Fangfang Tan

    Most existing e-commerce recommender systems aim to recommend the right products to a consumer, assuming the properties of each product are fixed. However, some properties, including price discount, can be personalized to respond to each consumer’s preference. This paper studies how to automatically set the price discount when recommending a product, in light of the fact that the price often will alter a consumer’s purchase decision. The key to optimizing the discount is to predict consumer’s willingness-to-pay (WTP), namely, the highest price a consumer is willing to pay for a product. Purchase data used by traditional e-commerce recommender systems provide points below or above the decision boundary. In this paper we collected training data to better predict the decision boundary. We implement a new e-commerce mechanism adapted from laboratory lottery and auction experiments that elicit a rational customer’s exact WTP for a small subset of products, and use a machine learning algorithm to predict the customer’s WTP for other products. The mechanism is implemented on our own e-commerce website that leverages Amazon’s data and subjects recruited via Mechanical Turk. The experimental results demonstrate that the proposed approach can better predict WTP, dramatically improve conversion rate and sales revenue.

    Session 5b: E-commerce & Ads

  • ExcUseMe: Asking Users to Help in Item Cold-Start Recommendations
    by Michal Aharon, Oren Anava, Noa Avigdor-Elgrabli, Dana Drachsler-Cohen, Shahar Golan, and Oren Somekh

    The item cold-start problem is of a great importance in collaborative filtering (CF) recommendation systems. It arises when new items are added to the inventory and the system cannot model them properly since it relies solely on historical users’ interactions (e.g., ratings). Much work has been devoted to mitigate this problem mostly by employing hybrid approaches that combine content-based recommendation techniques or by devoting a portion of the user traffic for exploration to gather interactions from random users.

    We focus on pure CF recommender systems (i.e., without content or context information) in a realistic online setting, where random exploration is inefficient and smart exploration that carefully selects users is crucial due to the huge flux of new items with short lifespan. We further assume that users arrive randomly one after the other and that the system has to immediately decide whether the arriving user will participate in the exploration of the new items.

    For this setting we present ExcUseMe, a smart exploration algorithm that selects a predefined number of users for exploring new items. ExcUseMe gradually excavates the users that are more likely to be interested in the new items and models the new items based on the users’ interactions. We evaluated ExcUseMe on several datasets and scenarios and compared it to state-of-the-art algorithms. Experimental results indicate that ExcUseMe is an efficient algorithm that outperforms all other algorithms in all tested scenarios.

    Session 2b: Cold Start and Hybrid Recommender Systems

  • Exploiting Geo-Spatial Preference for Personalized Expert Recommendation
    by Haokai Lu and James Caverlee

    Experts are important for providing reliable and authoritative information and opinion, as well as for improving online reviews and services. While considerable previous research has focused on finding topical experts with broad appeal – e.g., top Java developers, best lawyers in Texas – we tackle the problem of personalized expert recommendation, to identify experts who have special personal appeal and importance to users. One of the key insights motivating our approach is to leverage the geo-spatial preferences of users and the variation of these preferences across different regions, topics, and social communities. Through a fine-grained GPS-tagged social media trace, we characterize these geo-spatial preferences for personalized experts, and integrate these preferences into a matrix factorization-based personalized expert recommender. Through extensive experiments, we find that the proposed approach can improve the quality of recommendation by 24% in precision compared to several baselines. We also find that users’ geo-spatial preference of expertise and their underlying social communities can ameliorate the cold start problem by more than 20% in precision and recall.

    Session 2a: Contextual Challenges

  • Fast Differentially Private Matrix Factorization
    by Ziqi Liu, Yu-Xiang Wang and Alexander J. Smola

    Differentially private collaborative filtering is a challenging task, both in terms of accuracy and speed. We present a simple algorithm that is provably differentially private, while offering good performance, using a novel connection of differential privacy to Bayesian posterior sampling via Stochastic Gradient Langevin Dynamics. Due to its simplicity the algorithm lends itself to efficient implementation. By careful systems design and by exploiting the power law behavior of the data to maximize CPU cache bandwidth we are able to generate 1024 dimensional models at a rate of 8.5 million recommendations per second on a single PC.

    Session 4b: Algorithms

  • Gaussian Ranking by Matrix Factorization
    by Harald Steck

    The ranking quality at the top of the list is crucial in many real-world applications of recommender systems. In this paper, we present a novel framework that allows for pointwise as well as listwise training with respect to various ranking metrics. This is based on a training objective function where we assume that, for given a user, the recommender system predicts scores for all items that follow approximately a Gaussian distribution. We motivate this assumption from the properties of implicit feedback data. As a model, we use matrix factorization and extend it by non-linear activation functions, as customary in the literature of artificial neural networks. In particular, we use non-linear activation functions derived from our Gaussian assumption. Our preliminary experimental results show that this approach is competitive with state-of-the-art methods with respect to optimizing the Area under the ROC curve, while it is particularly effective in optimizing the head of the ranked list.

    Session 3: Distinguished Papers

  • HyPER: A Flexible and Extensible Probabilistic Framework for Hybrid Recommender Systems
    by Pigi Kouki, Shobeir Fakhraei, James Foulds, Magdalini Eirinaki and Lise Getoor

    As the amount of recorded digital information increases, there is a growing need for flexible recommender systems which can incorporate richly structured data sources to improve recommendations. In this paper, we show how a recently introduced statistical relational learning framework can be used to develop a generic and extensible hybrid recommender system. Our hybrid approach, HyPER (HYbrid Probabilistic Extensible Recommender), incorporates and reasons over a wide range of information sources. Such sources include multiple user-user and item-item similarity measures, content, and social information. HyPER automatically learns to balance these different information signals when making predictions. We build our system using a powerful and intuitive probabilistic programming language called probabilistic soft logic, which enables efficient and accurate prediction by formulating our custom recommender systems with a scalable class of graphical models known as hinge-loss Markov random fields. We experimentally evaluate our approach on two popular recommendation datasets, showing that HyPER can effectively combine multiple information types for improved performance, and can outperform existing state-of-the-art approaches.

    Session 2b: Cold Start and Hybrid Recommender Systems

  • ‘I like to explore sometimes’: Adapting to Dynamic User Novelty Preferences
    by Komal Kapoor, Vikas Kumar, Loren Terveen, Joseph A. Konstan and Paul Schrater

    Studies have shown that the recommendation of unseen, novel or serendipitous items is crucial for a satisfying and engaging user experience. As a result, recent developments in recommendation research have increasingly focused towards introducing novelty in user recommendation lists. While, existing solutions aim to find the right balance between the similarity and novelty of the recommended items, they largely ignore the user needs for novelty. In this paper, we show that there are large individual and temporal differences in the users’ novelty preferences. We develop a regression model to predict these dynamic novelty preferences of users using features derived from their past interactions. Finally, we describe an adaptive recommender, adaNov-R, that adapts to the user needs for novel items and show that the model achieves better recommendation performance on a metric that considers both novel and familiar items.

    Session 1a: The User in the Loop

  • It Takes Two to Tango: an Exploration of Domain Pairs for Cross-Domain Collaborative Filtering
    by Shaghayegh Sahebi and Peter Brusilovsky

    As the heterogeneity of data sources are increasing on the web, and due to the sparsity of data in each of these data sources, cross-domain recommendation is becoming an emerging research topic in the recent years. Cross-domain collaborative filtering aims to transfer the user rating pattern from source (auxiliary) domains to a target domain for the purpose of alleviating the sparsity problem and providing better target recommendations. However, the studies so far have either focused on a limited number of domains that are assumed to be related to each other (such as books and movies), or a division of the same dataset (such as movies) into different domains based on an item characteristic (such as genre). In this paper, we study a broad set of domains and their characteristics to understand the factors that affect the success or failure of cross-domain collaborative filtering, the amount of improvement in cross-domain approaches, and the selection of best source domains for a specific target domain. We propose to use Canonical Correlation Analysis (CCA) as a significant major factor in finding the most promising source domains for a target domain, and suggest a cross-domain collaborative filtering based on CCA (CD-CCA) that proves to be successful in using the shared information between domains in the target recommendations.

    Session 4a: Novel Setups

  • Learning Distributed Representations from Reviews for Collaborative Filtering
    by Amjad Almahairi, Kyle Kastner, Kyunghyun Cho and Aaron Courville

    Recent work has shown that collaborative filter-based recommender systems can be improved by incorporating side information, such as natural language reviews, as a way of regularizing the derived product representations. Motivated by the success of this approach, we introduce two different models of reviews and study their effect on collaborative filtering performance. While the previous state-of-the-art approach is based on a latent Dirichlet allocation (LDA) model of reviews, the models we explore are neural network based: a bag-of-words product-of-experts model and a recurrent neural network. We demonstrate that the increased flexibility offered by the product-of-experts model allowed it to achieve state-of-the-art performance on the Amazon review dataset, outperforming the LDA-based approach. However, interestingly, the greater modeling power offered by the recurrent neural network appears to undermine the model’s ability to act as a regularizer of the product representations.

    Session 4a: Novel Setups

  • Letting Users Choose Recommender Algorithms: An Experimental Study
    by Michael D. Ekstrand, Daniel Kluver, F. Maxwell Harper and Joseph A. Konstan

    Recommender systems are not one-size-fits-all; different algorithms and data sources have different strengths, making them a better or worse fit for different users and use cases. As one way of taking advantage of the relative merits of different algorithms, we gave users the ability to change the algorithm providing their movie recommendations and studied how they make use of this power. We conducted our study with the launch of a new version of the MovieLens movie recommender that supports multiple recommender algorithms and allows users to choose the algorithm they want to provide their recommendations. We examine log data from user interactions with this new feature to understand whether and how users switch among recommender algorithms, and select a final algorithm to use. We also look at the properties of the algorithms as they were experienced by users and examine their relationships to user behavior.

    We found that a substantial portion of our user base (25%) used the recommender-switching feature. The majority of users who used the control only switched algorithms a few times, trying a few out and settling down on an algorithm that they would leave alone. The largest number of users prefer a matrix factorization algorithm, followed closely by item-item collaborative filtering; users selected both of these algorithms much more often than they chose a non-personalized mean recommender. The algorithms did produce measurably different recommender lists for the users in the study, but these differences were not directly predictive of user choice.

    Session 1a: The User in the Loop

  • Overlapping Community Regularization for Rating Prediction in Social Recommender Systems
    by Hui Li, Dingming Wu, Wenbin Tang and Nikos Mamoulis

    Recommender systems have become de facto tools for suggesting items that are of potential interest to users. Predicting a user’s rating on an item is the fundamental recommendation task. Traditional methods that generate predictions by analyzing the user-item rating matrix perform poorly when the matrix is sparse. Recent approaches use data from social networks to improve accuracy. However, most of the social-network based recommender systems only consider direct friendships and they are less effective when the targeted user has few social connections. In this paper, we propose two alternative models that incorporate the overlapping community regularization into the matrix factorization framework. Our empirical study on four real datasets shows that our approaches outperform the state-of-the-art algorithms in both traditional and social-network based recommender systems regarding both cold-start users and normal users.

    Session 1b: Recommender Systems and Social Networks

  • Preference-oriented Social Networks: Group Recommendation and Inference
    by Amirali Salehi-Abari and Craig Boutilier

    Social networks facilitate a variety of social, economic, and political interactions. Homophily and social influence suggest that preferences (e.g., over products, services, political parties) are likely to be correlated among people whom directly interact in a social network. We develop a model, preference-oriented social networks, that captures such correlations of individual preferences, where preferences take the form of rankings over a set of options. We develop probabilistic inference methods for predicting individual preferences given observed social connections and partial observations of the preferences of others in the network. We exploit these predictions in a social choice context to make group decisions or recommendations even when the preferences of some group members are unobserved. Experiments demonstrate the effectiveness of our algorithms and the improvements made possible by accounting for social ties.

    Session 1b: Recommender Systems and Social Networks

  • PushTrust: An Efficient Recommendation Algorithm by Leveraging Trust and Distrust Relations
    by Rana Forsati, Iman Barjasteh, Farzan Masrour, Abdol-Hossein Esfahanian and Hayder Radha

    The significance of social-enhanced recommender systems is increasing, along with its practicality, as online reviews, ratings, friendship links, and follower relationships are increasingly becoming available. In recent years, there has been an upsurge of interest in exploiting social information, such as trust and distrust relations in recommendation algorithms. The goal is to improve the quality of suggestions and mitigate the data sparsity and the cold-start users problems in existing systems. In this paper, we introduce a general collaborative social ranking model to rank the latent features of users extracted from rating data based on the social context of users. In contrast to existing social regularization methods, the proposed framework is able to simultaneously leverage trust, distrust, and neutral relations, and has a linear dependency on the social network size. By integrating the ranking based social regularization idea into the matrix factorization algorithm, we propose a novel recommendation algorithm, dubbed PushTrust. Our experiments on the Epinions dataset demonstrate that collaboratively ranking the latent features of users by exploiting trust and distrust relations leads to a substantial increase in performance, and to effectively deal with cold-start users problem.

    Session 1b: Recommender Systems and Social Networks

  • Putting Users in Control of their Recommendations
    by F. Maxwell Harper, Funing Xu, Harmanpreet Kaur, Kyle Condiff, Shuo Chang and Loren Terveen

    The essence of a recommender system is that it can recommend items personalized to the preferences of an individual user. But typically users are given no explicit control over this personalization, and are instead left guessing about how their actions affect the resulting recommendations. We hypothesize that any recommender algorithm will better fit some users’ expectations than others, leaving opportunities for improvement. To address this challenge, we study a recommender that puts some control in the hands of users. Specifically, we build and evaluate a system that incorporates user-tuned popularity and recency modifiers, allowing users to express concepts like “show more popular items”. We find that users who are given these controls evaluate the resulting recommendations much more positively. Further, we find that users diverge in their preferred settings, confirming the importance of giving control to users.

    Session 1a: The User in the Loop

  • Recommending Fair Payments for Large-Scale Social Ridesharing
    by Filippo Bistaffa, Alessandro Farinelli, Georgios Chalkiadakis and Sarvapali D. Ramchurn

    We perform recommendations for the Social Ridesharing scenario, in which a set of commuters, connected through a social network, arrange one-time rides at short notice. In particular, we focus on how much one should pay for taking a ride with friends. More formally, we propose the first approach that can compute fair coalitional payments that are also stable according to the game-theoretic concept of the kernel for systems with thousands of agents in real-world scenarios. Our tests, based on real datasets for both spatial (GeoLife) and social data (Twitter), show that our approach is significantly faster than the state-of-the-art (up to 84 times), allowing us to compute stable payments for 2000 agents in 50 minutes. We also develop a parallel version of our approach, which achieves a near-optimal speed-up in the number of processors used. Finally, our empirical analysis reveals new insights into the relationship between payments incurred by a user by virtue of its position in its social network and its role (rider or driver).

    Session 4a: Novel Setups

  • Risk-Hedged Venture Capital Investment Recommendation
    by Xiaoxue Zhao, Weinan Zhang and Jun Wang

    With the increasing accessibility of transactional data in venture finance, venture capital (VC) firms face great challenges in developing quantitative tools to identify new investment opportunities. Recommendation techniques have the possibility of helping VCs making data-driven investment decisions by providing an automatic screening process of the large number of startups across different domains on the basis of their past investment data. A previous study has shown the potential advantage of using collaborative filtering to catch and predict the VCs’ investment behaviours. However, two fundamental challenges in venture finance make conventional recommendation techniques difficult to apply. First, risk factors should be cautiously considered when making investments: for a potential startup, a VC needs to specifically estimate how well this new investment can fit into its holding investment portfolio in such a way that investment risk can be hedged. Second, The investment behaviours are much sparser than conventional recommendation applications and a VC’s investments are usually limited to a few industry categories, making it impossible to use a topic-diversification method to hedge the risk. In this paper, we solve the startup recommendation problem from a risk management perspective. We propose 5 risk-aware startup selection and ranking algorithms to catch the VCs’ investment behaviours and predict their new investments. Apart from the contribution on the new risk-aware recommendation model, our experiments on the collected CrunchBase dataset show significant performance improvements over strong baselines.

    Session 2a: Contextual Challenges

  • Selection and Ordering of Linear Online Video Ads
    by Wreetabrata Kar, Viswanathan Swaminathan and Paulo Albuquerque

    This paper studies the selection and ordering of in-stream ads in videos shown in online content publishers. We propose an allocation algorithm that uses a collective measure of price and quality for each ad and factors in slot-specific continuation probabilities to maximize publisher revenue. The algorithm is based on cascade models and uses a dynamic programming method to assign linear (video) ads to slots in an online video. The approach accounts for the negative externality created by lower quality ads placed in a video, leading to viewer exit and thereby preventing the publisher from showing the subsequent ads scheduled in that session. Our algorithm is scalable and suited for real-time applications. A large log of viewer activity from a video ad platform is used to empirically test the algorithm. A series of simulations show that our algorithm, when compared to other algorithms currently practiced in industry, generates more revenue for the publisher and increases viewer retention.

    Session 5b: E-commerce & Ads

  • Top-N Recommendation for Shared Accounts
    by Koen Verstrepen and Bart Goethals

    Standard collaborative filtering recommender systems assume that every account in the training data represents a single user. However, multiple users often share a single account. A typical example is a single shopping account for the whole family. Traditional recommender systems fail in this situation. If contextual information is available, context aware recommender systems are the state-of-the-art solution. Yet, often no contextual information is available. Therefore, we introduce the challenge of recommending to shared accounts in the absence of contextual information. We propose a solution to this challenge for all cases in which the reference recommender system is an item-based top-N collaborative filtering recommender system, generating recommendations based on binary, positive-only feedback. We experimentally show the advantages of our proposed solution for tackling the problems that arise from the existence of shared accounts on multiple datasets.

    Session 2a: Contextual Challenges

Back to Program

Diamond Supporter
Platinum Supporters
Gold Supporters
Silver Supporter
Special Supporters