We introduce Auto-Surprise, an Automated Recommender System library. Auto-Surprise is an extension of the Surprise recommender system library and eases the algorithm selection and configuration process. Compared to out-of-the-box Surprise library, Auto-Surprise performs better when evaluated with MovieLens, Book Crossing and Jester Datasets. It may also result in the selection of an algorithm with significantly lower runtime. Compared to Surprise's grid search, Auto-Surprise performs equally well or slightly better in terms of RMSE, and is notably faster in finding the optimum hyperparameters.

As IoT smart home devices such as Amazon Alexas continue to grow in popularity, they provide us the opportunity to connect and interact with the internet in a variety of ways. Despite their popularity and the benefits, they bring to the user, they also pose a significant security risk if not properly secured. This is because hackers are acutely aware about the lack of basic security measures some .... [Read More ]

Career advisor systems are essentially recommender systems in the space of job searching and career advice. They provide recommendations to candidates with possible career paths and to employers with possible candidates for a job opening. In this post we will outline the required capabilities of such systems, and highlight the challenges that need to be overcome in order to construct a working system. Questions like "What is a career advisor system?", "What is it capable of doing?", "Why do we need them?" etc are answered in this article. We also discuss our recent work (presented at AAAI-IAAI [1]) which describes how we proposed to solve this problem.

Writing is a complex non-linear process that begins with a mental model of intent, and progresses through an outline of ideas, to words on paper (and their subsequent refinement). Despite past research in understanding writing, Web-scale consumer and enterprise collaborative digital writing environments are yet to greatly benefit from intelligent systems that understand the stages of document evolution, providing opportune assistance based on authors' situated actions and context. In this paper, we present three studies that explore temporal stages of document authoring. We first survey information workers at a large technology company about their writing habits and preferences, concluding that writers do in fact conceptually progress through several distinct phases while authoring documents. We also explore, qualitatively, how writing stages are linked to document lifespan. We supplement these qualitative findings with an analysis of the longitudinal user interaction logs of a popular digital writing platform over several million documents. Finally, as a first step towards facilitating an intelligent digital writing assistant, we conduct a preliminary investigation into the utility of user interaction log data for predicting the temporal stage of a document. Our results support the benefit of tools tailored to writing stages, identify primary tasks associated with these stages, and show that it is possible to predict stages from anonymous interaction logs. Together, these results argue for the benefit and feasibility of more tailored digital writing assistance.

Recently, conversational recommender system (CRS) has become With the rapid development of intelligent agents in e-commerce an emerging and practical research topic. Most of the existing CRS platforms, conversational recommender system (CRS) [5, 6, 9] has methods focus on learning effective preference representations for become an emerging research topic in seeking to provide highquality users from conversation data alone. While, we take a new perspective recommendations to users through conversations. Generally, to leverage historical interaction data for improving CRS. a CRS consists of a conversation module and a recommendation For this purpose, we propose a novel pre-training approach to module. The conversation module focuses on acquiring users' preference integrating both item-based preference sequence (from historical via multi-turn interaction, and the recommendation module interaction data) and attribute-based preference sequence (from conversation focuses on how to utilize the inferred preference information to data) via pre-training methods. We carefully design two recommend suitable items for users.

Most recommender systems (RS) research assumes that a user's utility can be maximized independently of the utility of the other agents (e.g., other users, content providers). In realistic settings, this is often not true---the dynamics of an RS ecosystem couple the long-term utility of all agents. In this work, we explore settings in which content providers cannot remain viable unless they receive a certain level of user engagement. We formulate the recommendation problem in this setting as one of equilibrium selection in the induced dynamical system, and show that it can be solved as an optimal constrained matching problem. Our model ensures the system reaches an equilibrium with maximal social welfare supported by a sufficiently diverse set of viable providers. We demonstrate that even in a simple, stylized dynamical RS model, the standard myopic approach to recommendation---always matching a user to the best provider---performs poorly. We develop several scalable techniques to solve the matching problem, and also draw connections to various notions of user regret and fairness, arguing that these outcomes are fairer in a utilitarian sense.

Matrix factorization is one of the most commonly used technologies in recommendation system. With the promotion of recommendation system in e-commerce shopping, online video and other aspects, distributed recommendation system has been widely promoted, and the privacy problem of multi-source data becomes more and more important. Based on Federated learning technology, this paper proposes a shared matrix factorization scheme called SharedMF. Firstly, a distributed recommendation system is built, and then secret sharing technology is used to protect the privacy of local data. Experimental results show that compared with the existing homomorphic encryption methods, our method can have faster execution speed without privacy disclosure, and can better adapt to recommendation scenarios with large amount of data.

Many recent advances in neural information retrieval models, which predict top-K items given a query, learn directly from a large training set of (query, item) pairs. However, they are often insufficient when there are many previously unseen (query, item) combinations, often referred to as the cold start problem. Furthermore, the search system can be biased towards items that are frequently shown to a query previously, also known as the 'rich get richer' (a.k.a. feedback loop) problem. In light of these problems, we observed that most online content platforms have both a search and a recommender system that, while having heterogeneous input spaces, can be connected through their common output item space and a shared semantic representation. In this paper, we propose a new Zero-Shot Heterogeneous Transfer Learning framework that transfers learned knowledge from the recommender system component to improve the search component of a content platform. First, it learns representations of items and their natural-language features by predicting (item, item) correlation graphs derived from the recommender system as an auxiliary task. Then, the learned representations are transferred to solve the target search retrieval task, performing query-to-item prediction without having seen any (query, item) pairs in training. We conduct online and offline experiments on one of the world's largest search and recommender systems from Google, and present the results and lessons learned. We demonstrate that the proposed approach can achieve high performance on offline search retrieval tasks, and more importantly, achieved significant improvements on relevance and user interactions over the highly-optimized production system in online experiments.

Voice technology has come a long way. With smart assistants like Alexa, Google Assistant, Cortana, and so forth, daily chores and tedious tasks are now a cakewalk. You come home from work and the light turns on and the coffee machine starts to brew. You don't have to worry about the washing machine staying on or whether you forgot to turn the kitchen lights off when you've already hit the bed. Smart voice assistants are now your personal butlers, thanks to voice technology.

Nuisance phone calls could disappear with the help of a virtual assistant that screens out spammers before the phone even rings. Robocalls, in which an automated recording pretends to be a human, are a common problem – there are an estimated 4.9 million every hour in the US alone. Simple block lists can screen some of these calls out, but they are only around 60 per cent effective, says Sharbani Pandit at the Georgia Institute of Technology.