This papers studies how competition affects machine learning (ML) predictors. As ML becomes more ubiquitous, it is often deployed by companies to compete over customers. For example, digital platforms like Yelp use ML to predict user preference and make recommendations. A service that is more often queried by users, perhaps because it more accurately anticipates user preferences, is also more likely to obtain additional user data (e.g. in the form of a Yelp review). Thus, competing predictors cause feedback loops whereby a predictor's performance impacts what training data it receives and biases its predictions over time. We introduce a flexible model of competing ML predictors that enables both rapid experimentation and theoretical tractability. We show with empirical and mathematical analysis that competition causes predictors to specialize for specific sub-populations at the cost of worse performance over the general population. We further analyze the impact of predictor specialization on the overall prediction quality experienced by users. We show that having too few or too many competing predictors in a market can hurt the overall prediction quality. Our theory is complemented by experiments on several real datasets using popular learning algorithms, such as neural networks and nearest neighbor methods.

Cross-Domain Recommendation (CDR) and Cross-System Recommendations (CSR) are two of the promising solutions to address the long-standing data sparsity problem in recommender systems. They leverage the relatively richer information, e.g., ratings, from the source domain or system to improve the recommendation accuracy in the target domain or system. Therefore, finding an accurate mapping of the latent factors across domains or systems is crucial to enhancing recommendation accuracy. However, this is a very challenging task because of the complex relationships between the latent factors of the source and target domains or systems. To this end, in this paper, we propose a Deep framework for both Cross-Domain and Cross-System Recommendations, called DCDCSR, based on Matrix Factorization (MF) models and a fully connected Deep Neural Network (DNN). Specifically, DCDCSR first employs the MF models to generate user and item latent factors and then employs the DNN to map the latent factors across domains or systems. More importantly, we take into account the rating sparsity degrees of individual users and items in different domains or systems and use them to guide the DNN training process for utilizing the rating data more effectively. Extensive experiments conducted on three real-world datasets demonstrate that DCDCSR framework outperforms the state-of-the-art CDR and CSR approaches in terms of recommendation accuracy.

Natural language processing (or NLP for short) refers to technology that allows computers to understand human language. NLP is what helps computers read, edit and summarize text – as well as enabling natural language generation (NLG), whereby computers generate their own "speech." In other words, NLP is the technology that enables Siri to understand your requests, while NLG means Siri can respond in natural-sounding language. Smart digital assistants like Alexa and Siri are among the best-known examples of NLP in action. Predictive text and email spam filters are earlier examples.

Online healthcare communities provide users with various healthcare interventions to promote healthy behavior and improve adherence. When faced with too many intervention choices, however, individuals may find it difficult to decide which option to take, especially when they lack the experience or knowledge to evaluate different options. The choice overload issue may negatively affect users' engagement in health management. In this study, we take a design-science perspective to propose a recommendation framework that helps users to select healthcare interventions. Taking into account that users' health behaviors can be highly dynamic and diverse, we propose a multi-armed bandit (MAB)-driven recommendation framework, which enables us to adaptively learn users' preference variations while promoting recommendation diversity in the meantime. To better adapt an MAB to the healthcare context, we synthesize two innovative model components based on prominent health theories. The first component is a deep-learning-based feature engineering procedure, which is designed to learn crucial recommendation contexts in regard to users' sequential health histories, health-management experiences, preferences, and intrinsic attributes of healthcare interventions. The second component is a diversity constraint, which structurally diversifies recommendations in different dimensions to provide users with well-rounded support. We apply our approach to an online weight management context and evaluate it rigorously through a series of experiments. Our results demonstrate that each of the design components is effective and that our recommendation design outperforms a wide range of state-of-the-art recommendation systems. Our study contributes to the research on the application of business intelligence and has implications for multiple stakeholders, including online healthcare platforms, policymakers, and users.

Wink's switch to a subscription service for its smart home platform hasn't had the best start. The company has confirmed reports (via Android Police and The Verge) of a wide-ranging outage affecting its services, including integration with Amazon Alexa and Google Home/Nest services and even Wink.com The problems appear to have started on September 10th. The company's status page indicated that fixed had been put in place for at least some issues. However, there were still "partial" outages listed for most support as of this writing (September 12th), and "degraded performance" for both the Core and Hub frameworks.

Apple will stage its traditional post-Labor Day product reveal on Tuesday, where it is expected to tout new editions of the Apple Watch and iPad. Along the way, there will be new things for Siri to do as well on the iPad, as part of the iOS mobile operating system upgrade. Siri is the oft-maligned but heavily used personal assistant. This year, Siri will tout a "completely new look," with "over 20x more facts than just three years ago." Yes, Apple actually says this, on the promo page for the iOS 14 upgrade, which has traditionally been made available in September.

The Flo by Moen Smart Water Leak Detector is a reliable gadget to help protect your home from water damage. Flo by Moen's Smart Water Leak Detector is the very best smart water leak detector we've ever tested, beating out our previous No. 1 pick, the Honeywell Home Water Leak Detector. While the two detectors are comparable, Moen is the more affordable of the two and, most of all, we were impressed by the near-instantaneous alerts (an imperative function of a smart leak detector) the Moen leak sensor sent to both of our iOS and Android devices, as well as via email. The Flo by Moen Smart Water Leak Detector passed all of our tests with flying colors and even continued to function after being submerged in water during our final round of testing. When a leak is detected, the sensor begins playing an alarm sound and flashes red, in addition to sending timely alerts in a matter of seconds. However, what it lacks in voice-control capabilities, it makes up for with a beautifully designed app full of useful data insights. The sensor also keeps track of the temperature and humidity within your home, which can help with moisture control.

Labor Day weekend deals extended into the rest of the week with a number of sales on electronics and home appliances. Amazon's $99 Instant Pot deal is still available while August's latest WiFi smart lock can still be had for $30 off. Some of the latest gadgets are on sale, too, including Apple's 2020 iPad Pros and Samsung's Galaxy Note 20 Ultra smartphone (which just came out). Here are the best deals from this week that you can still grab today. The Galaxy Note 20 Ultra has only been available for about a month and it's already on sale.

This glossary of artificial intelligence is a list of definitions of terms and concepts relevant to the study of artificial intelligence, its sub-disciplines, and related fields. Related glossaries include Glossary of computer science, Glossary of robotics, and Glossary of machine vision. Also stochastic Hopfield network with hidden units. Also exhaustive search or generate and test. Also deep structured learning or hierarchical learning.

Music preferences are strongly shaped by the cultural and socio-economic background of the listener, which is reflected, to a considerable extent, in country-specific music listening profiles. Previous work has already identified several country-specific differences in the popularity distribution of music artists listened to. In particular, what constitutes the "music mainstream" strongly varies between countries. To complement and extend these results, the article at hand delivers the following major contributions: First, using state-of-the-art unsupervised learning techniques, we identify and thoroughly investigate (1) country profiles of music preferences on the fine-grained level of music tracks (in contrast to earlier work that relied on music preferences on the artist level) and (2) country archetypes that subsume countries sharing similar patterns of listening preferences. Second, we formulate four user models that leverage the user's country information on music preferences. Among others, we propose a user modeling approach to describe a music listener as a vector of similarities over the identified country clusters or archetypes. Third, we propose a context-aware music recommendation system that leverages implicit user feedback, where context is defined via the four user models. More precisely, it is a multi-layer generative model based on a variational autoencoder, in which contextual features can influence recommendations through a gating mechanism. Fourth, we thoroughly evaluate the proposed recommendation system and user models on a real-world corpus of more than one billion listening records of users around the world (out of which we use 369 million in our experiments) and show its merits vis-a-vis state-of-the-art algorithms that do not exploit this type of context information.