Recommender systems have become an essential instrument in a wide range of industries to personalize the user experience. A significant issue that has captured both researchers' and industry experts' attention is the cold start problem for new items. In this work, we present a graph neural network recommender system using item hierarchy graphs and a bespoke architecture to handle the cold start case for items. The experimental study on multiple datasets and millions of users and interactions indicates that our method achieves better forecasting quality than the state-of-the-art with a comparable computational time.

My kids, ages 8 and 5, are showing me the future. When I want to watch a movie or turn out the lights, I instinctively reach for the remote or flick a switch. My children find it far more natural to just ask Siri for Peppa Pig, or tell Alexa to darken the room. Why not just talk to the machines around us like we talk to each other? Of course, right now talking -- rather than touching -- also has serious safety upsides. Voice tech adoption has accelerated as the coronavirus pandemic makes everyone touchy about how sanitary it is to poke buttons and screens.

AI and ML are some of the smart techs used in creating intelligent systems. Both are commonly used as synonyms of each other and there's a major correlation between both. However, each can be distinguished from the other as described below. Artificial Intelligence can be described as intelligence which attempts to mimic human intelligence. As the name implies, "artificial"-Human-made, "Intelligence"- thinking power.

A popular model of preference in the context of recommendation systems is the so-called \emph{ideal point} model. In this model, a user is represented as a vector $\mathbf{u}$ together with a collection of items $\mathbf{x_1}, \ldots, \mathbf{x_N}$ in a common low-dimensional space. The vector $\mathbf{u}$ represents the user's "ideal point," or the ideal combination of features that represents a hypothesized most preferred item. The underlying assumption in this model is that a smaller distance between $\mathbf{u}$ and an item $\mathbf{x_j}$ indicates a stronger preference for $\mathbf{x_j}$. In the vast majority of the existing work on learning ideal point models, the underlying distance has been assumed to be Euclidean. However, this eliminates any possibility of interactions between features and a user's underlying preferences. In this paper, we consider the problem of learning an ideal point representation of a user's preferences when the distance metric is an unknown Mahalanobis metric. Specifically, we present a novel approach to estimate the user's ideal point $\mathbf{u}$ and the Mahalanobis metric from paired comparisons of the form "item $\mathbf{x_i}$ is preferred to item $\mathbf{x_j}$." This can be viewed as a special case of a more general metric learning problem where the location of some points are unknown a priori. We conduct extensive experiments on synthetic and real-world datasets to exhibit the effectiveness of our algorithm.

StoryFile offers a somewhat unique service that seems poised to look like something out of Black Mirror. The company – a relative newcomer – helps people to record themselves telling their stories, then presents those stories in an interactive, voice-activated interface. Users can ask the digital storytellers questions, which are interpreted by the StoryFile app and answered with snippets from their recorded stories. Now, StoryFile is announcing that it has acquired a new portfolio of patents covering the use of AI in creating "artificially intelligent interactive memories." StoryFile began with a greenscreen studio and select guests, including Nobel laureates, astronauts, Holocaust survivors, and many others.

Alexa has been smartening up homes since 2014, but for those who don't want to bother with the setup process, a new Amazon program will let apartment building owners offer units with Alexa built in. With Alexa for Residential, property owners set up Alexa devices across units, making the move to voice-assistant life easier for tenants moving in. Renters control their apartment's smart features--set alarms and reminders, get the news, and more via voice commands--without linking their Amazon accounts or buying an Echo device themselves. If residents want to link their Amazon accounts to their apartment's smart devices for full control of their privacy settings, they can. They can log out at any time, and smart devices are reset at move-out.

As recommender systems are being designed and deployed for an increasing number of socially-consequential applications, it has become important to consider what properties of fairness these systems exhibit. There has been considerable research on recommendation fairness. However, we argue that the previous literature has been based on simple, uniform and often uni-dimensional notions of fairness assumptions that do not recognize the real-world complexities of fairness-aware applications. In this paper, we explicitly represent the design decisions that enter into the trade-off between accuracy and fairness across multiply-defined and intersecting protected groups, supporting multiple fairness metrics. The framework also allows the recommender to adjust its performance based on the historical view of recommendations that have been delivered over a time horizon, dynamically rebalancing between fairness concerns. Within this framework, we formulate lottery-based mechanisms for choosing between fairness concerns, and demonstrate their performance in two recommendation domains.

Recommender systems are being employed across an increasingly diverse set of domains that can potentially make a significant social and individual impact. For this reason, considering fairness is a critical step in the design and evaluation of such systems. In this paper, we introduce HyperFair, a general framework for enforcing soft fairness constraints in a hybrid recommender system. HyperFair models integrate variations of fairness metrics as a regularization of a joint inference objective function. We implement our approach using probabilistic soft logic and show that it is particularly well-suited for this task as it is expressive and structural constraints can be added to the system in a concise and interpretable manner. We propose two ways to employ the methods we introduce: first as an extension of a probabilistic soft logic recommender system template; second as a fair retrofitting technique that can be used to improve the fairness of predictions from a black-box model. We empirically validate our approach by implementing multiple HyperFair hybrid recommenders and compare them to a state-of-the-art fair recommender. We also run experiments showing the effectiveness of our methods for the task of retrofitting a black-box model and the trade-off between the amount of fairness enforced and the prediction performance.

Recommender systems are among the most fun and profitable applications of data science in the big data world. Training data (corresponding to the historical search, browse, purchase, and customer feedback patterns of your customers) can be converted into golden opportunities for ROI (i.e., Return On Innovation and Investment). The predictive analytics tools of data science yield a bonanza of mechanisms to engage your customers and enrich their customer experience. What better loyalty program can there be if not the one that offers the customer what they want before they ask (and sometimes, even before they think of it for themselves). Yes, we know of some cases that have gone bad (such as the secretly pregnant teen and the targeted coupons that Target sent to her father), and we recognize that there is a fine line between being intimate with your customers versus being intimidating, but usually people do like to receive offers for great products that they love.

Contemporary recommender systems act as intermediaries on multi-sided platforms serving high utility recommendations from sellers to buyers. Such systems attempt to balance the objectives of multiple stakeholders including sellers, buyers, and the platform itself. The difficulty in providing recommendations that maximize the utility for a buyer, while simultaneously representing all the sellers on the platform has lead to many interesting research problems.Traditionally, they have been formulated as integer linear programs which compute recommendations for all the buyers together in an \emph{offline} fashion, by incorporating coverage constraints so that the individual sellers are proportionally represented across all the recommended items. Such approaches can lead to unforeseen biases wherein certain buyers consistently receive low utility recommendations in order to meet the global seller coverage constraints. To remedy this situation, we propose a general formulation that incorporates seller coverage objectives alongside individual buyer objectives in a real-time personalized recommender system. In addition, we leverage highly scalable submodular optimization algorithms to provide recommendations to each buyer with provable theoretical quality bounds. Furthermore, we empirically evaluate the efficacy of our approach using data from an online real-estate marketplace.