Yes, Black Friday is basically here and, though we're not sure where this year went, all the sales are softening the blow. Amazon, sure to be the home of a lot of shopping this year, has already marked down some of its most wanted products. Included in the sales is our choice for best smart speaker under 50, the fifth generation Amazon Echo Dot. Right now, you can pick up the speaker for just 23 -- an all-time low price. The fifth-gen Amazon Echo Dot came out in 2022 and has great features, including exceptionally loud and clear audio for its sticker price (let alone the discounted one).

Dating apps are becoming one of the most popular ways for people in Japan to meet their spouses, at least for those in their 20s, recent surveys show. A survey released by an organization promoting "Good Couples Day" -- a celebration held on Nov. 22 each year since the date can be read phonetically as ii fūfu in Japanese, which directly translates to "good couple" -- showed that 24% of couples in their 20s had met their marriage partner through a dating app. For the youngest group of participants in the survey, which collected data from 1,000 married individuals over the age of 20 across the country in September this year, it was the most popular way to meet a partner, along with meeting through work, which was selected by the same percentage.

Modern recommendation systems often create information cocoons, limiting users' exposure to diverse content. To enhance user experience, a crucial challenge is developing systems that can balance content exploration and exploitation, allowing users to adjust their recommendation preferences. Intuitively, this balance can be achieved through a tree-structured representation, where depth search facilitates exploitation and breadth search enables exploration. However, current works face two challenges to achieve this target: (1) Euclidean methods fail to fully capture hierarchical structures and lack flexibility in balancing exploration-exploitation, while (2) hyperbolic approaches, despite better hierarchical modeling, suffer from insufficient semantic alignment due to their reliance on Euclidean text encoders. To address these challenges, we propose HARec, a hyperbolic representation learning framework that jointly aligns user-item collaborative information with textual descriptions in hyperbolic space. Our framework introduces two key technique novelty: (1) a hierarchical-aware graph-llm alignment mechanism that enables better hierarchical representation, and (2) a hyperbolic hierarchical tree structure that facilitates user-adjustable exploration-exploitation trade-offs. Extensive experiments demonstrate that HARec consistently outperforms both Euclidean and hyperbolic baselines, achieving up to 5.49% improvement in utility metrics and 11.39% increase in diversity metrics.

We present a large-scale news recommendation system implemented at Ringier Axel Springer Polska, focusing on enhancing prediction models with reinforcement learning techniques. The system, named Aureus, integrates a variety of algorithms, including multi-armed bandit methods and deep learning models based on large language models (LLMs). We detail the architecture and implementation of Aureus, emphasizing the significant improvements in online metrics achieved by combining ranking prediction models with reinforcement learning. The paper further explores the impact of different models mixing on key business performance indicators. Our approach effectively balances the need for personalized recommendations with the ability to adapt to rapidly changing news content, addressing common challenges such as the cold start problem and content freshness. The results of online evaluation demonstrate the effectiveness of the proposed system in a real-world production environment.

CTR prediction plays a vital role in recommender systems. Recently, large language models (LLMs) have been applied in recommender systems due to their emergence abilities. While leveraging semantic information from LLMs has shown some improvements in the performance of recommender systems, two notable limitations persist in these studies. First, LLM-enhanced recommender systems encounter challenges in extracting valuable information from lifelong user behavior sequences within textual contexts for recommendation tasks. Second, the inherent variability in human behaviors leads to a constant stream of new behaviors and irregularly fluctuating user interests. This characteristic imposes two significant challenges on existing models. On the one hand, it presents difficulties for LLMs in effectively capturing the dynamic shifts in user interests within these sequences, and on the other hand, there exists the issue of substantial computational overhead if the LLMs necessitate recurrent calls upon each update to the user sequences. In this work, we propose Lifelong User Behavior Modeling (LIBER) based on large language models, which includes three modules: (1) User Behavior Streaming Partition (UBSP), (2) User Interest Learning (UIL), and (3) User Interest Fusion (UIF). Initially, UBSP is employed to condense lengthy user behavior sequences into shorter partitions in an incremental paradigm, facilitating more efficient processing. Subsequently, UIL leverages LLMs in a cascading way to infer insights from these partitions. Finally, UIF integrates the textual outputs generated by the aforementioned processes to construct a comprehensive representation, which can be incorporated by any recommendation model to enhance performance. LIBER has been deployed on Huawei's music recommendation service and achieved substantial improvements in users' play count and play time by 3.01% and 7.69%.

We analyze the effect that online algorithms have on the environment that they are learning. As a motivation, consider recommendation systems that use online algorithms to learn optimal product recommendations based on user and product attributes. It is well known that the sequence of recommendations affects user preferences. However, typical learning algorithms treat the user attributes as static and disregard the impact of their recommendations on user preferences. Our interest is to analyze the effect of this mismatch between the model assumption of a static environment, and the reality of an evolving environment affected by the recommendations. To perform this analysis, we first introduce a model for a generic coupled evolution of the parameters that are being learned, and the environment that is affected by it. We then frame a linear bandit recommendation system (RS) into this generic model where the users are characterized by a state variable that evolves based on the sequence of recommendations. The learning algorithm of the RS does not explicitly account for this evolution and assumes that the users are static. A dynamical system model that captures the coupled evolution of the population state and the learning algorithm is described, and its equilibrium behavior is analyzed. We show that when the recommendation algorithm is able to learn the population preferences in the presence of this mismatch, the algorithm induces similarity in the preferences of the user population. In particular, we present results on how different properties of the recommendation algorithm, namely the user attribute space and the exploration-exploitation tradeoff, effect the population preferences when they are learned by the algorithm. We demonstrate these results using model simulations.

Mobile health has the potential to revolutionize health care delivery and patient engagement. In this work, we discuss how integrating Artificial Intelligence into digital health applications-focused on supply chain, patient management, and capacity building, among other use cases-can improve the health system and public health performance. We present an Artificial Intelligence and Reinforcement Learning platform that allows the delivery of adaptive interventions whose impact can be optimized through experimentation and real-time monitoring. The system can integrate multiple data sources and digital health applications. The flexibility of this platform to connect to various mobile health applications and digital devices and send personalized recommendations based on past data and predictions can significantly improve the impact of digital tools on health system outcomes. The potential for resource-poor settings, where the impact of this approach on health outcomes could be more decisive, is discussed specifically. This framework is, however, similarly applicable to improving efficiency in health systems where scarcity is not an issue.

Nothing says it's the holiday season like a brand-new Amazon device. Amazon has been expanding its product lineups left and right this year, from its speaker options with the revived Echo Spot to a relaunch of the entire Kindle line (with some hiccups). Now the Echo Show family is getting a big update. Literally--it's getting a massive, 21-inch device added to the roster. The Echo Show 21 ( 400) is the newest member of Amazon's vast list of Echo-powered devices, with a 21-inch display.

Comcast is spinning out Rotten Tomatoes, Fandango and a bunch of NBCUniversal (NBCU) cable networks into a separate company. That means USA Network, CNBC, MSNBC, Oxygen, E!, SYFY and Golf Channel will soon have a new home. Comcast is hanging onto other NBCU operations, namely NBC, Peacock, film and TV studios, Telemundo and theme parks. Bravo is also sticking around to help keep feeding Peacock's ever-hungry reality TV maw. Comcast says the new entity will be a "tax-free spin-off" and the step is "expected to be accretive to revenue growth at Comcast and approximately neutral to Comcast's leverage position."

The exploding popularity of online content and its user base poses an evermore challenging matching problem for modern recommendation systems. Unlike other frontiers of machine learning such as natural language, recommendation systems are responsible for collecting their own data. Simply exploiting current knowledge can lead to pernicious feedback loops but naive exploration can detract from user experience and lead to reduced engagement. This exploration-exploitation trade-off is exemplified in the classic multi-armed bandit problem for which algorithms such as upper confidence bounds (UCB) and Thompson sampling (TS) demonstrate effective performance. However, there have been many challenges to scaling these approaches to settings which do not exhibit a conjugate prior structure. Recent scalable approaches to uncertainty quantification via epinets have enabled efficient approximations of Thompson sampling even when the learning model is a complex neural network. In this paper, we demonstrate the first application of epinets to an online recommendation system. Our experiments demonstrate improvements in both user traffic and engagement efficiency on the Facebook Reels online video platform.