Recommender systems focus on timestamps as numeric or cyclical values, often ignoring real-world context like seasons, holidays and events. We present a scalable framework that utilizes large language models (LLMs) to create geo-temporal embeddings from timestamps and coarse locations, capturing holidays, seasonal trends, and local/global events. We then introduce a geo-temporal embedding informativeness test as a lightweight diagnostic, demonstrating on MovieLens, LastFM, and a large-scale production dataset that these embeddings provide a predictive signal consistent with the outcomes of full model integrations. Geo-temporal embeddings were integrated into sequential models via feature fusion with metadata. Our findings underscore the importance of adaptive and hybrid strategies for improving recommendations. We also release a context-enriched MovieLens dataset. https://github.com/yejinjennyK/movielens-1m-geo-temporal-context https://huggingface.co/datasets/yejinjennyK/movielens-1m-geo-temporal-context.

Millions of people rely on search functionality to find and explore content on entertainment platforms. Modern search systems use a combination of candidate generation and ranking approaches, with advanced methods leveraging deep learning and LLM-based techniques to retrieve, generate, and categorize search results. Despite these advancements, search algorithms can still surface inappropriate or irrelevant content due to factors like model unpredictability, metadata errors, or overlooked design flaws. Such issues can misalign with product goals and user expectations, potentially harming user trust and business outcomes. In this work, we introduce an additional monitoring layer using Large Language Models (LLMs) to enhance content moderation. This additional layer flags content if the user did not intend to search for it. This approach serves as a baseline for product quality assurance, with collected feedback used to refine the initial retrieval mechanisms of the search model, ensuring a safer and more reliable user experience.

Addressing the cold-start issue in content recommendation remains a critical ongoing challenge.In this work, we focus on tackling the cold-start problem for movies on a large entertainment platform.Our primary goal is to forecast the popularity of cold-start movies using Large Language Models (LLMs) leveraging movie metadata.This method could be integrated into retrieval systems within the personalization pipeline or could be adopted as a tool for editorial teams to ensure fair promotion of potentially overlooked movies that may be missed by traditional or algorithmic solutions.Our study validates the effectiveness of this approach compared to established baselines and those we developed.

Addressing the challenges related to data sparsity, cold-start problems, and diversity in recommendation systems is both crucial and demanding. Many current solutions leverage knowledge graphs to tackle these issues by combining both item-based and user-item collaborative signals. A common trend in these approaches focuses on improving ranking performance at the cost of escalating model complexity, reducing diversity, and complicating the task. It is essential to provide recommendations that are both personalized and diverse, rather than solely relying on achieving high rank-based performance, such as Click-through rate, Recall, etc. In this paper, we propose a hybrid multi-task learning approach, training on user-item and item-item interactions. We apply item-based contrastive learning on descriptive text, sampling positive and negative pairs based on item metadata. Our approach allows the model to better understand the relationships between entities within the knowledge graph by utilizing semantic information from text. It leads to more accurate, relevant, and diverse user recommendations and a benefit that extends even to cold-start users who have few interactions with items. We perform extensive experiments on two widely used datasets to validate the effectiveness of our approach. Our findings demonstrate that jointly training user-item interactions and item-based signals using synopsis text is highly effective. Furthermore, our results provide evidence that item-based contrastive learning enhances the quality of entity embeddings, as indicated by metrics such as uniformity and alignment.

At Xfinity, an instant search system provides a variety of results for a given query from different sources. For each keystroke, new results are rendered on screen to the user, which could contain movies, television series, sporting events, music videos, news clips, person pages, and other result types. Users are also able to use the Xfinity Voice Remote to submit longer queries, some of which are more open-ended. Examples of queries include incomplete words which match multiple results through lexical matching (i.e., "ali"), topical searches ("vampire movies"), and more specific longer searches ("Movies with Adam Sandler"). Since results can be based on lexical matches, semantic matches, item-to-item similarity matches, or a variety of business logic driven sources, a key challenge is how to combine results into a single list. To accomplish this, we propose merging the lists via a Learning to Rank (LTR) neural model which takes into account the search query. This combined list can be personalized via a second LTR neural model with knowledge of the user's search history and metadata of the programs. Because instant search is under-represented in the literature, we present our learnings from research to aid other practitioners.

Deep two-dimensional (2-D) convolutional neural networks (CNNs) have been remarkably successful in producing record-breaking results in a variety of computer vision tasks. It is possible to extend CNNs to three dimensions using 3-D kernels to make them suitable for volumetric medical imaging data such as CT or MRI, but this increases the processing time as well as the required number of training samples (due to the higher number of parameters that need to be learned). In this paper, we address both of these issues for a 3-D CNN implementation through the development of a two-stage computer-aided detection system for automatic detection of pulmonary nodules. The first stage consists of a 3-D fully convolutional network for fast screening and generation of candidate suspicious regions. The second stage consists of an ensemble of 3-D CNNs trained using extensive transformations applied to both the positive and negative patches to augment the training set. To enable the second stage classifiers to learn differently, they are trained on false positive patches obtained from the screening model using different thresholds on their associated scores as well as different augmentation types. The networks in the second stage are averaged together to produce the final classification score for each candidate patch. Using this procedure, our overall nodule detection system called DeepMed is fast and can achieve 91% sensitivity at 2 false positives per scan on cases from the LIDC dataset.