Recommendations For New Users Research Articles

Netflix Movies Recommendation System

Netflix is a leading global entertainment company with over 247 million paying customers who can access TV series, films, and games in over 190+ countries. Many languages and genres are offered for the content. As much as they like, whenever and wherever they wish, participants are free to change their plans and play, pause, and resume viewing. With the exponential growth of content on streaming platforms like Netflix, users often face the challenge of finding relevant and enjoyable movies.The "Cold-Start" issue is a recommendation system issue wherein new users or items have little data, making it challenging to provide appropriate recommendations. In response, this paper proposes a data-driven movie recommendation system tailored for Netflix. Leveraging machine learning techniques, user preferences, and historical data, the model aims to enhance the user experience by providing personalized movierecommendations. This study explores algorithms such as collaborative filtering, content-based filtering, and hybrid models to achieve accurate and effective movie recommendations. While content-based filtering uses item features to suggest shows or movies a user has previously enjoyed, collaborative filtering examines user behavior and preferences to produce suggestions. Even with insufficient data, the system can deliver more accurate recommendations for new users or things by combining various approaches. By making recommendations based on both item features and user behavior, this hybrid approach helps to reduce the cold start issue.

A Novel Cross-Domain Recommendation with Evolution Learning

In this “info-plosion” era, recommendation systems (or recommenders) play a significant role in finding interesting items in the surge of online digital activities and e-commerce. Several techniques have been widely applied for recommendation systems, but the cold-start and sparsity problems remain a major challenge. The cold-start problem occurs when generating recommendations for new users and items without sufficient information. Sparsity refers to the problem of having a large amount of users and items but with few transactions or interactions. In this article, a novel cross-domain recommendation model, Cross-Domain Evolution Learning Recommendation (abbreviated as CD-ELR), is developed to communicate the information from different domains in order to tackle the cold-start and sparsity issues by integrating matrix factorization and recurrent neural network. We introduce an evolutionary concept to describe the preference variation of users over time. Furthermore, several optimization methods are developed for combining the domain features for precision recommendation. Experimental results show that CD-ELR outperforms existing state-of-the-art recommendation baselines. Finally, we conduct experiments on several real-world datasets to demonstrate the practicability of the proposed CD-ELR.

Cannabis Retailer Communication About Cannabis Products, Health Benefits, and Risks: A Mystery Shopper Study of Licensed Retailers in Five U.S. Cities.

As the U.S. cannabis market expands, surveillance of retailer practices, especially product health claims and risks, is crucial to protect consumers. In this study, mystery shoppers (i.e., staff not explicitly identified as researchers) examined retail personnel communication regarding product recommendations, health benefits, safety, and/or risks among U.S. cannabis retailers. In Summer 2022, mystery shoppers audited 140 licensed cannabis retailers in 5 cities in states with established nonmedical (i.e., recreational) cannabis sales and diverse regulations (Denver, Colorado; Seattle, Washington; Portland, Oregon; Las Vegas, Nevada; Los Angeles, California). Descriptive and bivariate analyses characterized retail personnel communication overall and across cities. Common product recommendations for new users included edibles, pre-rolled joints, and bud/flower, and 8.6% offered free/inexpensive ways to sample products. Although Colorado, Washington, and Oregon explicitly prohibited health claims in advertising or labels, more than 90% of retailers there endorsed use for anxiety, insomnia, and/or pain. Whereas 54.3% endorsed use for pregnancy-related nausea (least common in Denver, 23.3%; most common in Seattle, 76.7%), 26.4% warned against use during pregnancy (most frequently in Denver, 46.7%; least frequently in Seattle and Portland, 13.3%). Overall, 52.1% warned against driving after use (most frequently in Denver, 80.0%; least frequently in Las Vegas, 20.0%). Almost all (≥90%) sold cannabidiol (CBD) products and endorsed their health benefits and safety, but few (<10%) sold or endorsed delta-8 tetrahydrocannabinol (THC), etc. (all of which were in Los Angeles). Ongoing cannabis retail surveillance, particularly using protocols assessing factors outside those visibly observable, is needed to inform regulatory and enforcement efforts, especially related to health claims.

Do Trust based Social Recommendation Algorithms Work as Intended?

Recommender systems are powerful tools that filter and recommend content/information relevant to a given user. Collaborative filtering is the most popular technique used in building recommender systems and it has been successfully incorporated in many applications. These conventional recommendation systems require a minimum number of users, items, and ratings in order to provide effective recommendations. This results in the infamous cold-start problem where the system is not able to produce effective recommendations for new users. Recently, there has been an escalation in the popularity and usage of social networks, which persuades people to share their experiences in the form of reviews and ratings on social media. The components of social media such as the influence of friends, interests, and enjoyment create the opportunities to develop solutions for sparsity and cold start problems of recommendation systems. This paper aims to observe these patterns and analyze three of the existing social recommendation systems, SocialMF, SocialFD, and GraphRec. SocialMF and SocialFD algorithms are based on matrix factorization and distance metric learning respectively whereas GraphRec is an attention based deep learning model. Through extensive experimentation with the datasets that these algorithms were tested on and one new dataset, we compared the results based on evaluation metrics including Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). To investigate how trust impacts the performance of these models, we evaluated them by modifying the trust and social component. Experimental results show that there is no conclusive evidence that trust propagation plays a major part in these models. Moreover, these models show a slightly improved performance in the absence of trust statements.

Application of transgenic zebrafish for investigating inflammatory responses to nanomaterials: Recommendations for new users

Despite the increasing exploitation of nanomaterials (NMs) in an array of consumer products, there are uncertainties regarding their potential adverse impact on human health. Investigation of whether NMs activate a pro-inflammatory response is routinely used to assess their toxicity in in vitro and in vivo (rodent) studies. The use of zebrafish (Danio rerio) to investigate inflammatory responses to chemicals, pathogens and injury has increased considerably over recent years. Zebrafish have also been used to investigate the role of inflammation in disease pathogenesis and for drug discovery. Availability of transgenic strains which express fluorescent proteins in immune cells (e.g. macrophages and neutrophils) enables the visualization and quantification of immune cell accumulation in the target site(s) of interest. We therefore propose that transgenic zebrafish have great utility for screening the toxicity of NMs via investigation of inflammatory responses. Indeed, we have successfully used non-protected life stages of transgenic zebrafish with fluorescent neutrophils (Tg(mpx:EGFP114) to investigate inflammatory responses to NMs. The more widespread use of transgenic zebrafish in nanotoxicology could reduce the reliance placed on rodents and thereby enhance the implementation of the 3Rs principles. As zebrafish continue to grow in popularity it is timely to offer guidance to new users on their use. Here we will reflect on: exposure routes that can adopted to mimic human/rodent exposure, what transgenic strains and life stages are best suited to investigate inflammatory responses, selection criteria for zebrafish embryos/larvae, the inclusion of appropriate controls, the importance of dose selection and sample size, and how the (inflammatory) response can be quantified. It is hoped that our recommendations will support the development of standard protocols that can be used to assess whether NMs activate inflammatory responses. Importantly, the themes discussed are not restricted to NMs but relevant also to zebrafish application in ecotoxicology or human health focused studies.

Genotype-environment associations to reveal the molecular basis of environmental adaptation.

A fundamental goal in plant biology is to identify and understand the variation underlying plants' adaptation to their environment. Climate change has given new urgency to this goal, as society aims to accelerate adaptation of ecologically important plant species, endangered plant species, and crops to hotter, less predictable climates. In the pre-genomic era, identifying adaptive alleles was painstaking work, leveraging genetics, molecular biology, physiology, and ecology. Now, the rise of genomics and new computational approaches may facilitate this research. Genotype-environment associations (GEAs) use statistical associations between allele frequency and environment of origin to test the hypothesis that allelic variation at a given gene is adapted to local environments. Researchers may scan the genome for GEAs to generate hypotheses on adaptive genetic variants (environmental genome-wide association studies). Despite the rapid adoption of these methods, many important questions remain about the interpretation of GEA findings, which arise from fundamental unanswered questions on the genetic architecture of adaptation and limitations inherent to association-based analyses. We outline strategies to ground GEAs in the underlying hypotheses of genetic architecture and better test GEA-generated hypotheses using genetics and ecophysiology. We provide recommendations for new users who seek to learn about the molecular basis of adaptation. When combined with a rigorous hypothesis testing framework, GEAs may facilitate our understanding of the molecular basis of climate adaptation for plant improvement.

Analysis of TV Film Scoring and Communication Efficiency Based on Artificial Intelligence

The spread of TV movies has brought free participation in film reviews. Movies have brought freedom of time and space for comments. You can publish your own comments at any time without time restrictions. You can publish comments on forums, blogs, vote, and various websites, film companies, and even individuals to hold special online film competitions or film review activities. With the gradual maturity of film types, a series of subtypes such as artificial intelligence, interstellar civilization, and alien species have been derived. These contents have different emphases on type characteristics and narrative characteristics, although the subtypes of films have some common characteristics in essence. Based on artificial intelligence, this paper studies the scoring analysis and communication efficiency of TV and film. By adjusting the recommendation through user feedback, the average absolute error has been improved by 18% and the accuracy has been improved by 24%. Moreover, through four rounds of feedback, the accuracy of online computing recommendation for new users is very close to that for old users. This shows the superiority of artificial intelligence algorithm in solving the problems of cold start and complex interest recommendation. It can be predicted that artificial intelligence will become a unique cultural phenomenon. Its cultural connotation is all inclusive and worthy of continuous research and exploration by future generations. Artificial intelligence appears more and more frequently in science fiction films and presents more rich and detailed diversity and complexity.

Optimizing broad ion beam polishing of zircaloy-4 for electron backscatter diffraction analysis

To provide useful materials characterization, we must prepare samples well so that we can avoid studying artefacts induced during sample preparation. This motivates us to systematically study our preparation methods. In this work, we focus on improving “broad ion beam” (BIB) polishing through a combination of consideration of the ion-sample interactions and a systematic study of options provided by commonly available broad ion beam milling machines. Our study specifically aims to optimise the preparation of zircaloy-4, which is an alloy of zirconium used in nuclear fuel cladding, and we note that this alloy is difficult to prepare with other sample preparations routes. We optimise BIB polishing to study the microstructure of the zircaloy-4 with electron microscopy based electron backscatter diffraction (EBSD). To conclude our study, we provide recommendations for new users of BIB based polishing methods.

Weighted AutoEncoding recommender system

AbstractRecommender systems are information filtering tools that seek to match customers with products or services of interest. Most of the prevalent collaborative filtering recommender systems, such as matrix factorization and AutoRec, suffer from the “cold‐start” problem, where they fail to provide meaningful recommendations for new users or new items due to informative‐missing from the training data. To address this problem, we propose a weighted AutoEncoding model to leverage information from other users or items that share similar characteristics. The proposed method provides an effective strategy for borrowing strength from user or item‐specific clustering structure as well as pairwise similarity in the training data, while achieving high computational efficiency and dimension reduction, and preserving nonlinear relationships between user preferences and item features. Simulation studies and applications to three real datasets show advantages in prediction accuracy of the proposed model compared to current state‐of‐the‐art approaches.

Recommendation System Based on Generative Adversarial Network with Graph Convolutional Layers

A graph convolutional generative adversarial network (GCGAN) is proposed to provide recommendations for new users or items. To maintain scalability, the discriminator was improved to capture the latent features of users and items, using graph convolution from a minibatch-sized bipartite graph. In the experiment using MovieLens, it was confirmed that the proposed GCGAN had better performance than the conventional CFGAN, when MovieLens 1M was employed with sufficient data. The proposed method is characterized in such a manner that it can learn domain information of both, users and items, and it does not require to relearn a model for a new node. Further, it can be developed for any service having such conditions, in the information recommendation field.

On Both Cold-Start and Long-Tail Recommendation with Social Data

The number of “hits” has been widely regarded as the lifeblood of many web systems, e.g., e-commerce systems, advertising systems and multimedia consumption systems. However, users would not hit an item if they cannot see it, or they are not interested in the item. Recommender system plays a critical role of discovering interesting items from near-infinite inventory and exhibiting them to potential users. Yet, two issues are crippling the recommender systems. One is “how to handle new users”, and the other is “how to surprise users”. The former is well-known as cold-start recommendation. In this paper, we show that the latter can be investigated as long-tail recommendation. We also exploit the benefits of jointly challenging both cold-start and long-tail recommendation, and propose a novel approach which can simultaneously handle both of them in a unified objective. For the cold-start problem, we learn from side information, e.g., user attributes, user social relationships, etc. Then, we transfer the learned knowledge to new users. For the long-tail recommendation, we decompose the overall interesting items into two parts: a low-rank part for short-head items and a sparse part for long-tail items. The two parts are independently revealed in the training stage, and transfered into the final recommendation for new users. Furthermore, we effectively formulate the two problems into a unified objective and present an iterative optimization algorithm. A fast extension of the method is proposed to reduce the complexity, and extensive theoretical analysis are provided to proof the bounds of our approach. At last, experiments of social recommendation on various real-world datasets, e.g., images, blogs, videos and musics, verify the superiority of our approach compared with the state-of-the-art work.

Towards yeast taxogenomics: lessons from novel species descriptions based on complete genome sequences.

In recent years, 'multi-omic' sciences have affected all aspects of fundamental and applied biological research. Yeast taxonomists, though somewhat timidly, have begun to incorporate complete genomic sequences into the description of novel taxa, taking advantage of these powerful data to calculate more reliable genetic distances, construct more robust phylogenies, correlate genotype with phenotype and even reveal cryptic sexual behaviors. However, the use of genomic data in formal yeast species descriptions is far from widespread. The present review examines published examples of genome-based species descriptions of yeasts, highlights relevant bioinformatic approaches, provides recommendations for new users and discusses some of the challenges facing the genome-based systematics of yeasts.

ML2E: Meta-Learning Embedding Ensemble for Cold-Start Recommendation

Cold-start problem has been recognized as the most crucial challenge in recommender systems. Many recommendation algorithms work well when lots of preference information is available but start to degrade in cold-start settings. Inspired by the spirit of meta-learning, we identified that the appeal of cold-start problems and the superiority of meta-learning are congruous where meta-learning aims to learn a model from a small set of labeled examples (users' consuming history), and then this model can be quickly generalized to new tasks (recommendation for new users or new items). Therefore, faced with the extreme cold-start scenario, we proposed a meta-learning embedding ensemble (ML2E) recommendation algorithm to forecast new users' preference and generate desirable initial embedding for new items. It's worth pointing out that the training process of ML2E only uses few first-order gradient information, and ML2E not only has the incremental mining ability for different mini-batches on the same task but also the generalization ability for different tasks. Finally, we validated ML2E on two benchmark datasets, experimental results showed that our algorithm has significantly improved recommendation metric in comparison with three existing baselines.

A benchmark for Monte Carlo simulation in gamma-ray spectrometry

Monte Carlo (MC) simulation is widely used in gamma-ray spectrometry, however, its implementation is not always easy and can provide erroneous results. The present action provides a benchmark for several MC software for selected cases. The examples are based on simple geometries, two types of germanium detectors and four kinds of sources, to mimic eight typical measurement conditions. The action outputs (input files and efficiency calculation results, including practical recommendations for new users) are made available on a dedicated webpage.

Addressing the user cold start with cross-domain collaborative filtering: exploiting item metadata in matrix factorization

Providing relevant personalized recommendations for new users is one of the major challenges in recommender systems. This problem, known as the user cold start has been approached from different perspectives. In particular, cross-domain recommendation methods exploit data from source domains to address the lack of user preferences in a target domain. Most of the cross-domain approaches proposed so far follow the paradigm of collaborative filtering, and avoid analyzing the contents of the items, which are usually highly heterogeneous in the cross-domain setting. Content-based filtering, however, has been successfully applied in domains where item content and metadata play a key role. Such domains are not limited to scenarios where items do have text contents (e.g., books, news articles, scientific papers, and web pages), and where text mining and information retrieval techniques are often used. Potential application domains include those where items have associated metadata, e.g., genres, directors and actors for movies, and music styles, composers and themes for songs. With the advent of the Semantic Web, and its reference implementation Linked Data, a plethora of structured, interlinked metadata is available on the Web. These metadata represent a potential source of information to be exploited by content-based and hybrid filtering approaches. Motivated by the use of Linked Data for recommendation purposes, in this paper we present and evaluate a number of matrix factorization models for cross-domain collaborative filtering that leverage metadata as a bridge between items liked by users in different domains. We show that in case the underlying knowledge graph connects items from different domains and then in situations that benefit from cross-domain information, our models can provide better recommendations to new users while keeping a good trade-off between recommendation accuracy and diversity.

Minimizing Required User Effort for Cold-Start Recommendation by Identifying the Most Important Latent Factors

Recommender systems have the effect of guiding users to interesting objects in a large space of possible options based on their preferences. However, providing accurate recommendations for new users, who do not have any records, is one of the most challenging problems in recommender systems. To retrieve sufficient information of the new users, existing solutions often require significant user effort to answer numerous questions. In this paper, we aim to propose a novel method that can build initial user profiles by requiring minimum user effort. In particular, non-negative matrix factorization is first adopted to extract only a few representative latent factors of the available items, which effectively reduces the problem dimensionality. A hybrid of personalized and non-personalized approach has then been proposed to iteratively collect users' feedback on the most important latent factors. In comparison with two state-of-the-art approaches, the proposed method requires less user effort while significantly improving the accuracy of the initial user profile.

Simplified Water Requirement Calculators for Fruits and Vegetables

New users of drip irrigation in Myanmar had no idea how much water to apply to their crops with drip and could not afford tensiometers or other soil moisture monitoring tools. The concept of a simple paper calculator was born out of their need for an easy-to-use yet inexpensive tool to estimate horticultural crop water requirements. We used a generalized crop coefficient and growth stage approach together with average evapotranspiration (ET) for the vegetable crops “Water Wheel” calculator and a canopy cover approach for the tree fruit calculator. Differences among published crop coefficients are relatively small for a large number of vegetables and single coefficients were used for groups of crops without putting farmers’ crops at risk. Vegetable crops were divided into two groups based on whether water requirements during harvest remained the same as for the flowering and fruiting stage or were reduced for the harvest period. A simplified canopy cover approach was used to determine water requirements for perennial fruit, tree, and vine crops. Our faith in the ability of farmers to make their own adjustments gave us confidence to simplify ET-based water requirements and make them available in the form of simple rotating disc calculators printed in color on laminated card stock. The calculators were welcomed by our staff and enabled them to provide reasonably reliable recommendations for new users of drip irrigation. When surveyed, field staff responded that 74% of farmers they advised followed Water Wheel recommendations. Rough estimates of fruit and vegetable water requirements reached a large number of new drip users in a form they could easily understand, thereby lowering adoption barriers for an unfamiliar technology. This paper describes the Water Wheel concept and design so nonspecialists might develop their own calculators using local climatic data.

Online Learning in Large-Scale Contextual Recommender Systems

In this paper, we propose a novel large-scale, context-aware recommender system that provides accurate recommendations, scalability to a large number of diverse users and items, differential services, and does not suffer from “cold start” problems. Our proposed recommendation system relies on a novel algorithm which learns online the item preferences of users based on their click behavior, and constructs online item-cluster trees. The recommendations are then made by choosing an item-cluster level and then selecting an item within that cluster as a recommendation for the user. This approach is able to significantly improve the learning speed when the number of users and items is large, while still providing high recommendation accuracy. Each time a user arrives at the website, the system makes a recommendation based on the estimations of item payoffs by exploiting past context arrivals in a neighborhood of the current user's context. It exploits the similarity of contexts to learn how to make better recommendations even when the number and diversity of users and items is large. This also addresses the cold start problem by using the information gained from similar users and items to make recommendations for new users and items. We theoretically prove that the proposed algorithm for item recommendations converges to the optimal item recommendations in the long-run. We also bound the probability of making a suboptimal item recommendation for each user arriving to the system while the system is learning. Experimental results show that our approach outperforms the state-of-the-art algorithms by over 20 percent in terms of click through rates.

A Comprehensive Recommender System Model: Improving Accuracy for Both Warm and Cold Start Users

Sparsity of the ratings available in the recommender system database makes the task of rating prediction a highly underdetermined problem. This poses a limit on the accuracy and the quality of prediction. In this paper, we utilize secondary information pertaining to user’s demography and item categories to enhance prediction accuracy. Within the matrix factorization framework, we introduce additional supervised label consistency terms that match the user and item factor matrices to the available secondary information (metadata). Matrix factorization model—conventionally employed in collaborative filtering techniques—yields dense user and dense item factor matrices—the assumption is that users have an affinity toward all latent factors and items possess all latent factors. Our formulation, based on a recent work, aims to recover a dense user and a sparse item factor matrix—this is a more reasonable model. Human beings show a natural interest toward all the factors, but every item cannot possess all the factors; this leads to a sparse item factor matrix. A natural outcome of our proposal is a solution to the pure cold start problem. We utilize the label consistency map generated from the proposed model to make reasonable recommendations for new users and new items which have not (been) rated yet. We demonstrate the performance of our model for a movie recommendation system. We also design an efficient algorithm for our formulation.

Goal-Based Framework for Multi-User Personalized Similarities in e-Learning Scenarios

Web-based learning or e-Learning in contrast to traditional education systems offer a lot of benefits. This article presents the Goal-based Framework for providing personalized similarities between multi users profile preferences in formal e-Learning scenarios. It consists of two main approaches: content-based filtering and collaborative filtering. Because only traditional content-based filtering is not sufficient to generate the recommendations for new-users, therefore, the proposed work hybridized multi user's collaborative filtering functionalities with personalized content-based profile preferences filtering. The main purpose of this proposed work is to (a) overcome the user-based cold-start profile recommendations and (b) improve the recommendations accuracy for new-users in formal e-learning recommendation systems. The experimental has been done by using the famous ‘MovieLens' dataset with 15.86% density of the user-item matrix with respect to ratings, while the evaluation of experimental results have been performed with precision mean and recall mean to test the effectiveness of Goal-based personalized recommendation framework. The Experimental result Precision: 81.90% and Recall: 86.56% show that the proposed framework goals performed well for the improvement of user-based cold-start issue as well as for content-based profile recommendations, using multi users personalized collaborative similarities, in formal e-Learning scenarios effectively.