Top Research Papers on Recommender Systems

A hybrid recommender system for the movies ranking, where a movie based recommender system suggests the user about the movie that he should rank after performing the intelligent analysis using weighted approach.

The novelty of the proposed approach is that it provides personalized recommen- dations regardless of the research field and regardless of the user’s expertise.

It was found that the flow and quantitative growth of various detailed studies of recommendation systems interact with the business growth of the actual applied service field.

A novel approach called Retrieval-augmented Recommender Systems is introduced, which combines the strengths of retrieval-based and generation-based models to enhance the ability of RSs to provide relevant suggestions.

This survey reviews over 60 papers published in top conferences/journals and provides an elaborate taxonomy of fairness methods in the recommendation, and outlines some promising future directions on fairness in recommendation.

An overview of TRSs is provided, including a discussion of the motivation and basic concepts of T RSs, a presentation of the challenges in building TRSS, and a perspective on the future directions in this area.

It is shown that recommender systems trained with the proposed paradigm significantly outperform the current SOTA models on various datasets, and that incorporating Semantic IDs into the sequence-to-sequence model enhances its ability to generalize, as evidenced by the improved retrieval performance observed for items with no prior interaction history.

This research re-formulates the aforementioned three recommendation policies into prompt formats tailored specifically to the domain at hand, and indicates that ChatGPT achieves an optimal balance between cost and performance when equipped with list-wise ranking.

The primary aim of the Food Recommendation System is to suggest the best restaurant nearby along with food using the given user preferences, which takes the food preferences and ratings into consideration to recommend the food to the users.

This article presents a comprehensive survey that examines the technologies influencing the development of recommendation systems tailored for the metaverse and identifies the key trends and fundamental concepts associated with these systems.

The roles of exploration in recommender systems are examined in three facets: 1) system exploration to reduce system uncertainty in regions with sparse feedback; 2) user exploration to introduce users to new interests/tastes; and 3) online exploration to take into account real-time user feedback.

IoT-enabled soil nutrient monitoring with machine learning algorithms for crop recommendations streamlines crop selection, minimizing unnecessary inputs while maximizing yields, and contributes to economic growth by fostering sustainable practices and increased yields.

An overview of the traditional formulation of the recommendation problem, the classical algorithmic paradigms for item retrieval and ranking, and a number of recent developments in recommender systems research are discussed.

This project is to support folks that have an interest in reading and to influence those individuals who are inculcating the habit of reading by building a book recommendation system to assist people opt for the proper book that interests them and so encouraging them to read more.

This is the first comprehensive survey on DeviceRSs that covers a spectrum of tasks to fit various needs and provides a fine-grained and systematic taxonomy of the methods involved in each aspect, followed by a discussion regarding challenges and future research directions.

Recommender systems are machine learning systems that help us discover new products, media content, and services depending on their earlier activities to save time for all the viewers while finding the content of their taste.

The design and implementation of a web- based medicine recommendation system aimed at improving medication selection and adherence is presented, which leverages advanced machine learning algorithms to provide personalized medicine recommendations based on user profiles, medical history, and specific health conditions.

A novel approach to fashion recommendation by combining machine learning and deep learning techniques to create a robust recommendation system that demonstrates its effectiveness in enhancing user engagement and satisfaction while increasing the platform's revenue.

A sophisticated Recipe Recommendation System based on ingredients is presented, leveraging the power of Python, flask, and MongoDB to revolutionize the way people approach cooking by providing personalized and efficient recipe suggestions tailored to the ingredients users already have.

It is shown that the diversity of the audience of a news website is a valuable signal to counter popularity bias and to promote journalistic quality, in an analysis of a comprehensive dataset of news source reliability ratings and web browsing histories.

An AutoRec++ model to comprehensively address the various biases existed in user behavior data is proposed, which achieves better prediction accuracy and robustness than both DNN-based and non-DNN-based state-of-the-art models and is more effective in processing sparser user behavior data.

This survey will introduce techniques related to trustworthy recommendation, including but not limited to explainable recommendation, fairness in recommendation, privacy-aware recommendation, robustness in recommendation, user-controllable recommendation, as well as the relationship between these different perspectives in terms of trustworthy recommendation.

A comparative study on the different algorithms used to do recommendation popularly and build a hybrid model out of them to look at the latest techniques which incorporate the factor of time while recommending products.

The crop recommendation system is to define and state that the appropriate crop should be grown based on a number of relative parameters, including soil features like nitrogen, phosphorus, and potassium that are extracted from the soil through filtration, and weather conditions that are embedded in a dataset in the form of structured data.

This article describes the current challenges for introducing explainability within a large-scale industrial music recommender system and provides research perspectives on how explainability can be addressed in the context of MRSs.

This paper concludes the general procedures and major challenges for MRS, and introduces the existing MRS models according to four categories, i.e., Modality Encoder, Feature Interaction, Feature Enhancement and Model Optimization.

This paper shows through simulations that the collaborative-filtering nature of recommender systems and the nicheness of extreme content can resolve the apparent paradox: although blindly following recommendations would indeed lead users to niche content, users rarely consume niche content when given the option because it is of low utility to them, which can lead the recommender system to deamplify such content.

This tutorial focuses on the critical challenges of GNN-based recommendation and the potential solutions, and discusses how to address these challenges by elaborating on the recent advances of GMM models with a systematic taxonomy from four critical perspectives.

A novel music recommendation technique based on the identification of personality traits, moods, and emotions of a single user, starting from solid psychological observations recognized by the analysis of user behavior within a social environment is described.

An algorithm, dubbed ZEro-Shot Recommenders (ZESRec), that is trained on an old dataset and generalize to a new one where there are neither overlapping users nor overlapping items, a setting that contrasts typical cross-domain RS that has either overlapping users or items.

A new metric, commonality, is introduced that measures the degree to which recommendations familiarize a given user population with specified categories of cultural content and contributes to a growing body of scholarship developing `public good' rationales for machine learning systems.

Some common privacy mechanisms used in FedRSs are summarized and several novel attacks and defenses against security are reviewed, as well as some approaches to address heterogeneity and communication costs problems.

A general erasable recommendation framework, namely LASER, which consists of Group module and SeqTrain module, which can not only achieve efficient unlearning, but also outperform the state-of-the-art unlearning framework in terms of model utility.

A new debiased contrastive loss is introduced to solve the problems of suboptimal sampling and sample bias in Bayesian Pairwise Ranking, which provides sufficient negative samples and applies a bias correction probability to alleviate the sample bias.

This work reformulates recommendation as a multitask Markov Decision Process, where each task represents a set of similar users and finds that a task-specific policy is more effective than a single universal policy for all users.

This PhD research involves the integration of sustainability-driven goals into RS design to improve tourism development by providing sustainable recommendations.

Abstract: Career recommendation system aims to offer direction and assist students in selecting engineering streams with the help of a WebApp. Nowadays, there are more educational courses available, making it easier for students to pick courses that interest them. However, in the 22nd century, more than half of the youths do not exercise their freedom of choice and make wellinformed decisions. A number of factors contribute to this. One of the main reasons is the lack of awareness of all the available options. The other well-known hindrance is the family pressure of following a well-known or p...

A recommendation system tailored to enrich course discovery on Udemy, employing a context-based, collaborative, and hybrid approach that prioritizes personalization, diversity, and transparency, shaping the future of course recommendations on Udemy.

A conversational recommender system for recommending cameras that interact with users using functional requirements is proposed, which uses semantic reasoning techniques on ontologies and can provide recommendations accurately and satisfy users.

This project developed a drug recommendation system that uses various vectorization processes such as Bow, TF-IDF, Word2Vec, and Manual Feature Analysis to predict sentiment, which can be used to recommend the most appropriate drug for a given disease based on different classification algorithms.

Although Machine learning models can learn from data, in the original stages, they may bear some mortal intervention as the nested layers within pass the data through scales of colorful generalities, which ultimately makes them able of learning through their own crimes.

The basics of recommender system methodology are reviewed and the emerging arena of active recommender systems are looked at, which shows which advertisements to show to users.

This paper described the research environment for recommendation systems in grocery stores and provided a very relevant and practical business transformation scenario that helps businesses in comparable circumstances change their business models.

The aim of this survey is to present a thorough review of the state of the art of recommender systems that leverage psychological constructs and theories to model and predict user behavior and improve the recommendation process.

The experimental findings on the TMDB dataset provide a dependable model that is precise and generates more customized movie recommendations that consider the impact of personal and situational factors on the user experience.

The FEVR framework provides a structured foundation to adopt adequate evaluation configurations that encompass this required multi-facetedness and provides the basis to advance in the field.

A review of existing methodologies and practices of fairness in recommender systems, spotlighting promising opportunities in comprehending concepts, frameworks, the balance between accuracy and fairness, and the ties with trustworthiness with the ultimate goal of fostering the development of fairness-awareRecommender systems.

Three main recommendation techniques employed in in E-learning are reviewed: content-based, collaborative filtering-based and knowledge-based recommendations and the basic mechanism of these technique together with how they are used to fulfill the specific requirements in the context of E- learning are highlighted and presented.

The Biclique Similarity Ordering Recommendation algorithm is introduced, an application of maximal bicliques of bipartite graphs to recommendation systems that makes use of the notion of biclique similarity of a set of vertices in order to recommend items to users in a certain order of preference.

Every online platform on the internet needs to have some kind of recommendation system. A recommendation system will suggest products or services on a platform to a user, based on their preference and history. This increases user engagement on the platform, as they help the user in their choices. Hence, there is a need for a simple recommendation system solution. Recommendation system works by creating relations between products or the users; and by evaluation of those relations, it can suggest relevant products related to any product. Hybrid Recommendation combines the predictions of two or m...