Optimally balancing receiver and recommended users' importance in reciprocal recommender systems

Kleinerman‬‏, ‪Akiva; Rosenfeld, Ariel; Ricci, Francesco; Kraus, Sarit

doi:10.1145/3240323.3240349

Cited by 23 publications

(18 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, Shani et al [ 25 ] casted the recommendation problem as a Markov Decision Process (MDP) such that the long-term effects of each recommendation could be considered and the expected returns could be optimized. Similar optimization approaches have been proposed for movie recommendations [ 26 , 27 ], nutrition [ 28 ] and online dating [ 29 , 30 ], to name a few. To the best of our knowledge, none of the above works have addressed the domain specific challenges associated with medical assignments such as the time-sensitive nature of the process.…”

Section: Related Workmentioning

confidence: 99%

LBA: Online Learning-Based Assignment of Patients to Medical Professionals

Rosemarin

Rosenfeld

Lapp

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Central to any medical domain is the challenging patient to medical professional assignment task, aimed at getting the right patient to the right medical professional at the right time. This task is highly complex and involves partially conflicting objectives such as minimizing patient wait-time while providing maximal level of care. To tackle this challenge, medical institutions apply common scheduling heuristics to guide their decisions. These generic heuristics often do not align with the expectations of each specific medical institution. In this article, we propose a novel learning-based online optimization approach we term Learning-Based Assignment (LBA), which provides decision makers with a tailored, data-centered decision support algorithm that facilitates dynamic, institution-specific multi-variate decisions, without altering existing medical workflows. We adapt our generic approach to two medical settings: (1) the assignment of patients to caregivers in an emergency department; and (2) the assignment of medical scans to radiologists. In an extensive empirical evaluation, using real-world data and medical experts’ input from two distinctive medical domains, we show that our proposed approach provides a dynamic, robust and configurable data-driven solution which can significantly improve upon existing medical practices.

show abstract

Section: Related Workmentioning

confidence: 99%

LBA: Online Learning-Based Assignment of Patients to Medical Professionals

Rosemarin

Rosenfeld

Lapp

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Since the introduction of RCF, a number of improvements to the system, or alternative hybrid RRSs have been designed. Kleinerman et al designed a modification to RCF to account for user popularity [2] and also tested explanations for the recommendations made by RCF, finding that users provided with explanations for their recommendations were more likely to use them [3]. Neve et al designed a collaborative filtering algorithm based on latent factors, and found that this improved on the efficiency of RCF on large datasets [22].…”

Section: Reciprocal Recommendationmentioning

confidence: 99%

“…Success based on matches would not be achieved by recommending the top users on the service, as these users match with a very small percentage of their recommendations, so even if it achieved one-way success, it would not generate a high precision in this evaluation. In order to ensure fairness, it would be straightforward to apply existing reciprocal methods such as [2].…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…This type of service is in the minority -most online dating services use images, and some very popular ones such as Tinder 1 encourage users to make initial decisions based entirely on images. There is informal evidence that users on dating services overwhelmingly make decisions based on image data, even when detailed text profiles are available 2 . In addition, recent social networks such as Instagram 3 often focus on images rather than written or categorical content.…”

mentioning

confidence: 99%

See 1 more Smart Citation

ImRec: Learning Reciprocal Preferences Using Images

Neve

McConville

2020

Fourteenth ACM Conference on Recommender Systems

View full text Add to dashboard Cite

Reciprocal Recommender Systems are recommender systems for social platforms that connect people to people. They are commonly used in online dating, social networks and recruitment services. The main difference between these and conventional user-item recommenders that might be found on, for example, a shopping service, is that they must consider the interests of both parties. In this study, we present a novel method of making reciprocal recommendations based on image data. Given a user's history of positive and negative preference expressions on other users images, we train a siamese network to identify images that fit a user's personal preferences. We provide an algorithm to interpret those individual preference indicators into a single reciprocal preference relation. Our evaluation was performed on a large real-world dataset provided by a popular online dating service. Based on this, our service significantly improves on previous state-of-the-art content-based solutions, and also out-performs collaborative filtering solutions in cold-start situations. The success of this model provides empirical evidence for the high importance of images in online dating.

show abstract

“…Für eine möglichst realitätsnahe Betrachtung der Interaktionen von Plattform zu Nutzer und Nutzer zu Nutzer werden in Abbildung 1 die in der Simulation betrachteten relevanten Attribute und Methoden der einzelnen Akteure dargestellt. Die Nutzer der Plattform werden durch persönliche, plattformunabhängige Attribute (1) und plattformbasierte Attribute charakterisiert (2,3). Initialisiert werden die plattformunabhängigen Attribute anhand der Profilbild-Studie 2019/2020 [27].…”

Section: Abbildung 1 Statisches Systemverhaltenunclassified

Der Einfluss von Matching-Algorithmen auf den Erfolg einer Dating-App

Mertens¹,

Müller²,

Sebastian³

2020

WI2020 Zentrale Tracks

View full text Add to dashboard Cite

Für den Erfolg von Online-Dating-Plattformen sind Matching-Algorithmen, die für passende, zielorientierte Partnervorschläge verantwortlich sind, von übergeordneter Bedeutung. Fokus dieser Arbeit ist die Betrachtung einer differenzierten Maximierung der wahrgenommenen Zufriedenheit der gesamten Population einer Dating App in Abhängigkeit von ihren Motiven zur Anmeldung auf dieser Plattform. Es wurden verschiedene Matching-Algorithmen implementiert und deren Erfolg verglichen. Es konnte festgestellt werden, dass ein Preferred Proposing (individualisierte Partnervorschläge) gegenüber zufälligen Partnervorschlägen zu einer maßgeblichen Steigerung der wahrgenommenen Zufriedenheit der Population führt. Weiterhin konnte die negative Auswirkung von Werbung und Fakeprofilen innerhalb der Plattform quantifiziert werden. Die stochastische agentenbasierte Simulation wurde mit AnyLogic PLE durchgeführt. Auf dieser Grundlage wurde das Matching-Verhalten der heterogenen Population visualisiert. Mit Hilfe dieser Visualisierung lässt sich das Verhalten der gesamten Population global sowie auf Ebene des Individuums präzise betrachten und nachvollziehen.

show abstract

Optimally balancing receiver and recommended users' importance in reciprocal recommender systems

Cited by 23 publications

References 13 publications

LBA: Online Learning-Based Assignment of Patients to Medical Professionals

LBA: Online Learning-Based Assignment of Patients to Medical Professionals

ImRec: Learning Reciprocal Preferences Using Images

Der Einfluss von Matching-Algorithmen auf den Erfolg einer Dating-App

Contact Info

Product

Resources

About