Solving a Potential Clustering Game

2019 ◽  
Vol 28 (02) ◽  
pp. 1950006
Author(s):  
Kahina Bouchama ◽  
Arnaud Lallouet ◽  
Mohammed Said Radjef ◽  
Lakhdar Sais

Data clustering is the unsupervised classification of a set of objects into groups (clusters), according to their similarities. This can be seen as a form of equilibrium, which is the motivation that led to recent formulations of the data clustering task using game theoretic models. In this context, we propose a novel game-theoretic clustering approach reducing the clustering task to that of searching for a pure Nash equilibrium of a potential game, which corresponds to a stable clustering. Interestingly, the existence and the convergence towards such equilibrium are established, and we experimentally prove that such stability is not always guaranteed by the classical k-means algorithm. We also propose an iterative best-response algorithm for solving this potential clustering game. This algorithm is implemented and tested on several real-world and artificial datasets. Considering most of clustering quality measures, the obtained results are compared to those provided by both the classical k-means and by an hybridization of these two algorithms.

2017 ◽  
Vol 33 (3) ◽  
pp. 615-622 ◽  
Author(s):  
Joonkyum Lee ◽  
Bumsoo Kim

We address a two-firm booking limit competition game in the airline industry. We assume aggregate common demand, and differentiated ticket fare and capacity, to make this study more realistic. A game theoretic approach is used to analyze the competition game. The optimal booking limits and the best response functions are derived. We show the existence of a pure Nash equilibrium and provide the closed-form equilibrium solution. The location of the Nash equilibrium depends on the relative magnitude of the ratios of the full and discount fares. We also show that the sum of the booking limits of the two firms remains the same regardless of the initial allocation proportion of the demand.


2016 ◽  
Vol 10 (5) ◽  
pp. 471-489 ◽  
Author(s):  
Zhenhong Du ◽  
Yuhua Gu ◽  
Chuanrong Zhang ◽  
Feng Zhang ◽  
Renyi Liu ◽  
...  

2010 ◽  
Vol 73 (13-15) ◽  
pp. 2332-2345 ◽  
Author(s):  
László Szilágyi ◽  
Lehel Medvés ◽  
Sándor M. Szilágyi

Author(s):  
Ning Wang ◽  
Xianhan Zeng ◽  
Renjie Xie ◽  
Zefei Gao ◽  
Yi Zheng ◽  
...  

2020 ◽  
Vol 79 (Suppl 1) ◽  
pp. 861-862
Author(s):  
Z. Izadi ◽  
T. Johansson ◽  
J. LI ◽  
G. Schmajuk ◽  
J. Yazdany

Background:The Rheumatology Informatics System for Effectiveness (RISE) Registry was developed by the ACR to help rheumatologists improve quality of care and meet federal reporting requirements. In the current quality program administered by the U.S. Centers for Medicare and Medicaid services, rheumatologists are scored on quality measures, and performance is tied to financial incentives or penalties. Rheumatoid arthritis (RA)-specific quality measures can only be submitted through RISE to federal programs.Objectives:This study used data from the RISE registry to investigate rheumatologists’ federal reporting patterns on five RA-specific quality measures in 2018 and investigated the effect of practice characteristics on federal reporting of these measures.Methods:We analyzed data on all rheumatologists who continuously participated in RISE between Jan 2017 to Dec 2018 and who had patients eligible for at least one RA-specific measure. Five measures were examined: tuberculosis screening before biologic use, disease activity assessment, functional status assessment, assessment and classification of disease prognosis, and glucocorticoid management. We assessed whether or not rheumatologists reported specific quality measures via RISE. We investigated the effect of practice characteristics (practice structure; number of providers; geographic region) on the likelihood of reporting using adjusted analyses that controlled for measure performance (performance in 2018; change in performance from 2017; and performance relative to national average performance). Analyses accounted for clustering by practice.Results:Data from 799 providers from 207 practices managing 213,757 RA patients was examined. The most common practice structure was a single-specialty group practice (53%), followed by solo (28%) and multi-specialty group practice (12%). Most providers (73%) had patients eligible for all five RA quality measures. Federal reporting of quality measures through RISE varied significantly by provider, ranging from no reporting (60%) to reporting all eligible RA measures (12.2%). Reporting through RISE also varied significantly by quality measure and was highest for functional status assessment (36%) and lowest for assessment and classification of disease prognosis (20%). Small practices (1-4 providers) were more likely to report all eligible RA quality measures compared to larger practices (21%, 6%; p<0.001). In adjusted analyses, solo practices were more likely than single-specialty group practices to report RA measures (42%, 31%; p<0.027) while multispecialty group practices were less likely (18%, 31%; p<0.001). Additionally, higher performance in 2018 and performance ≥ the national average performance was associated with federal reporting of the measures through RISE (p≤0.004).Conclusion:Forty percent of U.S. rheumatologists participating in RISE used the registry for federal quality reporting. Physicians using RISE for reporting were disproportionately in small and solo practices, suggesting that the registry is fulfilling an important role in helping these practices participate in national quality reporting programs. Supporting small practices is especially important given the workforce shortages in rheumatology. We observed that practices reporting through RISE had higher measure performance than other participating practices, which suggests that the registry is facilitating quality improvement. Studies are ongoing to further investigate the impact of federal quality reporting programs and RISE participation on the quality of rheumatologic care in the United States.Disclaimer: This data was supported by the ACR’s RISE Registry. However, the views expressed represent those of the authors, not necessarily those of the ACR.Disclosure of Interests:Zara Izadi: None declared, Tracy Johansson: None declared, Jing Li: None declared, Gabriela Schmajuk Grant/research support from: Pfizer, Jinoos Yazdany Grant/research support from: Pfizer


2005 ◽  
Vol 1281 ◽  
pp. 1399 ◽  
Author(s):  
A. Oliver ◽  
J. Martí ◽  
J. Freixenet ◽  
J. Pont ◽  
R. Zwiggelaar

Sign in / Sign up

Export Citation Format

Share Document