Informs Annual Meeting 2017

SC36

INFORMS Houston – 2017

SC36

2 - Outcomes-based Reimbursement Policies for Chronic Care Pathways Sasa Zorc, INSEAD, 1 Ayer Rajah Avenue, PhD Office, Singapore, 138676, Singapore, sasa.zorc@insead.edu, Stephen Chick, Sameer Hasija We develop an outcomes-based model of contracting in care of chronic patients, using data from United Kingdom’s NHS. The government contracts with healthcare providers in effort to maximise population health minus the cost. We consider the decision of whether to contract with individual healthcare providers or groups of such providers, as well as which contract type to use. Individual contracts fail to provide the desired incentives if providers under such contracts cooperate (collusion), however so do group contracts if group members fail to coordinate (free-riding). We demonstrate that individual outcomes-adjusted capitation contracts are the most resistant to these adverse effects. 3 - Directed Disease Networks based Multiple-Disease Risk Prediction Modeling Tingyan Wang, Tsinghua University, RM.519, Shunde Building, Beijing, 100084, China, wangty14@mails.tsinghua.edu.cn, Ming Yu, Runtong Zhang In this study, we propose a novel framework that combines directed disease network and collaborative filtering techniques to enhance multiple disease risk predictive modeling. Firstly, a directed disease network considering temporal information will be developed. Then based on this directed disease network, we investigate different disease risk score computing approaches. We validate the proposed methods with real-world datasets. The results demonstrate the potential value of the proposed modeling framework, e.g., a reference for medical experts to offer effective healthcare guidance for patients, or a tool that helps individuals create and maintain a better healthcare plan over time. 352C Applications and Methodological Issues on MCDA/M Sponsored: Multiple Criteria Decision Making Sponsored Session Chair: Adiel De Almeida-Filho, Brazil, ataf@cdsid.org.br Co-Chair: Roman Slowinski, Poznan University of Technology, Pl. Marii Sklodowskiej-Curie 5, NIP: 777-00-03-699, Poznan, 60-965, Poland, roman.slowinski@cs.put.poznan.pl 1 - Dominance Analysis of Conflict Amongst Bodies of Evidence for DST using DRSA One of the main problems encountered in Evidence Theory concerns with the identification when two bodies of evidence are high degree of conflict. Thus, different approaches have been developed in the literature without success. To circumvent such problems, this article develops the notion of consistency in conflict where it is possible formally to define when a metric or reduce set of metrics is consistent to classify the conflict. In addition, to obtain this set, the technique known as DRSA is used. In relation to conflict identification, it is possible to use DRSA to generate decision rules on classifying conflict which avoids using subjective thresholds that can be difficult to elicit. 2 - A TOPSIS with Intuitionistic Fuzzy Sets and DEA Approach to Evaluate Retail Industry Performance Ability Babek Erdebilli, Atılım University, Ankara, 06854, Turkey, babekd@atilim.edu.tr This research paper discusses a decision-making algorithm with hierarchical structure to find performance efficiencies in order to develop the performance evaluation process in RI in Turkey. The offer presents an Intuitionistic Fuzzy TOPSIS and DEA to utilize both qualitative and quantitative criteria. Firstly, IFTOPSIS can be used to handle more complex problems. At this stage, all qualitative values are weighted by IFTOPSIS; then, the alternatives are formulated by DEAs. It is shown that using the IFTOPSIS value as the only output into DEA classification is more accurate than just using the entire quantitative variables. Lucimario Gois de Oliveira Silva, Universidade Federal de Pernambuco, 1350 Av Cons Agiar, Boa Viagem 404 Flores, Recife-PE, 51011030, Brazil, lucio_gois@hotmail.com, Adiel Teixeira De Almeida Filho, Roman Slowinski, Salvatore Greco SC38

351F Service Science in the IT Industry Sponsored: Service Science Sponsored Session Chair: Aly Megahed, IBM Research - Almaden, San Jose, CA, 95123, United States, aly@gatech.edu 1 - Data Analytics for Pricing Highly-Valued IT Service Contracts Aly Megahed, IBM.Research - Almaden, 150 Palm Valley Blvd APT.2066, San Jose, CA, 95123, United States, aly@gatech.edu, Taiga Nakamura, Kugamoorthy Gajananan, Mark Smith, Gregory R.Heim Service providers in B2B (e.g., consulting, outsourcing, healthcare, logistics) often must prepare bids to win service outsourcing contracts. The contracting process can be expensive and highly uncertain as to whether a provider that bids will win a contract. This study presents a data analytics approach for pricing and winning service contracts in the IT industry. We propose a base model and model enhancements, using historical and market data. We show how our tools enhance insights and provide better visibility for contract managers of a real IT outsourcing service provider. 2 - Analytics Driven Business Travel Management Solution Pawan Chowdhary, IBM.Research, 650 Harry Road, E3-238, San Jose, CA, 95120, United States, chowdhar@us.ibm.com Business travel is essential to meet customers and for the company to grow. Mid to large enterprise has business travel as one of the largest spend items but still not managed efficiently. IBM Travel Manager is a solution that is catered for the Travel Program Manager to effectively manage travel spend and leverage analytics to get spend insights and savings opportunities. In the presentation we will go few such analytics and touch over cognitive aspect that will drive the travel manager to act upon opportunities pro-actively. 3 - Cognitive & Optimal Solution Composition for it Service Contracts Ahmed Nazeem, IBM.Research - Almaden, San Jose, CA, 95120, United States, ahmed.nazeem@ibm.com, Aly Megahed, Hamid Motahari, Taiga Nakamura, Hung N.(Nam) Ho-Nguyen For Information Technology (IT) service providers, composing a customized solution for a given request for proposal (RFP) is a tedious and time-consuming task. It requires a lot of expertise in reading and compiling the client’s requirements. Furthermore, composing a solution from existing services to meet the client’s requirement has a significant influence on the pricing of the deal, and hence, on the likelihood to win the deal. Given the complexity of the IT services, their range of attributes, and their inter- dependencies, their a need to develop an automated framework that provides an end-to-end efficient solution for technical solution managers. The project has two 2 main components: (i) a natural language processing components for parsing and compiling the RFP document, and (ii) an optimization component for composing the existing IT services in a way that increases the likelihood of winning the deal. To enable online solution composition, we develop efficient heuristic approaches using business insights and the domain knowledge. 352B Best IBM Service Science Student Paper Award Competition 3 Sponsored: Service Science Sponsored Session Chair: Robin Qiu, Penn State (The Pennsylvania State University), Penn State (The Pennsylvania State University), Malvern, PA, 19355, United States, robinqiu@psu.edu 1 - Proactive Inpatient Bed Reservations from ED to Reduce Patient Boarding Seung Yup Lee, Wayne State University, 673 Prentis Street, Detroit, MI, 48201, United States, seung.lee@wayne.edu, Ratna Chinnamm, Evrim Dalkiran, Seth Krupp, Michael Nauss We explore the benefits of early task initiation for the service network spanning the ED and inpatient units within a hospital. In particular, we investigate the value of proactive bed reservation signals based on future state information of ED patients to reduce ED patient boarding using a fork-join queueing system. Model accounts for the performance of the predictive analytics model for disposition decision. Our results show that proactive bed reservations can lead to significant reductions in ED patient boarding. The insights gained from our models should encourage hospital managers to embrace proactive coordination and adaptive work flow technologies enabled by modern health IT systems. SC37

80