Our faculty explore many themes within business analytics, decision sciences and quantitative analysis: healthcare analytics, analytics-driven decision making, social media analytics, workforce analytics, sensor-based and real-time analytics, the wisdom of the crowd, online platforms and recommendation systems.
This area explores healthcare issues related to patients, providers and payers. With respect to patients, our faculty have developed patient-centric healthcare and disease progression models. Relating to providers and payers, our faculty have developed decision support for hospitals and examined policies for healthcare coalitions including insurers and Medicare, respectively. Our faculty have provided analytical support to the Food and Drug Administration that enables the FDA to more accurately predict pharmaceutical product quality problems. Our faculty also examine social support of online health communities that can potentially connect patients with providers. Moreover, our faculty also conduct field studies to leverage social influence to motivate healthy behavior change.
Our faculty employ many different analytic techniques that support decision making. For example, in the context of healthcare operations, our faculty have employed Markov decision processes as a mathematical framework to model decision making. For designing service systems wherein customer heterogeneity information is available, our faculty have employed a queuing model to better manage customer expectations that are waiting for a service. In the context of humanitarian operations, our faculty have employed multi-period optimization to determine the location of global vehicle logistics hubs to respond to mega disasters. In the context of sustainable operations, our faculty have employed multi-period stochastic optimization models to analyze investments in renewable energy and energy storage.
This area focuses on big data environments through the analysis of social media data available online. Our faculty are interested in establishing connections between data generated by users in social media platforms and business, organizational and public policy outcomes. Work in this area typically combines recent techniques in machine learning and statistics to extract information from large, often unstructured datasets. In e-commerce setting, our faculty have analyzed the role of live chatting tools, and quantified the substitution pattern between live chat conversations and seller reputation.
Providing actionable insights to address workforce issues such as acquiring, rewarding, and retaining talent are prominent on the corporate agenda. Our faculty have explored staffing and turnover issues at hospitals, designed the staffing strategy for the base agents and cloud-based agents in call centers, compared the effect of hiring IT and non-IT labor from structurally diverse network of firms, and examined the role of IT in the displacement of service workers.
Industry 4.0 has brought about a world that is increasingly connected. At the heart of many of these connections are sensors embedded in numerous technologies. These sensors play a pivotal role in society today, particularly in automation, smart homes, Internet of Things, and other environments. Our faculty focus on developing novel approaches for analyzing the data generated from these devices for numerous applications, including mobile health, ICS cybersecurity, and AI-based cybersecurity applications.
This research includes the development of quantitative procedures for combining information from multiple experts to estimate uncertain or unknown variables. These methods allow a manager to improve decision making by harnessing the wisdom of the crowd. Our faculty have also explored factors that can enhance the crowd-based donation platforms for charitable fund-raising. Using a latent class model, we identify leaders in the crowd, and provide insights into how to alleviate the rich get richer problem.
Online platforms—for example, Craigslist, Amazon Marketplace, Airbnb and Uber—connect buyers with sellers, thus, helping manage demand and supply in an aggregated fashion. Our faculty are interested in the design and operations of online marketplaces with an emphasis on optimizing supply-side operations. On such platforms, a recommendation system is an information filtering system that predicts preference, or, rating, that a user would give to an item. Our faculty research seeks to quantify recommendation stability, the measure of the extent to which a recommendation algorithm provides predictions that are consistent with each other, and proposes an approach to develop recommendation stability.
Examples of Research in Business Analytics, Decision Sciences, and Operations Research
As the variety of products on the market continues to expand, retailers are faced with difficult decisions about their stock assortments. Taking into account the heterogeneity of customer preferences, customer’s willingness to substitute a second or third choice if their first choice is unavailable, and the dissatisfaction customers experience when they cannot purchase their preferred brands, M.A. Venkataramanan and his colleagues propose and test a model for retail category assortment that allows managers to balance customer satisfaction with short-term profit. See the associated video here.
- Ravi Anupindi, Sachin Gupta and M.A. Venkataramanan, “Managing Variety on the Retail Shelf: Using Household Scanner Panel Data to Rationalize Assortments,” Retail Supply Chain Management, N. Agarwal and S.A. Smith (ed.), pages 155–182, 2009.
Concerns over patient-care quality have prompted both state and national legislators to consider mandating nurse-to-patient ratios in hospitals. At the same time, the country continues to face shortages in qualified nursing staff. These dual constraints place a burden on hospital administrators to develop nursing schedules that not only meet specified ratios while keeping costs in check, but are also attractive to nurses who are in high demand. Kurt Bretthauer and his colleagues address this problem by proposing a scheduling model that takes into account not only costs and nurse-to-patient ratios but also the desirability of the schedule from the nurse’s perspective. See the associated video here.
- P. Daniel Wright, Kurt M. Bretthauer, Murray J. Côté, “Reexamining the Nurse Scheduling Problem: Staffing Ratios and Nursing Shortages,” Decision Sciences Journal, 37(1), pages 39–70, 2006.
The efficient flow of hospital patients between different units of care is not only a crucial element of effective treatment but also an important consideration in conserving resources and managing revenue. With this study, the researchers consider the “blocking” problem that occurs when at-capacity units cannot accommodate patients, causing some patients to remain in a higher unit of care than they require and others to be turned away from the hospital. By creating a simplified and highly accurate model of patient flow, Kurt Bretthauer and his colleagues provide a tool for determining the optimal mix of beds within a hospital’s budget constraints and specified management objectives.
- Kurt M. Bretthauer, H. Sebastian Heese, Hubert Pun, and Edwin Coe, “Blocking in Healthcare Operations: A New Heuristic and an Application,” Production and Operations Management, 20 (3), pages 375-391, 2011.
Recommendation stability measures the extent to which a recommendation algorithm provides predictions that are consistent with each other. Several approaches have been proposed in prior work to defining, measuring, and improving the stability of recommendation algorithms. Previous studies have focused primarily on understanding and evaluating recommendation stability in prediction-oriented settings, i.e., recommendation settings where it is crucial to provide the precise prediction of a user’s preference rating for an item. Jingjing Zhang and her colleagues build on prior work by generalizing the notion of stability to a broader set of recommendation settings and developing corresponding stability metrics. They provide a comprehensive empirical analysis of classification, ranking, and top-K stability performance of popular recommender algorithms on real-world rating data sets under a variety of settings.
- G. Adomavicius and Jingjing Zhang “Classification, Ranking and Top-K Stability of Recommendation Algorithms.” INFORMS Journal on Computing, 28 (1), pages 129-147, 2016.
In the aftermath of a mass-casualty incident, effective policies for timely evaluation and prioritization of patients can mean the difference between life and death. While operations research methods have been used to study the patient prioritization problem, prior research has either proposed decision rules that only apply to very simple cases, or proposed formulating and solving a mathematical program in real time, which may be a barrier to implementation in an urgent situation. Alex Mills connects these two regimes by proposing a general decision support rule that can handle survival probability functions and an arbitrary number of patient classifications. The proposed survival lookahead policy generalizes not only a myopic policy and a cμ type rule, but also the optimal solution to a version of the problem with two priority classes. This policy has other desirable properties, including index policy structure. Using simple heuristic parameterizations, the survival lookahead policy yields an expected number of survivors that is almost as large as published methods that require mathematical programming, while having the advantage of an intuitive structure and requiring minimal computational support.
- A. F. Mills “A Simple Yet Effective Decision Support Policy for Mass-Casualty Triage.” European Journal of Operational Research, 253(3), pages 734-745, 2016.
Using the wisdom of crowds—combining many individual judgments to obtain an aggregate estimate—can be an effective technique for improving judgment accuracy. In practice, however, accuracy is limited by the presence of correlated judgment errors, which often emerge because information is shared. To address this problem, Asa and his colleague propose an aggregation procedure called pivoting that adjusts a crowd's average judgment away from the average estimate of the judgment that all other respondents will provide on average. Data from four studies suggests that pivoting can significantly outperform classical averaging procedures.
- Asa Palley and J.B. Soll (forthcoming) “Extracting the Wisdom of Crowds When Information Is Shared.” Management Science.
This study examines how characteristics of a firm’s labor-flow network affect firm productivity. Using employee job histories, Fujie and her colleagues construct inter-firm labor-flow networks for both IT-labor and non-IT labor and analyze how a firm’s network structure for the two types of labor affects firm performance. They find that hiring IT workers from a structurally-diverse network of firms can substantially improve firm productivity, but the same is not true for hiring non-IT labor. These results demonstrate the importance of incorporating a network perspective in understanding the full impact of spillover effects from organizational hiring activities.
- L. Wu, Fujie Jin, and Lorin Hitt (forthcoming) “Are All Spillovers Created Equal? A Network Perspective on IT Labor Movements.” Management Science.
Although social support has been recognized for its effectiveness in promoting health, that social support may not always lead to good outcomes. By analyzing participants of an online weight‐loss community, Lucy shows that providing and receiving support affects weight‐loss outcomes in different ways. While providing support is positively associated with weight‐loss progress, receiving support could hinder the weight‐loss outcome for a person with high self‐efficacy. She finds evidence that the match between needed and received social support also influences individuals’ performance in the weight‐loss process, and a mismatch of social support could affect weight‐loss outcomes negatively. These findings can help maximize the usefulness of social support for participants, clinicians who refer individuals to online weight‐loss communities, and for the online community designers.
- L. Yan (2018) “Good Intentions, Bad Outcomes: The Effect of Mismatches in Social Support and Health Outcomes in an Online Weight Loss Community.” Production and Operations Management 27(1): 9-27.
Our faculty members hold several positions for the top journals in the field, including:
- Operations Research - Associate Editor: Rod Parker, 2012-present
- Decision Sciences Journal - Departmental Editors: Gil Souza, 2017-present; Alan Dennis, 2017-present
- Operations Management Education Review - Co-Editor: Kyle Cattani, 2018-present; Editorial Board: Doug Blocher, 2002-present
- Journal of Business Analytics – Associate Editors: Jingjing Zhang, 2018-present; Vijay Khatri, 2018-present
- European Journal of Operational Research - Guest Co-Editor, Special Issue on Humanitarian Operations Research: Alfonso Pedraza-Martinez, 2017.
Recent Selected Publications
- K. Bimpikis, W.J. Elmaghraby, K. Moon and W. Zhang (forthcoming) “Managing Market Thickness in Online B2B Markets.” Management Science.
- H. Ahn, D.D. Wang, O. Q. Wu (forthcoming) “Asset Selling Under Debt Obligations.” Operations Research.
- S.A. Yang, N. Bakshi, C.J. Chen (forthcoming) “Trade Credit Insurance: Operational Value and Contract Choice.” Management Science.
- A.C. Johnston, M. Warkentin, A.R. Dennis, and M. Siponen (forthcoming) “Speak Their Language: Designing Effective Messages to Improve Employees’ Information Security Decision Making.” Decision Sciences Journal, 50(2): 245-284.
- J. Mejia and C. Parker (forthcoming) “When Transparency Fails: Bias and Financial Incentives in Ridesharing Platforms.” Management Science.
- S. Sharma and A. Mehra (forthcoming) “Entry of Platforms into Complementary Hardware Access Product Markets.” Marketing Science.
- S. Samtani, H. Zhu, and H. Chen (forthcoming) “Proactively Identifying Emerging Hacker Threats on the Dark Web: A Diachronic Graph Embedding Framework (D-GEF).” ACM Transactions on Privacy and Security (TOPS).
- S. Samtani, M. Kantarcioglu, and H. Chen (forthcoming) “Privacy Analytics.” ACM Transactions on Management Information Systems (TMIS).
- J. Mejia and C. Parker (2020) “Underrepresented and LGBT in the Sharing Economy: Bias and Financial Incentives in Ridesharing Platforms.” Management Science.
- B. Ata and X. Peng (2020) “An Optimal Callback Policy for General Arrival Processes: A Pathwise Analysis.” Operations Research, 68(2), 327-347.
- X. Cheng, J. Zhang, and L. Yan (2020) “Understanding the Impact of Individual Users’ Rating Characteristics on Predictive Accuracy of Recommender Systems.” INFORMS Journal on Computing, 32(2): 303-320.
- R. Kleber, M. Rainer, M. Reimann, G. C. Souza, and W. Zhang (2020) “Two-sided Competition with Vertical Differentiation in Both Acquisition and Sales in Remanufacturing.” European Journal of Operational Research, 284(2): 572-587.
- J. Schoenfelder, K. Bretthauer, P.D. Wright, and E. Coe (2020) "Nurse Scheduling with Quick-Response Methods: Improving Hospital Performance, Nurse Workload, and Patient Experience." European Journal of Operational Research, 283(1): 390-403.
- A.Borenich, Y. Dickbauer, M. Reimann, and G. C. Souza (2020) “Should a Manufacturer Sell Refurbished Returns on the Secondary Market to Incentivize Retailers to Reduce Consumer Returns?” European Journal of Operational Research, 282(2): 569-579.
- D. Cho and K. Cattani (2019) “The Patient Patient.” Decision Sciences Journal, 50(4): 756-785.
- A. Palley and J.B. Soll (2019) “Extracting the Wisdom of Crowds When Information is Shared.” Management Science, 65(5): 1949-2443.
- J. Mejia, A. Mejia, and F. Pestilli (2019) “Open Data on Industry Payments to Healthcare Providers Reveal Potential Hidden Costs to the Public.” Nature Communications, 10(1): 1-8.
- P. Serex and J.D. Blocher (2019) “Teaching Critical Thinking and Problem Solving in a Business Analysis Course,” Operations Management Education Review, 13: 143-172.
- V. Khatri and B. Samuel (2019) “The Current and Future Use of Various Analytics Applications for Managerial Work: Trends in Four Business Functions.” Communications of the ACM, 62(4): 100-108.
- B. Ata and X. Peng (2018) “An Equilibrium Analysis of a Multiclass Queue with Endogenous Abandonments in Heavy Traffic.” Operations Research 66(1): 163-183.
- J. Ferrer, J. Martin, M.T. Ortuño, A. J. Pedraza-Martinez, G. Tiradoand B. Vitoriano (2018) “Multi-Criteria Optimization for Last Mile Distribution of Disaster Relief Aid: Test Cases and Applications.” European Journal of Operational Research, 269(2): 501-515.
- M. Besiou, A. J. Pedraza-Martinez, and L. N. Van Wassenhove (2018) “OR Applied to Humanitarian Operations.” European Journal of Operational Research, 269(2): 397-405.
- R. Kleber, M. Reimann, G. C. Souza, and W. Zhang (2018) “On the Robustness of the Consumer Homogeneity Assumption with Respect to the Discount Factor for Remanufactured Products.” European Journal of Operational Research, 269(3): 1027-1040.
- A. Aydin and R.P. Parker (2018) “Innovation and Technology Diffusion in Competitive Supply Chains,” European Journal of Operational Research, 265(3): 1102-1114.
- L. Wu, F. Jin, and L. Hitt (2018) “Are All Spillovers Created Equal? A Network Perspective on IT Labor Movements.” Management Science, 64(7): 2973-3468.
- D. Dey, A. Kim, and A. Lahiri (2018) “Online Piracy and the ‘Longer Arm’ of Enforcement.” Management Science, 65(3): 955-1453.
- S. Villa and J.A. Castañeda (2018) “Transshipments in Supply Chains: A Behavioral Investigation.” European Journal of Operational Research, 269(2): 715-729.
- S. Samtani, S. Yu, H. Zhu, M. Patton, J. Matherly, and H. Chen (2018) “Identifying SCADA Systems and their Vulnerabilities on the Internet of Things: A Text Mining Approach.” IEEE Intelligent Systems, 33(2): 63-73.
- M. Arikan, B. Ata, J. Friedewald, and R. Parker (2018) “Enhancing Kidney Supply Through Geographic Sharing in the United States.” Production and Operations Management, 27(12): 2103-2121.