Professor of Decision Sciences
Professor of Decision Sciences
Recent Working Papers
Babic, B., Gaba, A., I. Tsetlin and R.L. Winkler (2022), “Resolute and Correlated Bayesians,”
Chen, Z., Gaba, A., I. Tsetlin and R.L. Winkler (2022), “Evaluating Quantile Forecasts,” International Journal of Forecasting, forthcoming.
Babic, B., Gaba, A., I. Tsetlin and R.L. Winkler (2021), “Normativity, Epistemic Rationality and Noisy Statistical Evidence,” British Journal for the Philosophy of Science, forthcoming.
Makridakis, S., Spiliotis, E., Assimakopoulos, V., Chen, Z., Gaba, A., I. Tsetlin and R.L. Winkler (2021), “The M5 uncertainty competition: Results, findings and conclusions,” International Journal of Forecasting, forthcoming.
Gaba, A., D. Popescu and Z. Chen (2019), “Assessing Uncertainty from Point Forecasts,” Management Science, 65, 90-106.
Gaba, A., I. Tsetlin and R.L. Winkler (2017), "Combining Interval Forecasts," Decision Analysis 14.1, 1-20.
Jain, K., Mukherjee, K., J.N. Bearden and A. Gaba (2013), “Unpacking the Future: A Nudge Towards Wider Interval Forecasts,” Management Science 59, 1970-1987.
Makridakis, S., R.M. Hogarth and A. Gaba (2010), “Why Forecasts Fail. What to Do Instead,” Sloan Management Review, 51, no.2 (Winter), 83-90.
Makridakis, S., R.M. Hogarth and A. Gaba (2009), “Forecasting and Uncertainty in the Economic and Business World,” International Journal of Forecasting 25, 794-812.
Tsetlin, I., A. Gaba and R.L. Winkler (2004). “Strategic Choice of Variability in Multiround Contests and Contests with Handicaps,” Journal of Risk and Uncertainty 29, 143-158.
Gaba, A., I. Tsetlin and R.L. Winkler (2004). “Modifying Variability and Correlations in Winner-Take-All Contests,” Operations Research 52, 384-395.
Gaba, A. and A. Kalra, (1999). “Risk Behavior in Response to Quotas and Contests,” Marketing Science 18, 417-434.
Gaba, A. and W.K. Viscusi (1998), “Differences in Subjective Risk Thresholds: Worker Groups as an Example,” Management Science 44, 801-811.
Gaba, A. and R.L. Winkler (1995), “The Impact of Testing Errors on Value of Information: A Quality Control Example,” Journal of Risk and Uncertainty 10, 5-13.
Gaba, A. (1993), “Inferences with an Unknown Noise Level in a Bernoulli Process,” Management Science 39, 1227-1237.
Gaba, A. and R.L. Winkler (1992), “Implications of Errors in Survey Data: A Bayesian Model,” Management Science 38, 913-925.
Winkler, R.L. and A. Gaba (1990), “Inference with Imperfect Sampling from a Bernoulli Process,” Studies in Bayesian Econometrics and Statistics, Volume 7 (Bayesian and Likelihood Methods in Statistics and Econometrics), S. Geisser, J. Hodges, S.J. Press, and A. Zellner (Eds.), North Holland : Amsterdam, 303-317.
Makridakis, Spyros G., Robin M. Hogarth, and Anil Gaba (2009). Dance with chance: Making luck work for you. Simon and Schuster.
Makridakis, S. and A. Gaba (1998), “Judgment: Its Role and Value for Strategy,” in G. Wright and P. Goodwin (eds.), Forecasting with Judgment, Chichester: Wiley.
MBA: Uncertainty, Data, and Judgment (Core Course)
Regardless of the setting, management decisions are necessarily made under conditions of risk and uncertainty. The broad objective of this course is to enable the participants to embrace and manage risk and uncertainty, rather than be blindsided by it. The course highlights the overarching challenges in assessment of risk and uncertainty and our susceptibility to illusion of control, some fundamental concepts of probability and statistics, strengths and weakness of quantitative models, some common cognitive biases in human intuition, and a prescriptive approach of combining quantitative models with judgment. While the course uses some technical concepts of probability and statistics, the emphasis is on sharpening intuition related to risk and uncertainty for a management career.
Nominated for Outstanding Teacher Award MBA Core Course every year except one since 1993, and won the award fourteen times: 1993, 1996, 1998, 1999, 2001, 2003, 2004, 2005, 2012, 2013, 2016, 2017, 2019, 2020.
Ph.D.: Bayesian Analysis
This course introduces philosophy and methods of Bayesian inference and prediction, with emphasis on the general approach of modeling real-world problems of interest to data analysts and decision makers. Topics include subjective probability, evaluation of probabilities, modeling data-generating processes, development of priors, inference and prediction for various processes, Bayesian estimation and hypothesis testing, and comparisons with classical/frequentist methods.
Executive Teaching: Judgment
This includes a variety of combinations based on the three modules below.
A. Data, Models, and Illusion of Control
A senior management team along with the board of directors regularly look into the future and create a vision and subsequently craft a strategy towards that vision. A home team of a nation must continuously view the existing and the future world through multiple windows and then allocate limited resources to various initiatives for the security of that nation. The financial industry is the quintessential context for management of risk and uncertainty. However, there often exist severe limits to predicting the future, be it in the context of business, investments, policy, health, or even personal pursuits such as happiness. We then look for shelter in “engineered models” to accurately predict future outcomes. In doing so, we frequently go too far and often end up underestimating the role of chance and what we don’t control, we overestimate our ability to predict the future, underestimate risk and uncertainty, and hence fall prey to Illusion of Control with all its potential costs. A counterpart to this is the Paradox of Control: if we don’t try to control what we can’t control, we often end up with more beneficial outcomes.
Understanding and embracing uncertainty as an opportunity, developing options and flexibility in the face of uncertainty, role of a leader.
B. Discernment: Cognitive Biases, Emotional Barriers, and Barriers to Learning
Stemming from our illusion of control, while making decisions, we are susceptible to cognitive biases, emotional barriers (such as greed, fear, and hope), and obstacles to learning (such as self-serving attribution, lack of experimentation). Such distortions in individual decision making are illustrated with a variety of interactive online tools and some nudges are outlined to mitigate such distortions.
Budgeting and projections, performance reviews, evaluating downside/upside for risk management, stopping losing projects, alleviating inaction, fostering innovation and experimentation, defining organizational culture through leaders.
C. Diversity and Inclusiveness: A Judgmental View
Abundant theories exist on the importance of diversity and inclusiveness (D&I) at an organizational and societal level. Yet, the effectiveness of such initiatives despite heavy investments and good intentions remains an open question. This module highlights a value proposition for D&I as a fundamental aspect of improving the quality of judgments at an organizational level. It is well known that individual judgments, including judgments of experts in their domains, are susceptible to a variety of cognitive biases, emotional barriers and obstacles to learning. While such unconscious distortions in individual judgments can be mitigated through a variety of nudges, group-based judgments can be a powerful way to improve the quality of judgments. And, in leveraging the full potential of group judgments, D&I is a key factor. A tangible and constructive meaning of diversity and inclusiveness in a group judgment process is proposed. The practical implications cover various types of organizational and societal decision-making processes, the role of experts and leaders, and making the D&I initiatives effective with the correct messaging, with an overarching goal of improving judgments.
Individual judgments vs. group judgments, defining diversity, creating and managing a diverse team, defining and managing experts, the role of leaders and creating personal impact.
Some representative executive programs in which the Judgment modules are taught:
Open Enrollment Programs:
Company Specific Programs:
Singapore Home Team (various organizations of the Ministry of Home Affairs in Singapore)
Tata Consulting Services
Online Teaching Tools developed:
- Judgment Survey. The purpose of this tool is to highlight a variety of biases in human judgment in different real-life contexts, and to allow the possibility of benchmarking those biases for different population groups (for example, by demographics, culture, and institutions) against a reference population of interest. For example, we can benchmark different departments in an organization against a reference population (for example, another organization).
- Game of Experts Trivia. The purpose of this tool is to highlight the overconfidence bias in assessments of uncertainty, and to create a learning experience towards reducing the overconfidence bias. The tool enables an interactive exercise in several groups simultaneously, where participants engage in a game akin to a prediction market based on interval forecasts (rather than point forecasts) of trivia questions. The tool then generates a group-level report for participants.
- Game of Experts Real-Life. The purpose of this tool is to highlight the overconfidence bias in assessments of uncertainty, and to create a learning experience towards reducing the overconfidence bias. The tool enables an interactive exercise in several groups simultaneously, where participants engage in a game akin to a prediction market based on interval forecasts (rather than point forecasts) of real-life quantities. The tool then generates a group-level report for participants.
- Wisdom of Crowds. With this tool, the participants provide subjective estimates of unknown quantities, individually and in groups, in a variety of ways administered by the facilitator. The results provide an extensive platform for discussion of individual vs. group judgment.
Service at INSEAD
Governance Task Force, 2020 – 2022.
Faculty Compensation Task Force, 2018 – ongoing.
Faculty Representative, INSEAD Board of Directors, 2018 – 2021.
Faculty Strategic Advisory Committee, 2020 – 2021.
COVID19 Crisis Management Team (CMT), 2020.
Area Chair, Decision Sciences, March 2019 – August 2019.
Dean Search Committee – 2012-13.
Faculty Evaluation Committee – 2010-11, 2012-13.
Dean of Faculty, September 2006 – December 2009.
Academic Director, Center of Decision Making and Risk Analysis, September 2003 – ongoing.
Dean Search Committee – 2005-06.
Dean of Faculty and Research, Asia Campus, September 2002 – August 2006.
Chair, Research and Development Committee, September 2001 – August 2006.
Faculty Evaluation Committee, 2002-03 – 2003-04.
Associate Dean of Faculty, Asia Campus, September 2001 – August 2002.
Area Chair, Technology Management Area, September 1998 – August 2001.
Member, Ph.D. Committee, September 1995 – August 2000.
Member, MBA Admissions Committee, 1995 - 1996.
Member, MBA Committee, 1991-1995.
Coordinator for INSEAD, EICEP (Euro-India Cooperation and Exchange Programme) sponsored by EFMD (European Foundation for Management Development), Brussels, 1991-1994.
Editorial Board, Decision Analysis, 2020 -
Academic Committee, M6 Forecasting Competition: The Nexus Between Forecasting and Investment Performance, 2021 -
Member of INFORMS, Special Section on Decision Analysis in INFORMS.
Ad hoc referee for academic journals on management, statistics, forecasting, and operations research.
Email: [email protected]
Phone: +65 6799 5334