Decision Making under Uncertainty: Methodologies from Signal Processing & Forecasting

To better cope with business environments that are information-intensive, complex, and highly dynamic, companies increasingly rely on intelligent, data-driven methods to automatically “learn” from experiences over time to improve future decision-making. However, reliable data-driven induction depends on two critical ingredients: an effective induction (learning) method, and informative, relevant data. Importantly, the capacity of even the most effective technique to extract a reliable model of any real-world phenomenon is bounded by what information is available about prior experiences. In practice, organizations often acquire information only passively, through routine business transactions. However, the opportunity costs of acquiring information only passively can be substantial.

This challenge poses some fundamental and fascinating scientific questions: How does one enable predictive modeling techniques to reason intelligently about opportunities to actively acquire information? How should knowledge (or uncertainty) about the particular decisions that predictive models aim to inform, influence what information is best to acquire? And how can we incorporate prior knowledge into data-driven learning, so as to mitigate the high cost of learning from scratch? I will present an overview of my research on economic data mining in which I address these and related questions. I will also present results of the applications of the methods I developed to a broad range of decision problems, including in the context of market mechanism design, personalized marketing, recommender systems, and fraud detection.

Maytal Saar-Tsechansky and Foster Provost, “Decision-centric Active Learning of Binary-Outcome Models”, Information Systems Research, Vol. 18, No. 1, pp. 1–19, 2007

Emotions as social currency: How do people evaluate the risks of emotion expression?

In every social situation people decide anew whether to express or suppress emotions. Particularly in organisations emotion expression is essential for achieving individual goals such as building trust in relationships or persuading a counterpart of a certain point of view. However, emotion expression can also defeat its purpose and make the expresser vulnerable. To understand how individuals evaluate the risks of emotion expression, a theoretical framework building on prospect theory (Kahneman & Tversky, 1979) is presented. It is proposed that also when it comes to emotion expression people are risk-seeking in loss situations and risk-averse in gain situations. However, the riskiness of emotion expression is expected to vary with the nature of the emotion involved. This framework introduces a new theoretical perspective on emotion expression, and seeks to explain how emotion expression is utilised and can be utilised as a social currency in organisations.