Konstantinos Katsikopoulos

Professor of Behavioural Science, University of Southampton, UK

Website at the University of Southampton

Vita

Konstantinos' work combines behavioural science with analytics: He uses experiments to understand lay and expert decision-making under conditions of radical uncertainty; he uses this understanding to develop models of how such decisions should be made, and tests several models using machine learning methods. This approach is a rare success - the models are both accurate and transparent.

Konstantinos' group has developed tools for difficult problems such as detecting threats at security checkpoints in Afghanistan while minimising civilian casualties, regulating UK investment banks without stifling financial innovation, and predicting the incidence of flu in the US more reliably than Big Data. Such psychologically inspired quantitative models help set high standards of transparency and effectiveness for approaches such as machine learning algorithms. With the increasing use of artificial intelligence for decision support, understanding the rationale behind decisions is critical, especially in sensitive areas, future epidemics and other critical events.

Research interests

  • Decision making: Prescriptive and descriptive
  • Modeling of human behavior
  • Behaviorally informed policy

Selected Publications

Katsikopolous, K.,  Canellas,  M. (2022): Decoding human behavior  with big data?: Critical, constructive input from decision sciences, DOI: https://doi.org/10.1002/aaai.12034

Katsikopolous, K.,Egozcue, M., García, L.F. (2022): A simple model for mixing intuition and analysis, DOI: http://dx.doi.org/10.1016/j.ejor.2022.03.005

Katsikopoulos, K., Gammoh, L., Dawson, I. (2022): Determinants of flood risk awareness and preparedness among citizens: the case of Jordan, DOI: https://doi.org/10.3961/jpmph.21.333

Katsikopoulos, K., Şimşek, Ö., Buckmann, M., Gigerenzer, G. (2022): Transparent modeling of influenza incidence: Big data or a single data point from psychological theory?, DOI: http://dx.doi.org/10.1016/j.ijforecast.2020.12.006

Katsikopoulos, K., Şimşek, Ö., Buckmann, M., Gigerenzer, G. (2022): Reply to commentaries on “Transparent modelling of influenza incidence”: Recency heuristics and psychological AI, DOI: http://dx.doi.org/10.1016/j.ijforecast.2021.10.011