Computational modelling for decision-making: where, why, what, who and how

In order to deal with an increasingly complex world, we need ever more sophisticated computational models that can help us make decisions wisely and understand the potential consequences of choices. But creating a model requires far more than just raw data and technical skills: it requires a close collaboration between model commissioners, developers, users and reviewers. Good modelling requires its users and commissioners to understand more about the whole process, including the different kinds of purpose a model can have and the different technical bases. This paper offers a guide to the process of commissioning, developing and deploying models across a wide range of domains from public policy to science and engineering. It provides two checklists to help potential modellers, commissioners and users ensure they have considered the most significant factors that will determine success. We conclude there is a need to reinforce modelling as a discipline, so that misconstruction is less likely; to increase understanding of modelling in all domains, so that the misuse of models is reduced; and to bring commissioners closer to modelling, so that the results are more useful.

[1]  Julie A. McCann,et al.  Making Sense of the World: Framing Models for Trustworthy Sensor-Driven Systems , 2018, Comput..

[2]  S. Dobson,et al.  Making Sense of the World: Models for Reliable Sensor-Driven Systems , 2018, ArXiv.

[3]  Christl A. Donnelly,et al.  Computational modelling: technological futures , 2018 .

[4]  Mark Bowen,et al.  Methods of Mathematical Modelling: Continuous Systems and Differential Equations , 2015 .

[5]  O. Wolkenhauer.  Why model? , 2013, Front. Physiol..

[6]  Michael Fisher.  An Introduction to Practical Formal Methods Using Temporal Logic , 2011 .

[7]  William D. Nordhaus,et al.  Economic aspects of global warming in a post-Copenhagen environment , 2010, Proceedings of the National Academy of Sciences.

[8]  Robin Milner,et al.  The Space and Motion of Communicating Agents , 2009 .

[9]  G. Nigel Gilbert,et al.  Agent-Based Models , 2007 .

[10]  Robert M. Entman,et al.  Political Disagreement: The Survival of Diverse Opinions within Communication Networks , 2005 .

[11]  Jos C. M. Baeten,et al.  A brief history of process algebra , 2005, Theor. Comput. Sci..

[12]  R. Huckfeldt,et al.  Political Disagreement: The Survival of Diverse Opinions within Communication Networks , 2004 .

[13]  S. Howison,et al.  Applied Partial Differential Equations , 1999 .

[14]  Thomas A. Henzinger,et al.  The theory of hybrid automata , 1996, Proceedings 11th Annual IEEE Symposium on Logic in Computer Science.

[15]  Bengt Jonsson,et al.  A logic for reasoning about time and reliability , 1990, Formal Aspects of Computing.

[16]  H. M. Taylor,et al.  An introduction to stochastic modeling , 1985 .

[17]  L. Phillips.  A theory of requisite decision models , 1984 .

[18]  Robert M. Keller,et al.  Formal verification of parallel programs , 1976, CACM.

[19]  Kevin P. Murphy.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[20]  Y. Moschovakis.  Mathematical Logic , 2003 .

[21]  Amir Pnueli,et al.  Liveness with (0, 1, ∞)-counter abstraction , 2002 .

[22]  Donald C. Mikulecky,et al.  Methods of Mathematical Modelling , 1995 .

[23]  David D. McDonald,et al.  Programs , 1984, CL.

[24]  J. Forrester.  Principles of systems : text and workbook, chapters 1 through 10 , 1968 .

[25]  Willard Van Orman Quine,et al.  Mathematical logic , 1967 .