Argumentative Forecasting

We introduce the Forecasting Argumentation Framework (FAF), a novel argumentation framework for forecasting informed by recent judgmental forecasting research. FAFs comprise update frameworks which empower (human or artificial) agents to argue over time with and about probability of scenarios, whilst flagging perceived irrationality in their behaviour with a view to improving their forecasting accuracy. FAFs include three argument types with future forecasts and aggregate the strength of these arguments to inform estimates of the likelihood of scenarios. We describe an implementation of FAFs for supporting forecasting agents.

Authors

• Benjamin Irwin Imperial College London
• Antonio Rago King's College London
• Francesca Toni Imperial College London

Keywords

• Argumentation
• Forecasting
• Multi-Agent Debate