Programming Prescience: Issues in Human Construction of Forecasting Bots
This paper explores the challenges of building and evaluating AI forecasting systems through a qualitative interview study.
This paper provides a detailed account of the challenges faced by builders of AI forecasting systems, which is a novel contribution to the field.
Before reading this…
Applications
- →AI forecasting
- →Building and evaluating AI systems
To understand this paper, make sure you know these concepts first:
- Understanding of AI systems and forecastingfind papers →
- Knowledge of qualitative research methodsfind papers →
Abstract
More Like ThisAI models' growing capacity for complex reasoning has made them attractive tools for forecasting, or the systematic prediction of the future based on past and present data. However, should AI forecasting systems be adopted, human builders will shoulder the work of building and evaluating them. In this paper, we explore what this work looks like with a qualitative interview study with 15 builders of forecasting bots, sampled from among successful participants in a recent AI forecasting competition. Our analysis surfaces the challenges around (1) tuning a bot to acquire factual research, (2) implementing coherent reasoning, and (3) understanding how well one's bot actually does. During their work, builders frequently introduced complexity that did not pay off, and tested in ways that were opportunistic and piecemeal. Our detailed account of their challenges helps clarify what problems should be targeted in upcoming innovations in process, tools, and human-AI teaming for forecasting.