Superforecasting: The Art and Science of Prediction

By Philip Tetlock, Dan Gardner. 2015

676 citations recorded by the source corpus.

Subfields: Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/7fd0b7c04157ca1459ca16607de9ec139fd9ad51

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Management Science and Operations Research

Citations in the corpus

ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data (2020, methodology): “We consider forecasting as the process of anticipating the outcome of future events based on past and present data (Tetlock and Gardner, 2016).”
Unsolved Problems in ML Safety (2021, background): “Many governance and command and control decisions are based on forecasts [186] from humans, and some forecasts are starting to incorporate ML [39].”
Modelling complex systems of heterogeneous agents to better design sustainability transitions policy (2015, background): “We submit in contrast that forecasting is both necessary and inevitable, and can be improved within the bounds of finite predictability with increased attention to known nonlinearities and interaction effects (Tetlock and Gardner, 2015).”
Harms from Increasingly Agentic Algorithmic Systems (2023, background): “The emerging science of forecasting [Tetlock and Gardner 2016] may also provide insights into anticipating the impacts of emerging systems.”
Testing the ability of the surprisingly popular method to predict NFL games (2018, methodology): “The inferred parameters from the Lee and Lee (2017) analysis for each method are also shown in Figure 6.”
A practical guide to structured expert elicitation using the IDEA protocol (2018, background): “…very poor guides to determining a priori someone’s ability to provide good judgements in elicitation settings (Burgman et al., 2011; Shanteau et al., 2002; Tetlock & Gardner, 2015) and may result in the unnecessary exclusion of knowledgeable individuals (French, 2011; Shanteau et al., 2002).”
Forecasting: theory and practice (2020, background): “Recently, a major study on geo-political forecasts based solely on information held in the forecasters’ memory has been summarised by Tetlock and Gardner (2015).”
The Bias of Crowds: How Implicit Bias Bridges Personal and Systemic Prejudice (2017, methodology): “The “wisdom of crowds” effect has been used to improve prediction of political, military, and economic events by drawing on partial knowledge that is distributed across a population (Tetlock & Gardner, 2015).”
Of quantiles and expectiles: consistent scoring functions, Choquet representations and forecast rankings (2015, background): “Nevertheless, as mentioned by Patton, eliminating dominated forecasts may be a very useful strategy in empirical settings with many forecasters and overlapping information sets, such as in big on-line surveys (Tetlock and Gardner, 2015).”
What Motivates Effort?: Evidence and Expert Forecasts (2018, neutral): “2There is a larger literature on forecasting about topics other than research results, e.g., the Good Judgment Project on national security (Tetlock, 2010 and Tetlock and Gardner, 2015).”
Forecasting in social settings: The state of the art (2020, background): “Tetlock et al. (2015), in their Superforecasting book, enlist the qualities of “superforecasters” (individuals that consistently have a higher skill/luck ratio compared to regular forecasters).”
The Matthews Correlation Coefficient (MCC) is More Informative Than Cohen’s Kappa and Brier Score in Binary Classification Assessment (2021, methodology): “We usually refer to AUC as measuring only discrimination whereas strictly proper scoring rules like the Brier score are inﬂuenced by both the discriminating ability of the forecasts and their calibration, where calibration here means the relative frequency of observed outcomes [72].”