We find evidence suggesting that surveys of professional forecasters are biased by strategic incentives. First, we find that individual forecasts overreact to idiosyncratic information but underreact to common information. Second, we show that this bias is not present in forecasts data that is...

We study the use of a misspecified overdifferenced model to forecast the level of a stationary scalar time series. Let x(t) be the series, and let bias be the sample average of a series of forecast errors. Then, the bias of forecasts of x(t) generated by a misspecified overdifferenced ARMA model...

Firm characteristics, based on accounting and financial market data, are commonly used to represent firms in economics and finance. However, investors collectively use a much richer information set beyond firm characteristics, including sources of information that are not readily available to...

This paper studies the predictability of ultra high-frequency stock returns and durations to relevant price, volume and transactions events, using machine learning methods. We find that, contrary to low frequency and long horizon returns, where predictability is rare and inconsistent,...

This paper shows that shootings are predictable enough to be preventable. Using arrest and victimization records for almost 644,000 people from the Chicago Police Department, we train a machine learning model to predict the risk of being shot in the next 18 months. We address central concerns...

This paper proposes a new way of displaying and analyzing macroeconomic time series to form recession forecasts. The proposed data displays contain the last three years of each expansion. These allow observers to see for themselves what is different about the last year before recession. Based on...

We propose a novel time-series econometric framework to forecast U.S. Presidential election outcomes in real time by combining polling data, economic fundamentals, and political prediction market prices. Our model estimates the joint dynamics of voter preferences across states. Applying our...

We argue that comprehensive out-of-sample (OOS) evaluation using statistical decision theory (SDT) should replace the current practice of K-fold and Common Task Framework validation in machine learning (ML) research. SDT provides a formal framework for performing comprehensive OOS evaluation...

We nowcast world trade using machine learning, distinguishing between tree-based methods (random forest, gradient boosting) and their regression-based counterparts (macroeconomic random forest, gradient linear boosting). While much less used in the literature, the latter are found to outperform...

We propose a new tool to filter non-linear dynamic models that does not require the researcher to specify the model fully and can be implemented without solving the model. If two conditions are satisfied, we can use a flexible statistical model and a known measurement equation to back out the...