Search

This article reviews selected papers that use machine learning for economics research and policy analysis. Our review highlights when machine learning is used in economics, the commonly preferred models and how those models are used.

We study the formation of price bubbles on experimental asset markets where cash earns interest. There are two main conclusions.

Data show that income inequality in Canada increased substantially during the 1980s and first half of the 1990s but has been relatively stable over the past 25 years. This increase was felt mainly by low-income earners and younger people, while older people benefited from higher retirement income.

This paper investigates high-frequency (HF) market and limit orders in the U.S. Treasury market around major macroeconomic news announcements. BrokerTec introduced i- Cross at the end of 2007 and we use this exogenous event as an instrument to analyze the impact of HF activities on liquidity and price efficiency.

We study the distribution of political speech across U.S. firms. We develop a measure of political engagement based on firms’ communications (earning calls, regulatory filings, and social media) by training a large language model to identify statements that contain political opinions. Using these data, we document five facts about firms’ political engagement.

Many studies have documented that daily realized volatility estimates based on intraday returns provide volatility forecasts that are superior to forecasts constructed from daily returns only. We investigate whether these forecasting improvements translate into economic value added.

Under very general conditions, the total quadratic variation of a jump-diffusion process can be decomposed into diffusive volatility and squared jump variation. We use this result to develop a new option valuation model in which the underlying asset price exhibits volatility and jump intensity dynamics.

This paper explores the volatility forecasting implications of a model in which the friction in high-frequency prices is related to the true underlying volatility. The contribution of this paper is to propose a framework under which the realized variance may improve volatility forecasting if the noise variance is related to the true return volatility.

This paper proposes a unique approach to simulate intraday transactions in the Canadian retail payments batch system when such transactions are unobtainable. The simulation procedure has potential for helping with data-deficient problems where only high-level aggregate information is available.

I use a structural vector autoregression (SVAR) with sign restrictions to provide conditional evidence on the behavior of the US external finance premium (EFP). The results indicate that the excess bond premium, a proxy for the EFP, reacts countercyclically to supply and monetary policy shocks and procyclically to demand shocks.