This study applies state-of-the-art machine learning (ML) techniques to forecast IMF-supported programs, analyzes the ML prediction results relative to traditional econometric approaches, explores non-linear relationships among predictors indicative of IMF-supported programs, and evaluates model robustness with regard to different feature sets and time periods. ML models consistently outperform traditional methods in out of-sample prediction of new IMF-supported arrangements with key predictors that align well with the literature and show consensus across different algorithms. The analysis underscores the importance of incorporating a variety of external, fiscal, real, and financial features as well as institutional factors like membership in regional financing arrangements. The findings also highlight the varying influence of data processing choices such as feature selection, sampling techniques, and missing data imputation on the performance of different ML models and therefore indicate the usefulness of a flexible, algorithm-tailored approach. Additionally, the results reveal that models that are most effective in near and medium-term predictions may tend to underperform over the long term, thus illustrating the need for regular updates or more stable – albeit potentially near-term suboptimal – models when frequent updates are impractical. 

This paper quantitatively evaluates the impact of interrelated lifetime health and health care use dynamics on macroeconomic outcomes, including how the measurement of these dynamics affects estimates under changing socio-demographic and policy settings. I embed a dynamic model governing the stochastic lifetime evolution of both health and empirically-identified necessary health care use within a life-cycle model containing overlapping generations of heterogeneous households and consider three settings: a base U.S. economy scenario, a population age shift to 2070 demographic projections, and a policy reform that increases Medicare generosity. Through shaping underlying population health and the financial risk of health care utilization, health and health care dynamics over the life cycle are an important driver of consumption inequality, public finance, and macroeconomic aggregates in the calibrated model. Effects on outcomes such as income inequality are further highlighted when comparing the baseline model to coarser means of measuring health and health care use. 

This paper presents a tractable method for predictive modeling with high-dimensional, spatio-temporally-distributed economic data via borrowing techniques from visual recognition machine learning. Specifically, I cast the time series of spatially-disaggregated U.S. economic data as a temporal sequence of geographic ‘images’ in a computer vision setting and develop a deep learning model architecture to evaluate whether leveraging the spatio-temporal distribution of data features can improve macroeconomic forecasts. The resulting spatial recurrent convolutional neural network model accurately forecasts changes in U.S. GDP and outperforms more traditional linear methods as well as deep learning models that do not utilize the data’s spatial distribution. Analysis of the estimated model provides intuition for its improved performance by highlighting an ability to focus on regional economic experiences and shift geographic focus over time. 

This paper examines the economic and welfare impacts of publicly-subsidizing the production of a good/service characterized by uncertain utilization via the context of medical physicians and health care services in the United States. The financial risk of uncertain health care expenditure throughout life creates the potential for subsidization of health care factors of production to increase welfare through decreasing the cost of health care and thus household exposure to risk. To evaluate this mechanism, I perform policy experiments in a life-cycle model with a health care sector, physicians, and heterogeneous households with uncertain health. In the model, publicly-funding the private financial costs of physician training in the U.S. through subsidies or cash transfers increases physicians per capita, decreases health care costs and aggregate expenditure, and increases lifetime welfare by up to 0.55 percent of annual consumption per year when transfers are equal to the full value of medical school tuition. 

Expenditure on non-clinical, administrative tasks in the U.S. health care system is estimated to constitute 4.6 percent of GDP- almost 60 percent of which is specifically billing and insurance-related (BIR). I therefore construct a life-cycle model with uncertain health care utilization and a health care sector employing both clinical and administrative inputs in order to estimate the economic and welfare implications of ad ministrative complexity in U.S. health care. I quantify these impacts via comparison to a counterfactual U.S. economy that has BIR administrative characteristics of Canada. With Canadian BIR complexity, the price of health care services is 15.8 percent lower and health care service expenditure as a percentage of GDP decreases by 2.1 percentage points. In the model, differences in BIR administrative complexity can thus account for over 40 percent of the difference between health care service expenditure as a percentage of GDP in the U.S. compared to Canada.