Showing 1 - 10 of 8,368
This paper assesses trends in the global energy sector through 2040 by harmonizing multiple projections issued by private, government, and inter-governmental organizations based on methods from "Global Energy Outlooks Comparison: Methods and Challenges" (Newell and Qian 2015). These projections...
Persistent link: https://www.econbiz.de/10012456599
We apply deep learning to daytime satellite imagery to predict changes in income and population at high spatial resolution in US data. For grid cells with lateral dimensions of 1.2km and 2.4km (where the average US county has dimension of 55.6km), our model predictions achieve R2 values of 0.85...
Persistent link: https://www.econbiz.de/10012794597
We survey the nascent literature on machine learning in the study of financial markets. We highlight the best examples of what this line of research has to offer and recommend promising directions for future research. This survey is designed for both financial economists interested in grasping...
Persistent link: https://www.econbiz.de/10014322889
We explore the principal trends that are shaping the future landscape of energy supply, demand, and trade. We take a long-term view, assessing trends on the time scale of a generation by looking 25 years into the past, taking stock of the current situation, and projecting 25 years into the...
Persistent link: https://www.econbiz.de/10012459695
Forecasting using `diffusion indices' has received a good deal of attention in recent years. The idea is to use the … common factors estimated from a large panel of data to help forecast the series of interest. This paper assesses the extent … method stands out to have smaller forecast errors. This method forecasts the series of interest directly, rather than the …
Persistent link: https://www.econbiz.de/10012467399
Pools, and use it to investigate the relative forecasting performance of DSGE models with and without financial frictions … environment, leading to real-time forecast improvements relative to other methods of density forecast combination, such as …
Persistent link: https://www.econbiz.de/10012458090
areas of India, and that farmers respond more strongly to the forecast where there is more forecast skill and not at all … when there is no skill. We show, using an IV strategy in which the Indian government forecast of monsoon rainfall serves as … compared with farmers without access to forecasts. Even modest improvements in forecast skill would substantially increase …
Persistent link: https://www.econbiz.de/10012459327
forecast. In a stylized data generating process, we show that such forecasts can be effective even if there is essentially no … rates against 17 OECD countries. We forecast using factors, and using factors combined with any of fundamentals suggested by … improve on the forecast of a "no change" benchmark in the late (1999-2007) but not early (1987-1998) parts of our sample …
Persistent link: https://www.econbiz.de/10012460277
We review the literature on return and cash flow growth predictability form the perspective of the present-value identity. We focus predominantly on recent work. Our emphasis is on U.S. aggregate stock return predictability, but we also discuss evidence from other asset classes and countries
Persistent link: https://www.econbiz.de/10012462008
not observed at the time that the forecast is made--but can nonetheless improve forecasting accuracy by reducing parameter … of forecasting excess bond and equity returns. We find substantial improvements in out-of-sample forecast accuracy for … price movements around macroeconomic news announcements. These "surprises" cannot be used directly in forecasting--they are …
Persistent link: https://www.econbiz.de/10012464478