About this Research Topic
Macroeconomic variables such as output growth, inflation rate and interest rate, reveal information about the current state of the economy and play a key role in formulating appropriate monetary and fiscal policies. As indicators of future growth potential of the economy, macroeconomic forecasting is pivotal for central bankers, policymakers, and researchers. In fact, economic policymaking relies upon accurate forecasts of economic conditions. Furthermore, they are crucial for financial investors, households, and businesses in their investment decision-making process.
Despite the benefits of forecasting macroeconomic variables accurately, improving traditional models has proved challenging during the last two decades. Furthermore, the literature has largely neglected machine learning and the growth of big data in economics. With the availability of big data, the natural question that arises is whether the combination of both big data and machine learning methods can produce more accurate forecasts in economics. This new data-rich environment offers researchers a unique opportunity to identify, extend and adapt machine learning methods for forecasting macroeconomic variables. This Research Topic aims to explore machine-learning methods as an opportunity to improve upon forecast accuracy and to highlight new advancements in macroeconomic forecasting techniques.
We invite researchers to submit their original papers reporting studies of forecasting macroeconomic variables using both traditional econometric techniques and machine learning methods.
Topics of interest include but are not limited to:
- Forecasting macroeconomic variables by using traditional econometric methods
- Forecasting macroeconomic variables by using machine learning methods
- Forecasting financial variables by using machine learning methods
- Comparison of the forecasting performances of traditional econometric methods and ML tools
- Evaluation of the specification of the ML models
- Recent advances in macroeconomic forecasting using big data
Despite the benefits of forecasting macroeconomic variables accurately, improving traditional models has proved challenging during the last two decades. Furthermore, the literature has largely neglected machine learning and the growth of big data in economics. With the availability of big data, the natural question that arises is whether the combination of both big data and machine learning methods can produce more accurate forecasts in economics. This new data-rich environment offers researchers a unique opportunity to identify, extend and adapt machine learning methods for forecasting macroeconomic variables. This Research Topic aims to explore machine-learning methods as an opportunity to improve upon forecast accuracy and to highlight new advancements in macroeconomic forecasting techniques.
We invite researchers to submit their original papers reporting studies of forecasting macroeconomic variables using both traditional econometric techniques and machine learning methods.
Topics of interest include but are not limited to:
- Forecasting macroeconomic variables by using traditional econometric methods
- Forecasting macroeconomic variables by using machine learning methods
- Forecasting financial variables by using machine learning methods
- Comparison of the forecasting performances of traditional econometric methods and ML tools
- Evaluation of the specification of the ML models
- Recent advances in macroeconomic forecasting using big data
Keywords: Machine Learning Methods, Forecasting, Housing Market Volatility Forecasting, Comparing Forecasting Performance, Computing Missing Data in Economics, Forecasting Macroeconomic and Financial variables
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
