Let the data do the talking: Empirical modelling of survey-based expectations by means of genetic programming (original) (raw)
Related papers
Tracking Economic Growth by Evolving Expectations Via Genetic Programming: A Two-Step Approach
XREAP Working Papers, 2018-04, 2018
The main objective of this study is to present a two-step approach to generate estimates of economic growth based on agents’ expectations from tendency surveys. First, we design a genetic programming experiment to derive mathematical functional forms that approximate the target variable by combining survey data on expectations about different economic variables. We use evolutionary algorithms to estimate a symbolic regression that links survey-based expectations to a quantitative variable used as a yardstick (economic growth). In a second step, this set of empirically-generated proxies of economic growth are linearly combined to track the evolution of GDP. To evaluate the forecasting performance of the generated estimates of GDP, we use them to assess the impact of the 2008 financial crisis on the accuracy of agents' expectations about the evolution of the economic activity in 28 countries of the OECD. While in most economies we find an improvement in the capacity of agents' to anticipate the evolution of GDP after the crisis, predictive accuracy worsens in relation to the period prior to the crisis. The most accurate GDP forecasts are obtained for Sweden, Austria and Finland.
Empirica - Journal of European Economics, 2019
In this study we use agents' expectations about the state of the economy to generate indicators of economic activity in twenty-six European countries grouped in five regions (Western, Eastern, and Southern Europe, and Baltic and Scandinavian countries). We apply a data-driven procedure based on evolutionary computation to transform survey variables in economic growth rates. In a first step, we design five independent experiments to derive a formula using survey variables that best replicates the evolution of economic growth in each region by means of genetic programming, limiting the integration schemes to the main mathematical operations. We then rank survey variables according to their performance in tracking economic activity, finding that agents' " perception about the overall economy compared to last year " is the survey variable with the highest predictive power. In a second step, we assess the out-of-sample forecast accuracy of the evolved indicators. Although we obtain different results across regions, Austria, Slovakia, Portugal, Lithuania and Sweden are the economies of each region that show the best forecast results. We also find evidence that the forecasting performance of the survey-based indicators improves during periods of higher growth.
Empirical modelling of survey-based expectations for the design of economic indicators
CIRET/KOF/WIFO Workshop on Economic Tendency Surveys and Financing Conditions, 2017
In this study we use agents' expectations about the state of the economy to generate indicators of economic activity in twenty-six European countries grouped in five regions (Western, Eastern, and Southern Europe, and Baltic and Scandinavian countries). We apply a data-driven procedure based on evolutionary computation to transform survey variables in economic growth rates. In a first step, we design five independent experiments to derive the optimal combination of expectations that best replicates the evolution of economic growth in each region by means of genetic programming, limiting the integration schemes to the main mathematical operations. We then rank survey variables according to their performance in tracking economic activity, finding that agents' " perception about the overall economy compared to last year " is the survey variable with the highest predictive power. In a second step, we assess the out-of-sample forecast accuracy of the evolved indicators. Although we obtain different results across regions, Austria, Slovakia, Portugal, Lithuania and Sweden are the economies of each region that show the best forecast results. We also find evidence that the forecasting performance of the survey-based indicators improves during periods of higher growth.
Using survey data to forecast real activity with evolutionary algorithms. A cross-country analysis
Journal of Applied Economics, 2017
Business and consumer surveys are the main source of agents' expectations. In this study we use survey expectations about a wide range of economic variables to forecast real activity. We propose an empirical approach to derive mathematical functional forms that link survey expectations to economic growth. Combining symbolic regression with genetic programming we generate two survey-based indicators: a perceptions index, using agents' assessments about the present, and an expectations index with their expectations about the future. Our examination of the forecast accuracy of both indicators to track the evolution of economic activity in fourteen European countries indicates that the perceptions index always outperforms the expectations index, although the improvements of the perceptions index against the naïve forecasts used as a benchmark are only significant in Austria. When assessing the effect of the 2008 financial crisis on the forecasting performance we find an improvement in accuracy during the crisis, which may be in part caused by a decrease of disagreement among respondents during periods prior to turning points. In order to find the optimal combination of both indexes that best replicates the evolution of economic activity in each country we use a portfolio management procedure known as index tracking. By means of a generalized reduced gradient algorithm we derive the relative weights of both indexes. In most economies, the survey-based predictions generated with the composite indicator outperform the benchmark model for one-quarter ahead forecasts, although these improvements are only significant in Austria, Belgium and Portugal.
A Genetic Programming Approach for Economic Forecasting with Survey Expectations
Applied Sciences, 2022
We apply a soft computing method to generate country-specific economic sentiment indicators that provide estimates of year-on-year GDP growth rates for 19 European economies. First, genetic programming is used to evolve business and consumer economic expectations to derive sentiment indicators for each country. To assess the performance of the proposed indicators, we first design a nowcasting experiment in which we recursively generate estimates of GDP at the end of each quarter, using the latest business and consumer survey data available. Second, we design a forecasting exercise in which we iteratively re-compute the sentiment indicators in each out-of-sample period. When evaluating the accuracy of the predictions obtained for different forecast horizons, we find that the evolved sentiment indicators outperform the time-series models used as a benchmark. These results show the potential of the proposed approach for prediction purposes.
Short-term forecasting of GDP via evolutionary algorithms using survey-based expectations
Proceedings of the 36th International Symposium on Forecasting, 2016
We present an empirical modelling approach of agents’ expectations based on symbolic regression (SR) 1. Via genetic programming (GP) we derive two data-driven indicators from survey-based expectations 2. We assess the performance of both indicators in fourteen European countries 3. By means of constrained optimization we find the optimal weights of both indicators to construct a composite index 4. We evaluate the ability of the generated estimates of economic growth to track the evolution of GDP
Evolutionary computation for macroeconomic forecasting
Computational Economics, 2019
The main objective of this study is twofold. First, we propose an empirical modelling approach based on genetic programming to forecast economic growth by means of survey data on expectations. We use evolutionary algorithms to estimate a symbolic regression that links survey-based expectations to a quantitative variable used as a yardstick, deriving mathematical functional forms that approximate the target variable. The set of empirically-generated proxies of economic growth are used as building blocks to forecast the evolution of GDP. Second, we use these estimates of GDP to assess the impact of the 2008 financial crisis on the accuracy of agents’ expectations about the evolution of the economic activity in four Scandinavian economies. While we find an improvement in the capacity of agents’ to anticipate economic growth after the crisis, predictive accuracy worsens in relation to the period prior to the crisis. The most accurate GDP forecasts are obtained for Sweden.
A data-driven approach to construct survey-based indicators by means of evolutionary algorithms
Social Indicators Research, 2018
In this paper we propose a data-driven approach for the construction of survey-based indicators using large data sets. We make use of agents’ expectations about a wide range of economic variables contained in the World Economic Survey, which is a tendency survey conducted by the Ifo Institute for Economic Research. By means of genetic programming we estimate a symbolic regression that links survey-based expectations to a quantitative variable used as a yardstick, deriving mathematical functional forms that approximate the target variable. We use the evolution of GDP as a target. This set of empirically-generated indicators of economic growth, are used as building blocks to construct an economic indicator. We compare the proposed indicator to the Economic Climate Index, and we evaluate its predictive performance to track the evolution of the GDP in ten European economies. We find that in most countries the proposed indicator outperforms forecasts generated by a benchmark model.
Economic forecasting with evolved confidence indicators
Economic Modelling, 2020
We present a machine-learning method for sentiment indicators construction that allows an automated variable selection procedure. By means of genetic programming, we generate country-specific business and consumer confidence indicators for thirteen European economies. The algorithm finds non-linear combinations of qualitative survey expectations that yield estimates of the expected rate of economic growth. Firms' production expectations and consumers' expectations to spend on home improvements are the most frequently selected variables-both lagged and contemporaneous. To assess the performance of the proposed approach, we have designed an out-of-sample iterative predictive experiment. We found that forecasts generated with the evolved indicators outperform those obtained with time series models. These results show the potential of the methodology as a predictive tool. Furthermore, the proposed indicators are easy to implement and help to monitor the evolution of the economy, both from demand and supply sides. JEL Classification: C51; C55; C63; C83; C93