No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
A Machine Learning Approach to CCPI-Based Inflation Prediction
The consumer price index (CPI) is one of the most important macroeconomic indicators for determining inflation, and accurate predictions of CPI changes are important for a country's economic development. This study uses multivariate linear regression (MLR), support vector regression (SVR), autoregressive distributed lag (ARDL), and multivariate adaptive regression splines (MARS) to predict the CPI of the United States. Data from January 2017 to February 2022 were randomly selected and divided into two stages: 80 % for training and 20% for testing. The US CPI was modeled for the observed period and relied on a mix of elements, including crude oil price, world gold price, and federal fund effective rate. Evaluation metrics—mean absolute percentage value, mean absolute error, root mean square error, R-squared, and correlation of determination—were employed to estimate forecasted values. The MLR, SVR, ARDL, and MARS models attained high accuracy parameters, while the MARS algorithm generated higher accuracy in US CPI forecasts than the others in the testing phase. These outputs could support the US government in overseeing economic policies, sectors, and social security, thereby boosting national economic development.
In times of pronounced nonlinearity of macroeconomic variables and in situations when variables are not normally distributed, i.e. when the assumption of i.i.d. is not fulfilled, neural networks (NNs) should be used for forecasting. In this paper, Jordan neural network (JNN), a special type of NNs is examined, because of its advantages in time series forecasting suitable for inflation forecasting. The variables used as inputs include labour market variable, financial variable, external factor and lagged inflation, i.e. the most commonly used variables in previous researches. The research is conducted at the aggregate level of euro area countries in the period from January 1999 to January 2017. Based on 250 estimated JNNs, which differ in selected variables, sample breaking point and varying parameters (number of hidden neurons, weight value of the context unit), the model adequacy indicators for each JNN are calculated for two periods: in-the-sample and out-of-sample. Finally, the optimal JNN for inflation forecasting is obtained as the best compromise solution between low mean squared error in-the-sample and out-of-sample and low number of parameters to estimate. This paper contributes to existing literature in using JNN for inflation forecasting since it is rarely used for macroeconomic time series prediction in general. Moreover, this paper defines which set of variables contributes to the best inflation forecast. Additionally, JNN is examined thoroughly by fixing certain parameters of the model and alternating other parameters to contribute to the JNN literature, i.e. finding the optimal JNN.
This paper focuses on developing models to study influential factors on the inflation rate for a panel of available countries in the World Bank data base during 2008-2012. For this purpose, Random effect log-linear and Ordinal logistic models are used for the analysis of continuous and categorical inflation rate variables. As the original inflation rate response to variables shows an apparent right skewness, the log transformation in the linear mixed effect model seems necessery. In the ordinal logistic mixed effect model, as a new approach, the inflation rate variable is categorized based on two threshols to increase model predictibality and precision. These two models consider the potential serial correlation between annual infltion rates and categories through introducing some latent random effect parameters. The results of both models show that money growth, GDP, oil price and income levels of the available countries are significant predictors with increasing effect on the next year inflation rate category. Using the categorical inflation response variable yields some superior results where government expenditure, exchange rate and capital formation are also detected as significant determinants of ordinal inflation variable. Also, the random effect variance is highly significant in both models which shows the necessery need for consideration of the potential association of inflation variables across time.
This paper aims to review the theoretical and empirical studies on the impact of inflation on economic growth. Our critical review shows that there is no consensus on the relationship between inflation and economic growth both in theoretical and empirical studies. The results mostly depend on the assumptions adopted in the study. Accordingly, the theoretical literature indicates that the inflation-growth nexus can be positive, negative or neutral. Also, the empirical findings are diversified based on the economic conditions, methodology employed, data used, nature of the study whether cross section, panel data or country specific, and time period of the study as well as the number of explanatory variables included in the model. Therefore, the empirical results have two models: linear and nonlinear relationships.
Artificial Neural Network (ANN) is a modelling technique which is based on the way the human brain process information. ANNs have proved to be good forecasting models in several fields including economics and finance. The ANN methodology is used by some central banks to predict various macroeconomic indicators such as the inflation, money supply, GDP growth etc. The use of the ANN for prediction is common in the forecasting literature but rare in Ghana. This paper forecasts inflation with the ANN method using the Ghanaian data. The monthly y-o-y data between 1991:01 and 2010:12 are used to estimate and forecast for the period 2011:01 to 2011:12. The result of the ANNs are also compared with traditional time series models such as the AR (12) and VAR (14) which use the same set of variables. The basis of comparison is the out-of-sample forecast error (RMSFE). The results show that the RMSFE of the ANNs are lower than their econometric counterparts. That is, by this comparative criterion forecast based on ANN models are more accurate.
One of the key issues in constructing monetary policy is accurate prediction of the inflation level. The complex behavior and non-linear nature of the financial markets makes it hard to forecast the inflation rate precisely. This paper introduces a hybrid model that attempts to forecast the inflation rate with a combination of a subtractive clustering technique and a fuzzy inference neural network to overcome the shortcomings of the individual methodologies. Selected macroeconomic factors were used to predict the historical CPI data from the US Markets. The results of the proposed hybrid model are measured in RMSE.
An artificial neural network (ANN) is an information-processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information. In previous two decades, ANN applications in economics and finance; for such tasks as pattern reorganization, and time series forecasting, have dramatically increased. Many central banks use forecasting models based on ANN methodology for predicting various macroeconomic indicators, like inflation, GDP Growth and currency in circulation etc. In this paper, we have attempted to forecast monthly YoY inflation for Pakistan by using ANN for FY08 on the basis of monthly data of July 1993 to June 2007. We also compare the forecast performance of the ANN model with that of univariate AR(1) model and observed that RMSE of ANN based forecasts is much less than the RMSE of forecasts based on AR(1) model. At least by this criterion forecast based on ANN are more precise.
We assess the power of diverse Artificial Neural-Network (ANN) models as forecasting tools for monthly inflation rates for 28 Organization for Economic Co-operation and Development (OECD) countries. In the context of short out-of-sample forecasting horizon we find that, on average, the ANN models were a superior predictor for inflation for 45% while the Autoregressive model of order one (AR1) model performed better for 23% of the countries. Furthermore, we develop arithmetic combinations of several ANN models and find that these may also serve as credible tools for forecasting inflation.
We contribute to recent research on the optimality of macroeconomic forecasts. We start from the assumption that forecasters may have a flexible rather than a symmetric (quadratic) loss function assumed in standard tests. This assumption leads to the prediction that variables available to a forecaster when a forecast was formed should have no predictive value for a binary 0/1-indicator that captures the sign of the forecast error. A test of forecast optimality, thus, can be interpreted as a classification problem. We use random forests to model this classification problem. Random forests are a powerful nonparametric modeling instrument originally developed in the machine-learning literature. Unlike conventional linear-probability or logit/probit-models, random forests account in a natural way for potential nonlinear links between the signed forecast error and the variables in a forecaster's information set. Random forests also can handle a situation in which the number of forecasts is small relative to the number of predictor variables that a researcher uses to proxy a forecaster's information set. Random forests, therefore, are a powerful modeling device that is of interest for every researcher who studies the properties of macroeconomic forecasts. Upon estimating random forests on forecasts of four German research institutes, we document that optimality of longer-term inflation forecasts cannot be rejected and that inflation forecasts are weakly efficient. For shorter-term inflation forecasts, our results are heterogeneous across research institutes. When we pool the data across the research institutes, we reject optimality of both shorter-term and longer-term forecasts.
In this work we use a Neural Network model to forecast Mexican inflation. Related works forecast inflation in countries where this economic variable has a stable behavior while Mexican inflation has been characterized to be very volatile during certain periods. There were implemented different Neural Network models by varying the number of hidden layers (1 and 2) and the number of neurons in the hidden layer (from 1 to 100). The forecasting model results were divided into 3 categories: a volatile inflation phase, where the mean difference was 0.64% between real inflation and forecasted inflation; a transition phase, where the mean difference was 5.44%; and a stability phase, where the mean difference was 0.28%. By doing a comparison between model forecasting results and Bank of Mexico's predictions, Neural Networks model results are clearly more accurate to the real inflation behavior, a critical point during inflationary crisis periods.
Jordan neural network for inflation forecasting
- Å Estanoviä Tea