Evolutionary Strategies vs. Neural Networks: an Inflation Forecasting Experiment (original) (raw)

Co-evolving neural networks with evolutionary strategies: a new application to Divisia money

Applications of Artificial Intelligence in Finance and Economics, 2004

This work applies state-of-the-art artificial intelligence forecasting methods to provide new evidence of the comparative performance of statistically weighted Divisia indices vis a vis their simple sum counterparts in a simple inflation forecasting experiment. We develop a new approach that uses coevolution (using neural networks and evolutionary strategies) as a predictive tool. This approach is simple to implement yet produces results that outperform stand-alone neural network predictions. Results suggest that superior tracking of inflation is possible for models that employ a Divisia M2 measure of money that has been adjusted to incorporate a learning mechanism to allow individuals to gradually alter their perceptions of the increased productivity of money. Divisia measures of money outperform their simple sum counterparts as macroeconomic indicators.

EVOLUTIONARY STRATEGIES; A NEW MACROECONOMIC POLICY TOOL?

2000

Previous work has used neural networks to predict the rate of inflation in Taiwan using four measures of 'money' (simple sum and three Divisia measures). In this work a new approach is dev eloped that uses an evolutionary strategy as a predictive tool. This approach is simple to implement yet produces results that compare favourably with the neural network predictions.

Evolving Hybrid Neural Networks with Swarm Intelligence for Forecasting ASEAN Inflation

2018

Macroeconomic policy depends greatly on forecasting. Artificial neural networks (ANNs) such as multilayer perceptrons (MLPs) and recurrent neural networks (RNNs) can learn the nonlinearities of time series, making them strong candidates for improving economic forecasting. We forecast inflation rates from the ASEAN region using the standard automatic SARIMA as benchmark, the MLP, a state of the art RNN called Long Short Term Memory (LSTM), and a novel hybrid SARIMA-ANN model. Neural networks, however, are difficult to design and train. Thus, we let the network hyperparameters evolve using a recent Swarm Intelligence optimization algorithm: Grey Wolf Optimization (2014). We compare the one step and 12-steps ahead forecast accuracy of the evolving ANNs with SARIMA. Results show a clear superiority of the evolving SARIMA-ANN over every other model, with the evolving MLP at second, SARIMA at third, and LSTM performing the worst.

A Neural Network Approach to Inflation Forecasting: Recent Evidence for the USA and UK

IFAC Proceedings Volumes, 1998

In this paper a Divisia monetary index measure of money is constructed for the Italian economy and its inflation forecasting potential is compared with that of its traditional simple sum counterpart. The powerful and flexible Artificial Intelligence technique of neural networks is used to allow a completely flexible mapping of the variables and a greater variety of functional form than is currently achievable using conventional econometric techniques. Results show that superior tracking of inflation is possible for networks that employ a Divisia M2 measure of money. During a period of high financial innovation in Italy Divisia outperforms simple sum at both the AL and M 2 levels of monetary aggregation. This support for Divisia is entirely consistent with frndings based on standard econometric techniques. Divisia monetary aggregates appear to offer advantages over their simple sum counterparts as macroeconomic indicators. Further, the combination of Divisia measures of money with the artificial neural network offers a promising starting point for improved models of inflation.

Static, dynamic, and hybrid neural networks in forecasting inflation

Computational Economics, 1999

The back-propagation neural network (BPN) model has been the most popular form of artificial neural network model used for forecasting, particularly in economics and finance. It is a static (feed-forward) model which has a learning process in both hidden and output layers. In this paper we compare the performance of the BPN model with that of two other neural network models, viz., the radial basis function network (RBFN) model and the recurrent neural network (RNN) model, in the context of forecasting inflation. The RBFN model is a hybrid model with a learning process that is much faster than the BPN model and that is able to generate almost the same results as the BPN model. The RNN model is a dynamic model which allows feedback from other layers to the input layer, enabling it to capture the dynamic behavior of the series. The results of the ANN models are also compared with those of the econometric time series models.

FORECASTING INFLATION VARIABLES USING ARTIFICIAL NEURAL NETWORK TECHNIQUES

The analysis of monthly Inflation constitutes one of the major economic problems in emerging market economies that requires monetary authorities to elaborate tools and policies to prevent high volatility in prices and long periods of inflation. This work modeled and forecast monthly inflation rate of Nigerian by using neural networks on the evaluation of set of variables. The data set used for estimating the models are obtained from central bank statistical data base for the period of 2000 to 2017. The neural network models Back propagation neural network model or Back propagation Network model (BPN model) was used in this study in forecasting inflation rate. The results of the neural network models under static with the traditional econometric model and the results shows that the performance is better when compare it with the traditional econometric model in forecasting the inflation rate

Inflation Forecasting in Pakistan using Artificial Neural Networks

2007

An artificial neural network (hence after, ANN) is an informationprocessing 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 conventional univariate time series forecasting models such as AR(1) and ARIMA based models and observed that RMSE of ANN based forecasts is much less than the RMSE of forecasts based on AR(1) and ARIMA models. At least by this criterion forecast based on ANN are more precise.

Prediction of Indonesian Inflation Rate Using Regression Model Based on Genetic Algorithms

2020

Inflation occurs where there is an increase in the price of goods or services in general and continuously in a country. Uncontrolled inflation will have an impact on the decline of the Indonesian economy. Therefore, the prediction of future inflation levels is necessary for the government to develop economic policies in the future. Prediction of inflation levels can be done by studying historical past Consumer Price Index (CPI) data. Regression methods are often used to solve prediction problems. The problem of finding the optimal prediction model can be seen as an optimization problem. Genetic algorithms are often used to deal with optimization problems. Thus, this work proposed to use a genetic algorithm-based regression model for predicting inflation levels. The model was trained and evaluated using real CPI data which obtained from the Indonesian Central Bank. Based on the experiment, it is proved that the proposed model is effective in predicting the inflation level as it gains...

Enhanced Evolutionary Sequential Minimal Optimization Model for Inflation Prediction

International Journal of Engineering & Technology

The control of inflation rate is at the core of monetary policy making. Therefore, there is very great interest in reliable inflation forecasts by central bankers to help them achieve this aim. The aim of this investigation has been to forecast inflation in case of the United States as accurately as possible. This paper proposes a new forecasting model called Sequential Minimal Organization (SMOreg-3passes) for regression predictions. SMOreg-3passes consists of four steps, they are technical indicators generation, feature selection, normalization regression and regression forecaster. The proposed model evaluated using two regression measurements (Mean Absolute Error (MAE) and Root Mean Square Error (RMSE)). Our evidence from the SMOreg-3passes model suggests that the chronology of time series has great influence on future forecasting and the error in forecasting the past has an exponential impact on the current data. The results showed that the proposed model outperformed the tradit...

An Inflation Rate Prediction Based on Backpropagation Neural Network Algorithm

International Journal of Artificial Intelligence Research

This article aims to predict the inflation rate in Samarinda, East Kalimantan by implementing an intelligent algorithm, Backpropagation Neural Network (BPNN). The inflation rate data was obtained from the Provincial Statistics Bureau of Samarinda https://samarindakota.bps.go.id/ for the period January 2012 to January 2017. The method used to measure accuracy algorithm prediction was the mean square error (MSE). Based on the experiment results, the BPNN method with architectural parameters of 5-5-5-1; the learning function was trainlm; the activation functions were logsig and purelin; the learning rate was 0.1 and able to produce a good level of prediction error with an MSE value of 0.00000424. The results showed that the BPNN algorithm can be used as an alternative method in predicting inflation rates in order to support sustainable economic growth, so that it can improve the welfare of the people in Samarinda, East Kalimantan.