Abstract
Economic is important issue in a country since it is conducted by many sectors. Knowing stability of economic condition can be looked at by predicting the economic indicator. Unfortunately, the prediction that had been done to each of economic indicator did not concern about interconnection of them while predicting it. Because of that, learning about dependability of economic indicator still need further research about it. In other side, economic as knowledge that complex and chaos need differential dynamic to face the problem inside. Based on those reasons, this research not only observed about interconnection between indicators economic while predicting, but also needed differential dynamic which had been optimized by genetic algorithm. System got 20% until 80% for the accuracy system. The reason of why accuracy 80% was gotten because of using the same characteristics of economic indicators, ex. when system observed GDP and GNI together. Using similar data trend influenced the fitness function in GA able to optimized differential dynamic while doing prediction of economic indicators. Whereas, the decrease accuracy around 20% until 40% was came by using different characteristic of economic indicator. It can be found when learning dependable of GDP and Inflation while predict times series for GDP. Based on this research, it can be concluded that GA is able in optimizing learning the dependability of economic indicator’s Indonesia. Moreover, it can be said that using the same characteristic indicator economic give better result for GA to learning the dependability of economic indicator than not. It can be said indirectly that government should concern about value of indicators economic that have the same characteristics when monitoring economic condition.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Alquier, P., Wintenberger O.: Fast rates in learning with dependent observations. JMLR: Workshop and Conference Proceedings vol 1-15 (2012)
Anufriev, M., etc.: Learning-To-Forecast with Genetic algorithm. Amsterdam, 15 May (2012)
Arifovic, J.: Learning by Genetic Algorithms in Economic Environments. University of Chicago. SFI Working Paper: 1990—001. Oktober (1989)
Bonde, G., Khaled, R.: Stock Price Prediction using Genetic Algorithms and Evolution Strategies. Institute of Artificial Intelligence, University of Georgia. Athens. (2010)
Bruno, G.: Forecasting Using Functional Coefficients Autoregressive Models. ISAE, Institute for Studies and Economic Analyses, P.zza dell’Indipendenza, Rome, Italy. June (2008)
Davis, E.P., Karim, D.: Could Early Warning System Had Helped To Predict The Sub Prime Crisis. Brunel university and NIESR London. August (2007)
Drake, E.A.: Genetic Algorithms in Economics and Finance: Forecasting Stock Market Prices and Foreign Exchange. University of Stuttgart and University of New South Wales. Sydney.
Dietterich, T.G.: Machine Learning for Sequential Data: A Review. Oregon State University, Corvallis, Oregon, USA.
Inggrid.: Sector Financial and Economic Growth in Indonesia: Using Method of Causality in Multivariate Vector Error Correction Model (VECM). Economic Faculty of Universitas Kristen Petra Surabaya. (2006)
Lucas R.J. The Genetic Algorithm in Economics. Department of Agricultural and Economics, Montana State University. 4 May (2007)
Mahfoud, S., Mani, G.: Financial Forecasting using Genetic Algorithms. Applied AI, 10:543-565. (1996)
Shuhong, Z.: The Self Adaptable Modelling Of Socio-Economic Complex System Based On Genetic Algorithm. Journal of International for General Systems Studies. Hubei University of Economics, Wuhan. China. December 12, (2007)
Visco, I.: The Financial Crisis and Economic’s Forecast. Originally published in BIS review 49/2009. Estudos Avancados 23-66 (2009)
Van, D.B.J., Candelon, B., Urbain J-P.: A Cautious Note on The Use of Panel Model to Predict Financial Crises. Universiteit Maastricht, The Netherlands. June (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Saadah, S., Wulandari, G.S. (2015). Interconnection Learning between Economic Indicators in Indonesia Optimized by Genetic Algorithm. In: Kim, K. (eds) Information Science and Applications. Lecture Notes in Electrical Engineering, vol 339. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-46578-3_92
Download citation
DOI: https://doi.org/10.1007/978-3-662-46578-3_92
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-46577-6
Online ISBN: 978-3-662-46578-3
eBook Packages: EngineeringEngineering (R0)