Nonlinear analysis and prediction of soybean futures

Yin T., Wang Y. (2021): Nonlinear analysis and prediction of soybean futures. Agric. Econ. – Czech, 67: 200–207.

supplementary materialdownload PDF

We use chaotic artificial neural network (CANN) technology to predict the price of the most widely traded agricultural futures – soybean futures. The nonlinear existence test results show that the time series of soybean futures have multifractal dynamics, long-range dependence, self similarity, and chaos characteristics. This also provides a basis for the construction of a CANN model. Compared with the artificial neural network (ANN) structure as our benchmark system, the predictability of CANN is much higher. The ANN is based on Gaussian kernel function and is only suitable for local approximation of nonstationary signals, so it cannot approach the global nonlinear chaotical hidden pattern. Improving the prediction accuracy of soybean futures prices is of great significance for investors, soybean producers, and decision makers.

Chan B., Wan A. (2013): Range-based price forecasts and a trading strategy for corn and soybeans futures. Journal of Business & Economics, 5: 1–23.
Das S., Mishra D. (2019): A hybridized ELM using self-adaptive multi-population based Jaya algorithm for currency exchange prediction: An empirical assessment. Neural Computing & Applications, 31: 7071–7094.
Falat L., Marcek D. (2014): Financial time series modelling with hybrid model based on customized RBF neural network combined with genetic algorithm. Advances in Electrical and Electronic Engineering, 12: 307–318.
Fama E. (1976): Foundations of Finance: Portfolio Decisions and Securities Prices. New York, USA, Basic Books: 1–395.
Fraser A., Swinney H. (1986): Independent coordinates for strange attractors from mutual information. Physical Review A., 33: 11–34.
Gao J., Zheng Z. (1993): Local exponential divergence plot and optimal embedding of a chaotic time series. Physics Letters A, 181: 153–158.
Gebremariam S., Marchetti J. (2018): Economics of biodiesel production: Review. Energy Conversion and Management, 168: 74–84.
Hanias M., Ozun A., Curtis P. (2010): A chaos analysis for Greek and Turkish equity markets. Euromed Journal of Business, 5: 101–118.
Haugen R. (1999): The Inefficient Stock Market. New Jersey, USA, Prentice Hall: 1–98.
Hsu C. (2013): A hybrid procedure with feature selection for resolving stock/futures price forecasting problems. Neural Computing & Applications, 22: 651–671.
Ihlen E. (2012): Introduction to multifractal detrended fluctuation analysis in Matlab. Frontiers in Physiology, 3: 141.
Kantelhardt J., Zschiegner S., Koscielny B. (2002): Multifractal detrended fluctuation analysis of nonstationary time series. Physica A: Statistical Mechanics and its Applications, 316: 87–114.
Lahmiri S. (2017): On fractality and chaos in Moroccan family business stock returns and volatility. Physica A: Statistical Mechanics and its Applications, 473: 29–39.
Lashermes B., Abry P., Chainais P. (2004): New insights into the estimation of scaling exponents. International Journal of Wavelets, Multiresolution and Information Processing, 2: 497–523.
Lei L. (2018): Wavelet neural network prediction method of stock price trend based on rough set attribute reduction. Applied Soft Computing, 62: 923–932.
Liu C. (2009): Price forecast for gold futures based on GA-BP neural network. In: Proceedings, International Conference on Management and Service Science (IEEE), Wuhan/Beijing, China, Sept 20–22, 2009: 1–3.
Ma W., Wang Y., Dong N. (2010): Study on stock price prediction based on BP neural network. In: International Conference on Emergency Management and Management Sciences (IEEE), Beijing, China, Aug 8–10, 2010: 57–58.
Mensi W., Tiwari A., Yoon S. (2017): Global financial crisis and weak-form efficiency of Islamic sectoral stock markets: An MF-DFA analysis. Physica A, 471: 135–46.
Moody J., Darken C. (1989): Fast learning in networks of locally-tuned processing units. Neural Computation, 1: 281–294.
Pandey V., Kohers T., Kohers G. (2010): Deterministic non-linearity in the stock returns of major European equity markets and the United States. Financial Review, 33: 45–64.
Peters E. (1991): Fractal Market Analysis: Applying Chaos Theory to Investment and Economics. New York, USA, Wiley & Sons.
Rizvi S., Dewandaru G., Bacha O., Masih M. (2014): An analysis of stock market efficiency: Developed vs Islamic stock markets using MF-DFA. Physica A, 407: 86–99.
Rumelhart D., Hinton G., Williams R. (1986): Learning Internal Representations by Error Propagation in Parallel Distributed Processing. Cambridge, Massachusetts, USA, MIT Press: 318–362.
Shahzad S., Nor S., Mensi W. (2017): Examining the efficiency and interdependence of US credit and stock markets through MF-DFA and MF-DXA approaches. Physica A, 471: 351–363.
Shynkevich Y. (2017): Forecasting price movements using technical indicators: Investigating the impact of varying input window length. Neurocomputing, 264: 71–88.
Wang C., Gao Q. (2018): High and low prices prediction of soybean futures with LSTM neural network. 9th International Conference on Software Engineering and Service Science (IEEE), Beijing, China, Nov 23–25, 2018: 140–143.
Wang J., Wang J., Zhang Z. (2011): Forecasting stock indices with back propagation neural network. Expert Systems with Applications, 38: 10–16.
Wind (2020): Wind Economic Database. [Dataset]. Wind.
Wolf A., Swift J., Swinney H., Vastano J. (1985): Determining Lyapunov exponents from a time series. Physica D: Nonlinear Phenomena, 16: 285–317.
Yang S., Tseng C. (1996): An orthogonal neural network for function approximation. IEEE Transactions on System, Man and Cybernetics, Part B., 5: 23–29.
Zhu H., Zhang W. (2018): Multifractal property of Chinese stock market in the CSI 800 index based on MF-DFA approach. Physica A: Statistical Mechanics and its Applications, 490: 497–503.
supplementary materialdownload PDF

© 2021 Czech Academy of Agricultural Sciences | Prohlášení o přístupnosti