Type-2 Fuzzy Clustering and a Type-2 Fuzzy Inference Neural Network for the Prediction of Short-term Interest Rates

Abstract The following paper discusses the use of a hybrid model for the prediction of short-term US interest rates. The model consists of a differential evolution-based fuzzy type-2 clustering with a fuzzy type-2 inference neural network, after input preprocessing with multiple regression analysis. The model was applied to forecast the US 3- Month T-bill rates. Promising model performance was obtained as measured using root mean square error.

[1]  Lotfi A. Zadeh,et al.  The Concepts of a Linguistic Variable and its Application to Approximate Reasoning , 1975 .

[2]  Maurice Larrain.  Testing Chaos and Nonlinearities in T-Bill Rates , 1991 .

[3]  R. Tschernig,et al.  Nonlinear Interest Rate Dynamics and Implications for the Term Structure , 1996 .

[4]  R. Storn,et al.  Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series) , 2005 .

[5]  Suh Young Kang,et al.  An investigation of the use of feedforward neural networks for forecasting , 1992 .

[6]  Stephen F. LeRoy,et al.  Efficient Capital Markets and Martingales , 1989 .

[7]  James D. Hamilton.  Rational-expectations econometric analysis of changes in regime: An investigation of the term structure of interest rates , 1988 .

[8]  Manfred Grauer,et al.  Stock Market Prediction with Multiple Regression, Fuzzy Type-2 Clustering and Neural Networks , 2011, Complex Adaptive Systems.

[9]  Jerry M. Mendel,et al.  Type-2 fuzzy sets made simple , 2002, IEEE Trans. Fuzzy Syst..

[10]  Vasant Naik,et al.  The Yield Curve and Bond Option Prices with Discrete Shifts in Economic Regimes , 1994 .

[11]  Bijan Fazlollahi,et al.  Evolutionary algorithm-based learning of fuzzy neural networks. Part 2: Recurrent fuzzy neural networks , 2009, Fuzzy Sets Syst..

[12]  David Enke,et al.  A New Hybrid Approach For Forecasting Interest Rates , 2012, Complex Adaptive Systems.

[13]  Mehdi Khashei,et al.  A new hybrid artificial neural networks and fuzzy regression model for time series forecasting , 2008, Fuzzy Sets Syst..

[14]  Witold Pedrycz,et al.  Type-2 fuzzy neural networks with fuzzy clustering and differential evolution optimization , 2011, Inf. Sci..