A ROBUST ALGORITHM IN SEQUENTIALLY SELECTING SUBSET TIME- SERIES SYSTEMS USING NEURAL NETWORKS

In this paper a numerically robust lattice-ladder learning algorithm is presented that sequentially selects the best specification of a subset time series system using neural networks. We have been able to extend the relevance of multilayered neural networks and so more effectively model a greater array of time series situations. We have recognized that many connections between nodes in layers are unnecessary and can be deleted. So we have introduced inhibitor arcs, reflecting inhibitive synapses. We also allow for connections between nodes in layers which have variable strengths at different points of time by introducing additionally excitatory arcs, reflecting excitatory synapses. The resolving of both time and order updating leads to optimal synaptic weight updating and allows for optimal dynamic node creation/deletion within the extended neural network. The paper presents two applications that demonstrate the usefulness of the process.

[1]  Y. P. Chung,et al.  A Transactions Data Test of Stock Index Futures Market Efficiency and Index Arbitrage Profitability , 1991 .

[2]  John Geweke,et al.  Maximum Likelihood "Confirmatory" Factor Analysis of Economic Time Series , 1981 .

[3]  T. Brailsford,et al.  Mispricing in Stock Index Futures: A Re‐Examination Using the SPI , 1997 .

[4]  R. Chou,et al.  ARCH modeling in finance: A review of the theory and empirical evidence , 1992 .

[5]  A. Mackinlay,et al.  Index-Futures Arbitrage and the Behavior of Stock Index Futures Prices , 1988 .

[6]  Jammie H. Penm,et al.  A note on the sequential fitting of multichannel subset autoregressions using the prewindowed case , 1995, IEEE Trans. Signal Process..

[7]  Kalok Chan,et al.  Intraday Volatility in the Stock Index and Stock Index Futures Markets , 1991 .

[8]  Kalok Chan,et al.  A Further Analysis of the Lead–Lag Relationship Between the Cash Market and Stock Index Futures Market , 1992 .

[9]  E. Hannan,et al.  The statistical theory of linear systems , 1989 .

[10]  C. A. Petri.  Introduction to General Net Theory , 1979, Advanced Course: Net Theory and Applications.

[11]  Richard Terrell,et al.  ON THE RECURSIVE FITTING OF SUBSET AUTOREGRESSIONS , 1982 .

[12]  C. B. Tilanus,et al.  Applied Economic Forecasting , 1966 .

[13]  Ton Vorst,et al.  A Threshold Error Correction Model for Intraday Futures and Index Returns , 1998 .

[14]  Yiu Kuen Tse,et al.  Lead-lag relationship between spot index and futures price of the nikkei stock average , 1995 .

[15]  James T. Kwok,et al.  Constructive algorithms for structure learning in feedforward neural networks for regression problems , 1997, IEEE Trans. Neural Networks.

[16]  Stanley J. Farlow,et al.  Self-Organizing Methods in Modeling: Gmdh Type Algorithms , 1984 .

[17]  S. Mittnik.  Forecasting with balanced state space representations of multivariate distributed lag models , 1990 .

[18]  James M. Holmes,et al.  ‘Optimal’ model selection when the true relationship is weak and occurs with a delay , 1989 .

[19]  Toshio Fukuda,et al.  An adaptive control for CARMA systems using linear neural networks , 1992 .

[20]  R. Terrell,et al.  Multivariate subset autoregressive modelling with zero constraints for detecting ‘overall causality’ , 1984 .

[21]  Kishan G. Mehrotra,et al.  Forecasting the behavior of multivariate time series using neural networks , 1992, Neural Networks.

[22]  Richard S. Sutton,et al.  A Unified View , 1998 .

[23]  Timo Teräsvirta,et al.  POWER OF THE NEURAL NETWORK LINEARITY TEST , 1993 .

[24]  Jammie H. Penm,et al.  Using the Bootstrap as an Aid in Choosing the Approximate Representation for Vector Time Series , 1992 .

[25]  Peter Hall,et al.  Using the bootstrap to estimate mean squared error and select smoothing parameter in nonparametric problems , 1990 .