From mavrmgls@rtsg.mot.com Tue Feb 1 21:59:57 EST 1994 Article: 14561 of comp.ai.neural-nets Xref: glinda.oz.cs.cmu.edu comp.ai.neural-nets:14561 Path: honeydew.srv.cs.cmu.edu!das-news.harvard.edu!noc.near.net!MathWorks.Com!europa.eng.gtefsd.com!uunet!mdisea!mothost!delphinium.cig.mot.com!mavrmgls From: mavrmgls@rtsg.mot.com (Nick M. Mavromagoulos) Newsgroups: comp.ai.neural-nets Subject: NN in Financial Apps (1 of 2) Date: 31 Jan 1994 20:11:20 GMT Organization: Motorola Inc., Cellular Infrastructure Group Lines: 115 Distribution: na Message-ID: <2ijol8$3qc@delphinium.cig.mot.com> NNTP-Posting-Host: khaki44.rtsg.mot.com The following is a listing of information concerning Neural Networks in financial applications. Thanks to all who responded. This is file 1 of 2. BOOKS & MAGAZINES: ------------------ 1. Title: Neural Networks in Finance and Investing, Summary: Using artificial intelligence to improve real-world performance. Editors: Robert R. Trippi, Efraim Turban. Chicago, Ill., Probus, 1992 xxviii, 513p, ill 2. From an advertisement in 'PC AI' magazine. Title: Forecasting With Neural Networks Price: $12.50 (US). Summary: The interesting bit is that the detailed example in the paper is a "how to" on using neural networks to predict commodity prices. It is really quite good. Address: Bellwood Research Center 19 Bellwood Avenue Ottawa, Ontario Canada, K1S 1S6 3. Fortune Sept. 93. An article about Neural Netwirks had clips on financial management. Look at the picture, you can tell what software they used. 4. Title: NEUROVE$T JOURNAL Summary: A bi-monthly journal on applying neural networks and other advanced technologies and tools to the financial markets. Looking for papers and subscribers. If you're interested in either or both, please contact the editor. (See below). Address: P.O. Box 764 Haymarket, VA 22069 USA Editor: Randall Caldwell E-Mail: rbcaldwell@delphi.com 5. Title: Forecasting with Neural Networks Source: Neuron Digest (V12 #24) 6. Title: Technical Analysis of Stocks and Commodities (ISSN 0738-3355) Summary: The magazine covers "the waterfront" on financial markets from the trader's view and focuses only on market trading. As it strives to appeal to a broad audience, the articles tend to be short and introductory, but the magazine does introduce all the hot topics. Note: This may be a BONUS issue which are only available to subscribers. It is usally found at the "better" book stores. The bonus issues contain abstracts and idexes to all of the articles. Source: Technical Analysis, Inc. Address: 4757 California Ave. S. W. Seattle, WA 98116-4499 7. Source: Forbes Date: Jan 21-28 1994 GROUPS / CONFERENCES: --------------------- 1. Name: The Society for the Management of Advanced Relevant Technologies in Financial Services (SMART-F$) Summary: SMART-F$ membership is a great way to find out what the financial services community's interests and activities are in the emerging technologies area. The organization was established in 1987 and was originally called Society for the Management of AI Resources and Technology in Financial Services, with the same acronym -- SMART-F$. Cost: SMART-F$ annual membership, which includes admission to 5 general meetings per year and all of its SIG sessions, is $40.00 per person for end users of advanced/emerging technologies and $100.00 per person for vendors of advanced/emerging technologies or vendors to the financial services companies. Contact: Dr. Dan Schutzer Susan Garavaglia Chairman Advisory Board Member 212-599-1876 201-605-6216 MISCELLANEOUS: -------------- 1. I'm near-real-time testing a NN solution for predicting SPX (SP 500 Index Options). Took months to generate usable preprocessing rules for training data (selecting applicable features, manipulations for averaging, scaling, etc.), days (hours) to train Back Propagation network. Currently, I am loading each day's closing data and testing to see if the NN can predict the future - then checking to see if it was right at the end of the prediction period. If it works, I'll happily publish my methods and results after I retire. If it dosen't, I'll go ahead and post them in the next few months. At least you'll be able to eliminate one method. Mark Jurik (I think I've seen some of his posts in this group) gives as good a description of the mechanics of selecting and preprocessing data as any I've seen, but you'd better be your own domain expert and select your own features - not use the ones he uses in his example. Also, Jurik's basic article is in the Appendix to the User Manual of BrainCel - a simple, easy NN package that's a DLL for Microsoft Excel on a Windows 3.1 PC. I found Braincel a cheap way to get started before spending a lot of time coding my own NN algorithms (or spending a major chunk of my risk capital on one of the more elegant packages like BrainMaker) - they had a $99.95 special going at one time. Manufacturer is Promised Land Technologies - they advertise in 'AI Expert' and 'Stocks & Commodities' magazines. Might also subscribe to Neurove$t Journal - I've seen one issue and it had some hints. Also advertised in 'Stocks & Commodities'. Article 14562 of comp.ai.neural-nets: Xref: glinda.oz.cs.cmu.edu comp.ai.neural-nets:14562 Path: honeydew.srv.cs.cmu.edu!das-news.harvard.edu!noc.near.net!MathWorks.Com!europa.eng.gtefsd.com!uunet!mdisea!mothost!delphinium.cig.mot.com!mavrmgls From: mavrmgls@rtsg.mot.com (Nick M. Mavromagoulos) Newsgroups: comp.ai.neural-nets Subject: NN in Financial Apps (2 of 2) Date: 31 Jan 1994 20:13:26 GMT Organization: Motorola Inc., Cellular Infrastructure Group Lines: 491 Distribution: na Message-ID: <2ijop6$3qr@delphinium.cig.mot.com> NNTP-Posting-Host: khaki44.rtsg.mot.com The following is a listing of information concerning Neural Networks in financial applications. Thanks to all who responded. This is file 2 of 2. REFERENCES ON NEURAL NETWORKS, GENETIC ALGORITHMS IN FINANCIAL FORECASTING Note: The below mentioned references have been arranged in order of receipt. Some redundancies and inconsistencies in the formatting will therefore be there. ==========++++++++++++++++++++++++++++++++++++++++=============== Akaike H, 1986, Use of Statistical Models for Time Series Analysis, Proceesings ICASSP 86, 3147-3155, IEEE, Tokyo. Bulsari A. B. & Sax H., 1993, A Recurrent Neural Network for Time Series Modelling, in Artificial Neural Nets and Genetic Algorithms, Ed. Albrecht R.F., Steele N.C., & Reeves C.R., 285- 291, Springer-Verlag, Innsbruck, Austria. Casdagli M, 1989, Nonlinear Prediction of Chaotic Time Series, Physical Review, 35, 335-356. Farmer J. D. & Sidorowich J. J., 1987, Predicting chaotic time series, Physical Review Letters,59, 845-848. Gabr M. M. & Subba Rao, T, 1981, The estimation and prediction of subset bilinear time series models with applications, Journal of Time Series Analysis, 2, 155-171. Gent C.R., 1990, Predicting Time Series by a Fully Connected Recurrent Net Trained by Back Propagation -- A First Look,Handsheed at Neuro Nimes 90. Jones R D , Y. C. Lee , C. W. Barnes , G. W. Flake , K. Lee , P. S. Lewis and S. Qian, Function Approximation and Time Series Prediction withNeural Networks,International Joint Conference on Neural Networks, Univ. of Calif., Los Alamos Nat. Laboratory, June, San Diego, CA, 649-665, I, 1990 Lewis P A. W.& J. G. Stevens, Nonlinear modeling of time series using multivariate adaptive regression splines (MARS) Preprint, Naval Postgraduate School, Monterey, CA, January 1991, Martin R. Douglas, 1981, Robust methods for time series, Applied Time Series Analysis II 683-759, D. F. Findley, New York, Academic Press. Metzger M.A., Mitsumoto K, 1991, Forecasting Multivariate Time- Series: Confidence Intervals and Comparison of Performances of Feed-Forward Neural Network and StateSpace Models, International Joint Conference on Neural Networks, submitted, Seattle, Washington. Packard N H, J P. Crutchfield, J. D. Farmer and R. S. Shaw, 1980, Geometry from a Time Series, Physical Review Letters, 712- 716, 45. Weigend A S, & David E. Rumelhart, Bernardo A. Huberman, 1990, Back-propagation, weight-elimination and time series prediction, Proceedings of the 1990 Connectionist Models Summer School, Ed. David S. Touretzky and J. L. Elman, Terence J. Sejnowski, Geoffrey E. Hinton, PUBLISHER = Morgan Kaufmann, San Mateo, CA, 105--116 Kuan, Chung-Ming "Forecasting Exchange Rates Using Feedforward And Recurrent Neural Networks", faculty working paper of University of Illinois at Urbana Champaign. PC AI Magazine "Forecasting With Neural Networks", available from Bellwood Research Center, Bellwood Avenue, Ottawa, Ontario, Canada, K1S 1S6. Choi, Jai J, O'Keefe, Kenneth H and Baruah, Pranab "Non-linear System Diagnosis Using Neural Networks And Fuzzy Logic" [FUZZY IEEE 92] and Boeing Computer Services TR B91-91. Collard, J E "Commodity Trading With A Three Year Old" [IJCNN]. Grinzberg, I and Horn, D "Learning The Rule Of A Time Series" International Journal Of neural Systems, volume 3 number 2/3 Murtagh, Fionn "Neural Networks For Statistical And Economic Data" Workshop Proceeding Dublin. Refenes, A N, Barac, M Azeman,Chen, L and Karouses, S A "Currency Exchange Rate Prediction And Neural Networks Design Strategies" TR Department of Computerscience University College London and Journal Of Neurocomputing and Applications. Scho:neburg, E "Stock Price Prediction Using Neural Networks: A Project Report" Neurocomputing 2 pp. Sharda, R and Patil, R B "Neural Network A Forecasting Expert: An Empirical Test" [IJCNN90]. White, H "Economic Prediction Using Neural Networks: The Case Of IBM Daily Stock Return" University of California, San Diego TR 88-20. Wang, F and Tan, P Y "Neural Networks And Genetic Algorithms For Economic Forecasting". Lapedes, A and faber, R "Non-linear Signal Processing Using Neural Networks: Prediction and System Modeling" Los Alamos National Laboratory Report. `Nonlinear modeling and forecasting', book edited by Casdagli and Eubank, The Santa fe Institute Studies in the Sciences of Complexity -Addison Wesley 1992 Soft Classification, a.k.a. Penalized Log Likelihood and Smoothing Spline Analysis of Variance by Grace Wahba, Chong Gu, Yuedong Wang and Rick Chappell to appear in the proceedings of the Santa Fe Workshop on Supervised Machine Learning, August 1992, D. Wolpert and A. Lapedes, eds. also partly presented at CLNL*92. Smoothing Spline ANOVA with Component-Wise Bayesian `Confidence Intervals' by Chong Gu and Grace Wahba, J. Computational and Graphical Statistics, March 1993 W. Hsu and L. S. Hsu and M. F. Tenorio, "Feature Subset Selection with Application to Financial Prediction Tasks," in Financial Applications and Neural Networks, P. Refenes, ed., Cambridge Press, 1993. Tenorio, M. F., and W. T. Lee, "Self Organizing Networks for Optimum Supervised Learning," IEEE Trans. on Neural Networks, IEEE Press, vol. 1, no. 1, pp. 100-110, 1990, premier issue. Tenorio, M. F., "Topology Synthesis Networks: Self Organization of Structure and Weight Adjustment as a Learning Paradigm," Parallel Computation, North Holland, vol. 14, pp. 363-380, 1990. Tenorio, M. F., and W. T. Lee, "Self Organizing Neural Networks for the Identification Problem," 2nd IEEE Neural Information Processing Systems Conference, sponsored by IEEE, Denver, Colorado, December 1988. Tenorio, M. F., "The Self Organizing Neural Network Algorithm: Adapting Structure for Optimum Supervised Learning," Hawaii International Conference System Sciences, HICSS-22, Honolulu, Hawaii, January 1990. Hsu, W., and M. F. Tenorio, "A Similarity Based Approach to Forecasting," IEEE Workshop on Neural Networks, co-sponsored by Auburn University Space Power Institute, the Center for Commercial Development of Space Power and Advanced Electronics, and NASA Headquarters, Auburn, Alabama, pp. 138-142, February 1992. Hsu, W. and Tenorio, M. F., "Plastic Network for Predicting the Mackey-Glass Time Series," International Joint Conference on Neural Networks, sponsored by the IEEE Neural Network Council and the International Neural Network Society, Baltimore, Maryland, pp.941-946, June 1992. Thome, A. C., M. F. Tenorio, "Economic Signal Analysis, Modelling, and Estimation Through a Similarity Based Approach," IX Brazilian Society for Artificial Intelligence Meeting, Rio de Janeiro, Brazil, October 1992. M. F. Tenorio, "Application of Neural Network for Chaotic System Modelling," International Keynote Speech, First Workshop on Neural Networks, co-sponsored by IBM and Varig, Rio de Janeiro, Brazil, October 1992. M. F. Tenorio, "Implications of Neural Networks to Economic Forecasting," First Workshop on Neural Networks, co-sponsored by IBM and Varig, Rio de Janeiro, Brazil, October 1992. W. Hsu and L. S. Hsu and M. F. Tenorio, "A ClusNet Architecture for Prediction," International Conference on Neural Networks, sponsored by the IEEE Neural Network Council, IEEE Publishing Services, 1993. Thome, A. C., M. F. Tenorio, "Analysis, Modelling, and Estimation Through a Similarity Based Approach: An Economic Signal Case Study" International Conference on Neural Networks, sponsored by the IEEE Neural Network Council, IEEE Publishing Services, 1993. Hsu, W., L. S. Hsu and M. F. Tenorio,"Feature Subset Selection and Financial Prediction Tasks", TR-EE-92-53, Technical Report of the School of Electrical Engineering, Purdue University, December 1992. Hsu W., L. S. Hsu and M. F. Tenorio, "A Neural Network Architecture for Prediction", TR-EE-92-38, Technical Report of the School of Electrical Engineering, Purdue University, December, 1992. Hsu, W. , L. S. Hsu and M. F. Tenorio, "An Embedding Selection Algorithm for the Prediction of Chaotic Dynamical Systems", TR- EE-92-51, Technical Report of the School of Electrical Engineering, Purdue University, December, 1992. Hsu W., L. S. Hsu and M. F. Tenorio, "A Decision Boundary Method for Embedding Selection", TR-EE-92-52, Technical Report of the School of Electrical Engineering, Purdue University, December, 1992. Hsu,W., L. S. Hsu, M. F. Tenorio, "Indicator Selection with SupNet and Currency Prediction," The Journal of Neural Computing & Applications, submitted. Hsu,W., L. S. Hsu, M. F. Tenorio, "The ClusNet Algorithm for the Prediction of Time Series" International Journal of Neural Systems,submitted. Hsu,W., L. S. Hsu, M. F. Tenorio, "A Decision Boundary Method for Chaotic Time Series Embedding Selection," Journal of Complex Systems, submitted. Hsu,W., L. S. Hsu, M. F. Tenorio, "A Novel Embedding Selection Algorithm for Chaotic Time Series Prediction," Physics Review Letters , submitted. J.-S. Roger Jang, ANFIS: Adaptive-Network-Based Fuzzy Inference System, itsmc, 1993, 23, 03, may, (Forthcoming) S. Margarita, "Genetic neural networks for financial markets: Some results", 10th European Conf on AI, ECAI-92, pp211-213. Andrewa Beltratti & Segrio Margarita, "Evolution of trading strategies among heterogeneous artificial economic agents," 2nd international conf on simulation of adaptive behaviour (SAB92). T. Tanigawa,k K. Kamijo, "Stock price pattern matchin system -- Dynamic programming neural net approach", IJCNN92, Vol II, pp 465-471. R. D. Jones, Y. C. Lee, C. W. Barnes, G. W. Flake, K Lee, P. S. Lewis, S. Qian, "Function approximation and time series prediction with neural networks", tech report LA-UR 90-21, Los Alamos National Lab. Richard J. Bauer & Gunar Liepins, "Genetic Algorithms and Stock Market Timing Trading Rules", 11th International Syumposium on Forcasting, New York City, 1991. Chia-Fen Chang, B. J. Sheu, Jeff Thomas, "Multil-Layered back- propagation neural networks for finance analysis", World Congress on Neural Networks, Portland, OR, 1993, pp 445-450. Refenes A.N et al, Currency exchange Rate prediction and Neural network Design Strategies, Neural Computing and Applications, 1, 1, 1993. Hoptroff RG The principles and practice of Time series forecasting and Business Modelling Using neural nets, Neural Computing and Applications, 1,1, 1993 (springer) Back, A.D., Tsoi, A.C. ``A time series modelling methodology using FIR and IIR synapses''. Proc Workshop on Neural Networks for Statistical and Economic Data, Dublin, DOSES, Statistical Office of European Communities, F. Murtagh (Ed.), pp 187 - 194, 199 K. Chakraborty, K. Mehrotra, C.K. Mohan & S. Ranka,`Forecasting the behavior of multivariate time series using neural networks', Neural Networks 5 (1992): 961-70. J. Deppisch, H.U. Bauer & T. Geisel, `Hierarchical training of neural networks and prediction of chaotic time series Physics Letters A 158 (1991): 57-62. J.B. Elsner, `Predicting time series using a neural network as a method of distinguishing chaos from noise', J. of Physics A 25 (1992): 843-50. W.R. Foster, F. Collopy & L.H. Ungar, `Neural network forecasting of short, noisy time series', Computers & Chemical Engineering 16 (1992): 293-7. A.R. Hoptroff, `The principles and practice of time series forecasting and business modelling using neural nets', Neural Computing and Applications 1 (1) (1993): 59-66. D. McCaffrey, S. Ellner, A.R. Gallant & D. Nychka, `Estimating the Lyapunov exponent of a chaotic system with nonparametric regression', J. American Statistical Assoc. 87 (1992): 682-. R.M. Miller, Computer-Aided Financial Analysis (Addison-Wesley, 1990). D. Nychka, S. Ellner, A.R. Gallant & D. McCaffrey, `Finding chaos in noisy systems', J. Royal Statistical Soc. B 54 (1992): 399- 426. A.N. Refenes, `Currency exchange rate prediction and neural network design strategies', Neural Computing and Applications 1 (1) (1993). E. Schoenenberg, `Stock price prediction using neural networks: a project report', Neurocomputing 2 (1990): 17-27. A.S. Weigend & N.A. Gershenfeld, eds, Predicting the Future and Understanding the Past: A Comparison of Approaches, Santa Fe Institute Studies in the Sciences of Complexity, Proceedings vol XVII (Addison-Wesley, 1993, to appear). A.S. Weigend, B.A. Huberman & D.E. Rumelhart, `Predicting the future: a connectionist approach', International J. of Neural Systems 1 (1990): 193-209. A.S. Weigend, B.A. Huberman & D.E. Rumelhart, `Predicting sunspots and exchange rates with connectionist networks', in M. Casdagli & S. Eubank, eds, Nonlinear Modeling and Forecasting Santa Fe Institute Studies in the Sciences of Complexity, Proceedings vol XII (Addison-Wesley, 1992). H. White, `Economic prediction using neural networks: the case of IBM daily returns', in R. Trippi & E. Turban, eds, Investment Management, Decision Support and Expert Systems (Boyd & Fraser, 1990),\ 383-92. D.M. Wolpert & R.C. Miall, `Detecting chaos with neural networks', Proc. Royal Society of London B 242 (1990): 82-6. F. Wong & P.Y. Tan, `Neural networks and genetic algorithm for economic forecasting', available by anonymous ftp from archive.cis.ohio-state.edu, file wong.nnga.ps.Z in pub/neuroprose. Y. Yamamoto & S.A. Zenios, `Predicting prepayment rates for mortgage-backed securities using the cascade-correlation learning algorithm', J. of Fixed Income 2 (4) (Mar 1993): 86-96. Weigend A. S., "Predicting the Future: A Connectionist Approach," International Journal of Neural Systems, Vol.1, No.3, 193-209 (1990) Chakraborty K. et al., "Forecasting the Behavior of Multivariate Time Series Using Neural Networks," Neural Networks, Vol.5, 961- 970 (1992) Bacha H. et al., "A Neural Network Architecture for Load Forecasting," Proc. of IJCNN'92-Baltimore, Vol.II, 442-447 (1992) Park D. C. et al., "Electric Load Forecasting Using An Artificial Neural Network," IEEE Trans. Power Systems, Vol.6, No.2, 442-449 (1991) Caire P. et al., "Progress in Forecasting by Neural Networks,"Proc. of IJCNN'92-Baltimore, Vol.II, 540-545 (1992) Varfis A. et al., "Univariate Economic Time Series Forecasting by Connectionist Methods," Proc. of INNC'90-Paris, 342-345 (1990) Windsor C. et al., "Multi-variate Financial Index Prediction -A Neural Network Study," Proc. of INNC'90-Paris, 357-360 (1990) Kimoto T. et al., "Stock Market Prediction with Modular Neural Networks," Proc. of IJCNN'90-San Diego, Vol.I, 1-6 (1990) Dutta S. et al., "Bond Rating: A Non-Conservative Application of Neural Networks," Proc. of ICNN'88, Vol.II, 443-450 (1988) White H. et al., "Economic Prediction Using Neural Networks: The Case Study of IBM Daily Stock Returns," Proc. of ICNN'88, Vol.II, 451-458 (1988) Connor J. et al., "Recurrent Neural Networks and Time Series Prediction," Proc. of IJCNN'91-Seattle, Vol.I, 301-306 (1991) Hoptroff R. G. et al., "Forecasting Economic Turning Points with Neural Nets," Proc. of IJCNN'91-Seattle, Vol.I, 347-351 (1991) Lambert J. M. et al., "Application of Feedforward and Recurrent Neural Networks to Chemical Plant Predictive Modeling," Proc. of IJCNN'91-Seattle, Vol.I, 373-378 (1991) Milidiu R. L. et al., "Oil Product Prices Forecasting through Backpropagation," Proc. of Neuro-Nimes'91, 99-104 (1991) Pelikan E., de Groot C., Wuertz D.: Power Consumption in West- Bohemia: Improved forecasts with decorrelating connectionist networks, Neural Network World 6, Vol 2, 1992, 701-712 de Groot C., Wuertz D.: Forecasting Time Series with Connectionist Nets: Applications in Statistics, Signal Processing and Enonomics, Lecture Notes in Artificial Intelligence 604, F.Belli and J. Rademacher Eds., Springer Verlag, Heidelberg 1992, 461-470 Wong, Francis and Tan, Pan Yong (1992): Neural Networks and Genetic Algorithm for Economic Forecasting, Institute of System Science, National University of Singapore, erscheint in: AI in Economics and Business Administration. available as "archive.cis.ohio-state.edu:/pub/neuroprose/wong.nnga.ps.Z" Casdagli, Martin (1991): International Forecasting Workshop held, in: The Bulletin of the Santa Fe Institute, Vol. 6, No. 1, S. 6- 7. contains references to Norman Packard (Univ Ill.) who used genetic algorithms for identifying windows of predictibility in the S&P 500 Chakraborty, Kanad, Mehrorta, Kishan, Mohan, Chilukuri K. und Ranka, Sanjay (1992): Forecasting the Behavior of Multivariate Time Series Using Neural Networks, in:Neural Networks, Vol.5, S. 961-969. Refenes, A. N. et al (1993): Financial Modelling Using Neural Networks, to appear in: Liddell, H. (Hrsg.): Commercial Parallel Processing, Unicom. Schumann, Matthias und Lohrbach, Thomas (1993): Comparing Artificial Neural Networks with Statistical Methods within the Field of Stock Market Prediction, in: Proceedings of the Twenty- Sixth Annual Hawaii International Conference on System Sciences, S .597-606. Varfis, Aristide und Versino, C. (1990): Univariate Economic Time Series Forecasting by Connectionist Methods, in: International Neural Network Conference - INNC-90-Paris, Vol. 1, S. 342-345. Windsor, Colin G. und Harker, Antony H. (1990): Multi-variate Financial Index Prediction - A Neural Network Study, International Neural Network Conference INNC-90-Paris, Vol. 1, S. 357-360 M Casdagli (1989) Nonlinear prediction of chaotic time series. Physica D35, 335-356. E Schoneburg (1990) Stock price prediction using neural networks: a project report. Neurocomputing 2, 17-27. C de Groot & D Wurtz (1991) Analysis of univariate time series with connectionist nets: a case study of two classical examples. Neurocomputing 3, 177-192. RH Berry and GD Smith (1993) Using a genetic algorithm to investigate taxation induced interactions in capital budgeting. In RF Albrecht, CR Reeves and NC Steele (1993) Artificial Neural Nets and Genetic Algorihms: Proceedings of the International Conference. Springer-Verlag, Vienna. ISBN 3-211-82459-6. K Stokbro, D K Umberger, and J A Hertz: Exploiting Neurons with Localized Receptive Fields to Learn Chaos. Complex Systems 4, 603-622 (1990) N H Wulff and J A Hertz: Prediction with Recurrent Networks. in Neural Networks for Signal Processing II, Proceedings of the 1993 IEEE Workshop (S Kung, F Fallside, J Aa Sorensen and C Kamm, eds.), pp. 464-473, IEEE Press (1992) Kuan, Chung-Ming "Forecasting Exchange Rates Using Feedforward And Recurrent Neural Networks", faculty working paper of University of Illinois at Urbana Champaign. Trippi and Turban "Neural Networks In Finance And Investing" available from Finance Trading Seminar, phone 1-800-458-0939. PC AI Magazine "Forecasting With Neural Networks", available from Bellwood Research Center, Bellwood Avenue, Ottawa, Ontario, Canada, K1S 1S6. Choi, Jai J, O'Keefe, Kenneth H and Baruah, Pranab "Non-linear System Diagnosis Using Neural Networks And Fuzzy Logic" [FUZZY IEEE 92] and Boeing Computer Services TR B91-91. Collard, J E "Commodity Trading With A Three Year Old" [IJCNN]. Grinzberg, I and Horn, D "Learning The Rule Of A Time Series" International Journal Of neural Systems, volume 3 number 2/3 Murtagh, Fionn "Neural Networks For Statistical And Economic Data" Workshop Proceeding Dublin. Refenes, A N, Barac, M Azeman,Chen, L and Karouses, S A "Currency Exchange Rate Prediction And Neural Networks Design Strategies" TR Department of Computerscience University College London and Journal Of Neurocomputing and Applications. Scho:neburg, E "Stock Price Prediction Using Neural Networks: A Project Report" Neurocomputing 2 pp. Sharda, R and Patil, R B "Neural Network A Forecasting Expert: An Empirical Test" [IJCNN90]. White, H "Economic Prediction Using Neural Networks: The Case Of IBM Daily Stock Return" University of California, San Diego TR 88-20. Wang, F and Tan, P Y "Neural Networks And Genetic Algorithms For Economic Forecasting". Lapedes, A and faber, R "Non-linear Signal Processing Using Neural Networks: Prediction and System Modeling" Los Alamos National Laboratory Report.