پایان نامه پیش بینی الگوی بازار سهام با استفاده از شبکه های عصبی مصنوعی چندلایه پرسپترون

فهرست:

فهرست مطالب... شش

چکیده. ده

فصل اول: مقدمه. 1

فصل دوم: 6

2-1 مقدمه. 6

2-2 بررسی اولین پژوهشهای انجام شده. 6

2-3 استفاده از روشهای شبکه عصبی و تحلیلهای سری زمانی.. 7

2-4 بررسی بازار کارآمد. .8

2-5 فاکتورهای موثر در پیش بینی.. 9

2-6 ادغام روشهای شبکه­های عصبی  و فازی.. 9

2-7 روش ماشین بردار پشتیبان.. 10

2-8 تاثیر انتشار اطلاعات بورس بر روند پیش بینی.. 10

2-9 ایجاد سیستم خودکار. 11

2-10 بررسی جدیدترین روشها .11

2-11 بررسی روشهای داده کاوی در پیش بینی.. 14

2-12بررسی روش ماکف... 14

2-13 بررسی روش ARIMA.. 15

2-14 نتیجه گیری. 17

فصل سوم: 17

3-1مقدمه. 19

3-2 اصطلاحات رایج در بازار بورس... 19

3-2-1سهام. 19

3-2-2 بورس... 20

3-2-3 حجم مبنا 20

3-2-4 درصد تحقق سود. 20

3-2-5 پیش بینی سود. 21

3-2-6 شاخص.... 21

3-2-7 نماد. 21

3-2-8 دامنه نوسان   21

3-2-9 بررسی فاکتورهای کیفی و کمی.. 22

3-3 انواع روشهای پیش بینی. 22

3-3-1تحلیل تکنیکی.. 23

3-3-2تحلیل پایه. 24

3-3- 3روشهای جایگزین.. 28

شش

3-4 فرضیه بازار کارآمد.. 37

3-5 ماشین بردار پشتیبانی. 37

3-6 نتیجه­گیری... 38

فصل چهارم: 39

4-1 مقدمه. 39

4-2 انواع دیدگاه در ادبیات مالی.. 40

4-2-1 روش بنیادی.. .40

4-2-2روش تکنیکی. 40

4-3 الگوریتم TRAINLM .44

4-4 آموزش دسته ای کاهش شیب.. 46

4-5 آموزش دسته ای Momentum 46

4-6 تعیین تعداد لایه و تعداد نورون در هر لایه. 46

4-7 تحلیل نتایج.. 47

4-8 الگوی سر و سرشانه. 53

4-9 نحوه آماده سازی داده به کمکRandomWalk 56

4-10 تعیین تعداد لایه و تعداد نورون در هر لایه. 57

4-11نتیجه­گیری.. 62

فصل پنجم: 63.

5-1 مقدمه. 63

5-2 کارهای انجام شده در پایان نامه. 63

5-2-1 پژوهشی.. 63

5-2-2 اصلاحات... 63

5-2-3 نرم افزار. 64

5-2-4 پایگاه داده. 64

5-3 دوره زمانی پیش بینی.. 64

5-4 انواع پیش بینی.. 64

5-5 نوع پنجره انتخابی.. 64

6-5 تعداد لایه های پنهان و تعداد نورونها 65

5-7 نتیجه­گیری. 67

فصل ششم: 68

6-1 نتیجه گیری... 68

6-2 پیشنهادات.. 69

مراجع. 70

منبع:

[1] Papadrakakis M, Tsompanakis Y and Goldberg  N, : Optimization and Machincs and engineering pp. 309-333,vol. 156, 1989.

[2] Bingul  Z, A Sekman and S Zein-zabato: Evolutionary Approach to Multi Objective Problems Using Genetic Algorithms, IEEE transactions, international conference of systems, man and cybernetics, 2000.

[3] Robert J and Van Eyden: The Application of Neural Networks in the Forecasting of Share Prices,  Technology  Finance Publishing, 1996.

[4]White H: Economic prediction using neural networks a case of IBM daily stock returns,  International Conference on Neural Networks,1988, vol. 2, pp. 451-458.

[5] Phua, P K, H Ming and D Lin: Neura Network with Genetic Algorithms for Stocks Prediction, Fifth Conference of the Association of Asian-Pacific Operations Research Societies, Singapore, 5th - 7th July,2000.

[6] Kim K and Han I: Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index, vol. 19,2000.

[7] Chiang W C, Urban T L and Baldridge G W: A neural network approach to mutual fund net asset value forecasting, Omega,Intmgmt Sci, 2000, PP 205-215.

[8] Black E D :Financial market Analysis, second Edition, JohnWiley and sons, Ltd, New York. PP. 282-287.

[9] Schumann M and Lohrbach T: Comparing artificial neural networks with statistical methods within the field of stock market prediction, System Sciences, Proceeding of the Twenty-Sixth Hawaii International Conference on,1993 , pp. 597-606.

[10] Yoon Yand Swales G: Predicting Stock Price Performance: A Neural Networks Approach, Proceedings of the IEEE Twenty-Fourth Annual Hawaii International Conference on System Sciences,1991, pp. 156-162.

[11] Yoon Y Swales, G Jr. and Margavio T M: A Comparison of Discriminant Analysis Versus Artificial Neural Networks, Journal of the Operational Research Society, vol. 44,1993, pp. 51-60.

[12] Garliauskas A:Neural Network Chaos and Compuational Algorithm of Forecast in Finance, Proceedings of the IEEE SMC Conference on Systems, Man,and Cybernetics 2, pp. 638-643, 12-15 October 1999.

[13] Kim K, Hong T and Han I: KnowledgeDiscovery Process In Internet For Effective KnowledgeCreation, Korea AdvancedInstitute of Science and Technology,1998.

[14] Hong T and Han I: Integrated approach ofcognitive maps and neural networks using qualitativeinformation on the World Wide Web: KBN Miner, ExpertSystems, vol. 21 no.5,2004, pp. 243-252.

[15] Hong T and Han I: Knowledge-based datamining of news information on the Internet using cognitivemaps and neural networks, Expert Systems withApplications, vol. 23, no. 1, 2002,pp. 1-8.

[16] Fung G P C, Yu J X and Lam W:NewsSensitive Stock Trend Prediction, Lecture Notes in Computer Science, vol. 2336, Jan 2002, pp. 481.

[17] Kohara K: Selective-Learning-Rate Approachfor Stock Market Prediction by Simple Recurrent NeuralNetwork, Lecture Notes in Computer Science, vol 2773,Jan 2003, pp. 141-147.

[18] Kohara K Ishikawa, T Fukuhara Yand Nakamura Y: Stock Price Prediction Using Prior Knowledge and Neural Networks, Intelligent System In Accounting,Finance and Management, vol. 6,1997, pp. 11-22.

[19] Pui Cheong Fung,G Xu Yu J and Lam W :Stock prediction: Integrating text mining approach using real-time news, Computational Intelligence for FinancialEngineering, Proceedings, IEEE InternationalConference on 2003, pp. 395-402.

[20] Kohara K Ishikawa, T Fukuhara Y and Nakamura Y: Stock Price Prediction Using Prior Knowledge andNeural Networks, Intelligent System In Accounting,Finance andManagement, vol. 6,1997 pp. 11-22.

[21] Hong T and Han I :Knowledge-based datamining of news information on the Internet using cognitivemaps and neural networks, Expert Systems withApplications, vol. 23, no. 1, pp. 1-8.

[22] Kuo, R J Chen, C H and Hwang Y C :Anintelligent stock trading decision support system throughintegration of genetic algorithm based fuzzy neural networkand artificial neural network, Fuzzy Sets and Systems, vol.118,2001, pp. 21-45.

[23] Kuo R J Lee, L C and Lee C F 1996 :Integrationof Artificial Neural Networks and Fuzzy Delphi for Stock Market Forecasting,IEEE, June,1998, pp. 1073-1078.

[24] Fama, E F: Efficient capital markets II,.Journalof Finance. vol 47,1991, pp. 1575-1617.

[25] Tsibouris G and Zeidenberg M: Testing the Efficient Markets Hypothesis with gradientdescentalgorithms, In Neural Networks in the Capital Markets, vol. 8,1995, pp 127–136.

[26] Eyden R J:The Application of Neural Networksin the Forecasting of Share Prices, Finance and TechnologyPublishing,1996.

[27] Fung G P C, Yu J X and Lam W:NewsSensitive Stock Trend Prediction’, Lecture Notes in Computer Science, vol. 2336, Jan 2002, pp. 481.

[28] Mittermayer M A:Forecasting intraday stockprice trends with text mining techniques, System Sciences, Proceedings of the 37th Annual Hawaii InternationalConference on,2004, pp. 64-73.

 [29] Yoo Paul, D Kim, Maria H and Jan T: Machine Learning Techniques and Use of Event Information for Stock Market Prediction, International Conference on Computational Intelligence (CIMCA-IAWTIC' 05)2007.

[30] Schumann M and Lohrbach T: Comparingartificial neural networks with statistical methods within thefield of stock market prediction, System Sciences, Proceeding of the Twenty-Sixth Hawaii International Conference on, vol. 4,1993, pp. 597-606 vol.594.

[31] Lawrence R:Using Neural Networks toForecast Stock Market Prices, University of Manitoba,1997.

[32] Refenes  A Zapranis A D and Francis G:Modelling stock returns in the framework of APT: Acomparative study with regression models, Neural Networksin the Capital Markets, vol. 7,1997, pp. 101–126.

[33] Steiner M and Wittkemper H: Neural networks as an alternative stock market model, Neural Networks inthe Capital Markets, vol. 9,1995, pp. 137–148.

[34] Yoon Y, Swales G Jr. and Margavio T M:AComparison of Discriminant Analysis Versus ArtificialNeural Networks, Journal of the Operational ResearchSociety, vol. 44,1993, pp. 51-60.

[35] Dash M and Liu H: Feature selection forclassifications’, Intelligent Data Analysis: An InternationalJournal, vol. 1,1997, pp. 131-156.

[36] Hiemstra Y:Modeling structured nonlinear knowledge to predict stock market returns, R. R.(ed.), Chaos& Nonlinear Dynamics in the Financial Markets: Theory,Evidence and Applications, Irwin,1995, pp. 163-175.

[37] Tsaih R, Hsu Y and Lai C C:Forecasting S&P 500 stock index futures with a hybrid AI system, DecisionSupport Systems, vol. 23,1998, pp. 161-174.

[38] Vapnik V:An overview of statistical learningtheory, IEEE Transactions of Neural Networks, vol. 10,1999, pp.988-99.

[39] Yang H, Chan L and King I:Support VectorMachine Regression for Volatile Stock Market Prediction, Lecture Notes in Computer Science, vol. 2412,2002, pp. 391.

[40] Vapnik V: Statistical learning theory,New York.

[41] Tay F and Cao L:A comparative study of saliency analysis and genetic algorithm for feature selectionin support vector machines, Intelligent Data Analysis, vol. 5,2001, pp. 191-209

[42] Tay F and Cao L J:Application of supportvector machines in financial time series forecasting, Omega,vol. 29,2001, pp. 309-17.

[43] Kim K: Financial time series forecasting usingsupport vector machines, Neurocomputing, vol. 55,2004, pp. 307-319.

[44] Kim K:Toward Global Optimization of Case-Based Reasoning Systems for Financial Forecasting,Applied Intelligence, vol. 21, no. 3,2004, pp. 239-249.

[45] Ng  A and Fu A W:Mining Frequent Episodes for Relating Financial Events and Stock Trends, LectureNotes in Computer Science, vol. 2637,2003, pp. 27-39.

[46] Fawcett T and Provost F J: Combining data mining and machine learning for effective user profiling, In Proceedings of the Second International Conference onKnowledge Discovery and Data Mining, KDD-96,2004, pp. 8-13.

[47] Dase R K and Pawar D D: Application of Artificial Neural Network for stock market predictions: AA review of literature, International Journal of Machine Intelligence, ISSN: 0975–2927, Volume 2, Issue 2, 2010, pp-14-17.

[48] JingTao Y and Chew Lim T: Guidelines for Financial Prediction with Artificial neural networks,1999.

[49] David E and Suraphan T: The use of data mining and neural networks for forecasting stock market returns, 2005.

[50] Senthamarai Kannan K, Sailapathi Sekar P, Mohamed Sathik  M and Arumugam P: Financial stock market forecast using data mining Techniques, 2010, Proceedings of the international multiconference of engineers and computer scientists.

[51] Hsieh Y L, Don-Lin Yang and Jungpin Wu: Using Data Mining to study Upstream and Downstream causal relationship in stock Market, 2007.

[52] Rafiul Hassan M and Baikunth N: Stock Market forecasting using Hidden Markov Model: A New Approach, Proceeding of the 2005 5th international conference on intelligent Systems Design and Application 0-7695-2286-06/05, IEEE 2005.

[53]Rafiul Hassan M, Baikunth N and Kirley M: A fusion model of HMM, ANN and GA for stock market forecasting,  Expert systems with Applications, 2007, pp. 171-180,

[54] Yi-Fan Wang, Shihmin Cheng and Hsu M: Incorporating the Markov chain concepts into fuzzy stochastic prediction of stock indexes, Applied Soft Computing, 2010, pp.613-617.

[55] Peter Zhang G: Time series forecasting using a hybrid ARIMA and neural network model, Elsevier Neurocomputing 50 (2003) 159 – 175.

[56] Song Q and Chissom B S: New models for forecasting enrollments: fuzzy time series and neural networkapproaches, ERIC, 1993, p. 27.

[57] Hassan S,  Jaafar J, Samir B and Jilani  A: A Hybrid Fuzzy Time Series Model for Forecasting” Engineering letters, 2012.

[58] Devi P, Vijayalakshmi C and Sakthivel E: Design of a Fuzzy Time Series Forecasting Model for Hydro Power Generation, International Journal of Computer Applications (0975 – 8887) Volume 74– No.16, July 2013.

[59]  SANTHI T: STOCK MARKET FORECASTING TECHNIQUES: A SURVEY, Department of Computer Application, SASTRA University, Thanjavur,2010.

[60]  Adebiyi  A , Adewumi  A and  Ayo  CH: Comparison of ARIMA and Artificial Neural Networks Models for Stock Price Prediction, Journal of Applied Mathematics
Volume, Article No. 614342, 7 pages, March 2014.

[61] Haykin S , Neural Network A Comprehensive Foundation. Mcmaster University Hamilton, Ontario, Canada : Prentice Hall International Inc.

[62] Fagnerde Oliveira A., Cristiane N., Luis E., (2013); “Applying Artificial Neural Networks to prediction of stock price and improvement of the directional prediction index – Case study of PETR4, Petrobras Brazil” , Expert Systems with Applications, vol. 40, pp. 7596–7606, 2013.

 [63] Rodriguez J. V., Torra S., Felix J. A., (2005); “STAR andANN models: Forecasting Performance on SpanishIbex-35 Stock Index”, Journal of EmpiricalFinance, no. 12 vol.3, pp. 490-509, 2005.

[64] Zapranis  A and Samolada E "Can Neural Networks Learn the “Head and Shoulders”Technical Analysis Price Pattern? Towards a Methodology for Testing the Efficient Market Hypothesis", ICANNPart II, LNCS 4669, Springer-Verlag Berlin Heidelberg, (516–526), 2007.

[65] Jegadeesh N, "Foundations of technical analysis", Computational algorithms, statistical inference, and empirical implementation", The J. of Fin 4, 1765–1770, 2000.

[66] Volna E, Kotyrba K and Jarusek R " Multi-classifier based on Elliott wave’s recognition",  Elsevier Ltd computer and mathematics with applications 66, (213-255), 2013.

[67] Zapranis A and Tsinaslanidis P "Identification of the Head and Shoulder technical analysis pattern with Neural Network", ICANN Part III, LNCS 6354, Springer-Verlag Berlin Heidelberg, (130-136), 2010.