Open Access Open Access  Restricted Access Subscription or Fee Access

An Ensemble Model for Pattern Prediction Problems

Dr. A. Chitra, S. Uma

Abstract


Stock markets are non-linear and chaotic in nature.Though fundamental and technical analysis are used for forecasting the future values of the share prices, as the data involved is voluminous, it is difficult for correct predictions. Neural networks are extensively used by researchers for solving pattern recognition problems. In literature, single level ensemble models are seen. Hence, a two level neural network based ensemble model, “Pattern Prediction Ensemble Model (PAPEM)” is proposed. This model is experimentally found to increase the prediction accuracy of non-linear time series systems. The PAPEM model can be employed in non-linear time series prediction problems like Stock Predictions, Commodity Trading, Forex Trading, Mackey glass, Sunspot, North Atlantic Oscillation Predictions and Electricity Demand Forecasting. Experiments have proved that the performance of the PAPEM model is better than the performance of the individual neural network and single level ensemble models.


Keywords


Cascade Forward neural network, Feed Forward Back Propagation neural network, ensemble, time series prediction

Full Text:

PDF

References


LI Hong-quan and MA Chao-qun, “The Behavior of Stock Prices: Random Walk or Chaotic Dynamics”, Management Science and Engineering, 2006. ICMSE '06.

P.Y. Mok, K.P. Lam and H.S. NG, “An ICA Design of Intraday Stock Prediction Models with Automatic Variable Selection”, IEEE, 2004, 2135 – 2140

Keith V. Nesbitt and Stephen Barrass, “ Finding Trading Patterns in Stock Market Data”,IEEE Computer Graphics and Applications, 2004 pp 45 -55.

Antonio Glaria-Bengochea, Claudio Ordonez-Ureta, Manuel Marchan-saavedra, Nelson Opaza-Medina, “Stock Market Indeces in Satiago de Chile: Forecasting Using Neural Networks”, IEEE, 1996 pp 2172 – 2175.

Xinyu Guo, Xun Liang and Xiang Li, “ A Stock Pattern Recognition Algorithm Based on Neural Networks”, Third International Conference on Natural Computation, IEEE,2007

Lean Yu, Shouyang Wang and Kin Keung Lai,”Mining Stock Market Tendency Using GA-Based Support Vector Machines”, Springer, pp336 -345,2005.

Chiung-Hon Leon Lee, WenSung Chen and Alan Liu, “An Implementation of Knowledge Based Pattern Recognition for Financial Prediction”, IEEE,2004, pp 218 – 223.

Junmyung Lee, Sungzoon Cho and Jinwoo Back, “Trend Detection Using Auto-Associative Neural Networks: Intraday KOSPI 200 Futures”,IEEE,2003 pp 417-420.

Marina Resta, “ATA: The Artificial Technical Analyst Building Intra-day Market Strategies”, IEEE 2000, pp729-732.

Youngohe Yoon and George Swales, “Predicting Stock Price Performance: A Neural Network Approach”, IEEE 1991 pp 156-162.

Fernando Gonzalez Miranda and Neil Burgess, “Intraday Volatility Forecasting for Option Pricing using a Neural Network Approach”,IEEE,1995 pp 31.

Amir Atiya and Noha Talaat,”An Efficient Stock Market Forecasting Model Using Neural Networks”, IEEE,1997, pp 2112-2115.

Norio BABA, “An Intelligent Forecasting System of Stock Price Using Neural Networks”, IEEE, 1992. pp 371-376.

ZHAO Wei and HE Jian-min, “Long Memory Behavior in the Chinese Stock Market Based on Semiparameteric Estimation Method”,Management Science and Engineering, 2006. ICMSE '06, pp 1576-1579.

Mark O.Afolabi and Olatoyosi Olude, “Predicting Stock Prices Using a Hybrid Kohonen Self Organizing Map(SOM), Proceedings of the Hawai International Conference on System Sciences - IEEE 2007.

W.S. Cheung and H.S. Ng. K.P. Lam, “Intraday Stock Price Analysis and Prediction”,IEEE 2000, pp47 – 52.

Piotr Lipinski and Jerzy Korezak, “Early Warning in On-line Stock Trading Systems”,IEEE 2005.

Ot man. M . Ahtiwash, Mohd. Z. Abdulmuin and Siti Fatimah Siraj,”A Neural Fuzzy Logic Approach for Modeling and Control of Nonlinear Systems”,IEEE 2002,pp270-273.

K.P. Lam and P.Y. Mok, “Stock Price Prediction using Intraday and AHIPMI data”, Proceedings of the 9th International Conference on Neural Information Processing (ICONIP’02), Vol.8, 2002.

Kevin A.J. Doherty, Rod G. Adams, Neil Davey and Wanida Penusuwon, “Hierarchical Topological Clustering Learns Stock Market Sectors”, IEEE,2003.

Bing-Hong Wang, Yi-Ming Wai, Shang-jun Ying, Ying Fen, “The Effect of Investment Intent on Stock Market – An analysis based on Cellular Automata”, 2003.

Kin Keung Lai, Lean Yu, Shouyang Wang, and Huang Wei,” A Novel Nonlinear Neural Network Ensemble Model for Financial Time Series Forecasting”, International Conference on Computational Science (1) 790-793, 2006.

Hansen L. K and Salamon P, “Neural network ensembles,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 10, pp. 993-1001,1990.

Simon Haykin,”Feed Forward Neural Networks an Introduction”,Available:http://media.wiley.com/product_data/excerpt/19/04713491/0471349119.pdf


Refbacks

  • There are currently no refbacks.