A combined PCA-MLP model for predicting stock index

Authors:
K. V. Sujatha;S. Meenakshi Sundaram
Affiliations:
Sathyabama University, Jeppiaar Nagar, Chennai, Tamilnadu, India;Sathyabama University, Jeppiaar Nagar, Chennai, Tamilnadu, India
Venue:
Proceedings of the 1st Amrita ACM-W Celebration on Women in Computing in India
Year:
2010

Citing 6
Cited 0

Utilization of Neural Networks & GAs for Constructing Reliable Decision Support Systems to Deal Stocks

IJCNN '00 Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 5 - Volume 5
Automatic Estimation of Stock Market Forecasting and Generating the Corresponding Natural Language Expression

ITCC '04 Proceedings of the International Conference on Information Technology: Coding and Computing (ITCC'04) Volume 2 - Volume 2
Predicting Stock Prices Using a Hybrid Kohonen Self Organizing Map (SOM)

HICSS '07 Proceedings of the 40th Annual Hawaii International Conference on System Sciences
Statistical models of KSE100 index using hybrid financial systems

Neurocomputing
Stock market prediction of S&P 500 via combination of improved BCO approach and BP neural network

Expert Systems with Applications: An International Journal
Mining stock market tendency using GA-Based support vector machines

WINE'05 Proceedings of the First international conference on Internet and Network Economics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Predicting stock prices is a challenging and daunting task due to the complexity of the stock market. In this study, a combined model is proposed to explore market tendency. Prediction of daily closing price using the variables daily opening price, high, low and volume of transaction is done. In this approach, the predictor variables are multi collinear in nature which is overcome by using Principal Component Analysis (PCA) which resulted in a new set of independent variables that are taken for predicting the stock prices using Multilayer Layer Perceptron (MLP) model. To evaluate the prediction ability of the model, we compare the performance of models using a common error measure. The empirical results reveal that the proposed approach is a promising alternate to stock market prediction.