Indian Stock Market Prediction Using Differential Evolutionary Neural Network Model
Journal Title: International Journal of Electronics Communication and Computer Technology - Year 2012, Vol 2, Issue 4
Abstract
This paper presents a scheme using Differential Evolution based Functional Link Artificial Neural Network (FLANN) to predict the Indian Stock Market Indices. The Model uses Back-Propagation (BP) algorithm and Differential Evolution (DE) algorithm respectively for predicting the Stock Price Indices for one day, one week, two weeks and one month in advance. The Indian stock prices i.e. BSE (Bombay Stock Exchange), NSE, INFY etc. with few technical indicators are considered as input for the experimental data. In all the cases, DE outperforms the BP algorithm. The Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) are calculated for performance evaluation. The MAPE and RMSE in case of DE are found to be very less in comparison to BP method. The simulation study has been done using Java-6 and NetBeans.
Authors and Affiliations
Puspanjali Mohapatra (Asst. Prof)| Dept of Computer Science and Engineering IIIT Bhubaneswar Bhubaneswar, India, Alok Raj| Dept of Computer Science and Engineering IIIT Bhubaneswar Bhubaneswar, India, Tapas Kumar Patra (Reader)| Dept of Instrumentation & Electronics Engineering College of Engineering Technology Bhubaneswar, India
Keywords
Related Articles
- EP ID EP8294
- DOI -
- Views 324
- Downloads 31
A High Capacitive and Confidentiality Steganography Using Private key
Steganography and Steganalysis are two important areas of research that involve a number of applications. These two areas of research are important especially when reliable and secure information exchange is required. To...
Advanced Composite Communication System
Advanced Composite Communication System (ACCS) is the new generation of composite communication systems for on board NAVAL ships. The secret form of communication in between ship to ship can be done from this system. Her...
Design Of Digital FIR Filter Using LUT Based Multiplier
In FPGA design the implementation fir filters for DSP applications place an important role. The FPGA area is mainly decided by the number of LUT’s occupied. Hence for any design if the optimisation for the area is car...
An Error Notification Method for a High Speed Serial Communication on FPGA
In parallel communication the cost as well as complexity of the system increases due to simultaneous transmission of data bits on multiple wires. Serial communication alleviates this drawback and emerges as effective...
Area Efficient and A High Bit Rate Serial-Serial Multiplier With On-the-Fly Accumulation by Asynchronous Counters
Traditional Serial-Serial multiplier addresses the high data sampling rate. It is effectively considered as the entire partial product matrix with n data sampling cycle for n×n multiplication function instead of 2n cycle...