Scribd
Upload
46 views7 pages

Rohit Oberoi: Mba 3 Semester

This document discusses forecasting the BSE Sensex stock market index in India using a neural network model. It will collect daily stock market data from 2013-2014 as input variables to train the neural network and then forecast future closing values. The objectives are to form and train a neural network model on BSE Sensex input data and check the accuracy of forecasts against actual closing values. Globalization makes accurate stock market prediction more challenging, and neural networks can detect non-linear patterns in multi-dimensional data better than linear methods.

Uploaded by

Rohit Oberoi
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
46 views7 pages

Rohit Oberoi: Mba 3 Semester

This document discusses forecasting the BSE Sensex stock market index in India using a neural network model. It will collect daily stock market data from 2013-2014 as input variables to train the neural network and then forecast future closing values. The objectives are to form and train a neural network model on BSE Sensex input data and check the accuracy of forecasts against actual closing values. Globalization makes accurate stock market prediction more challenging, and neural networks can detect non-linear patterns in multi-dimensional data better than linear methods.

Uploaded by

Rohit Oberoi
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 7

Rohit Oberoi

MBA 3rd semester

Introduction
A neural network is a massively parallel distributed processor that has a natural propensity for storing experiential knowledge and making it available for use. It resembles the brain in two respects: Knowledge is acquired by the network through a learning process Interneuron connection strengths known as synaptic weights are used to store the knowledge.

OBJECTIVES
To form and train a neural network model based upon input variables from stock market (BSE Sensex). To forecast the closing values of each day of BSE Sensex starting from 13th September 2013 till 31st January 2014 based upon input variables from stock market (BSE Sensex).

To check the accuracy of the forecasted values.

Forecasting BSE Sensex using Neural Network

Need and Significance


Globalization has made the stock market prediction (SMP) accuracy more challenging and rewarding for the researchers and other participants in the stock market. The principal strength with a neural network is its ability to find patterns and irregularities as well as detecting multi-dimensional non-linear connections in data. If other methods such as linear programming are used, there is a problem of multi co linearity i.e the factors there are inter dependent and hence cannot give accurate results.

Helps to predict whether it is best to buy or hold or sell shares of stock market.

Forecasting BSE Sensex using Neural Network

METHODOLOGY
Data Collection

Secondary Data from BSE Website

Time Frame of Variables Variables Opening Value of BSE Sensex Maximum Value of BSE Sensex Minimum Value of BSE Sensex Closing Value of BSE Sensex Time frame Daily Daily Daily Daily

No. of Shares traded


Forecasting BSE Sensex using Neural Network

Daily
5

METHODOLOGY

Tools of Analysis

Neuro XL Predictor

Forecasting BSE Sensex using Neural Network

Forecasting BSE Sensex using Neural Network

You might also like