Data Analysis using Artificial Neural
Network for Business Prediction
Under the guidance of
Ms. Roohi Sille
of Computer Science and Engineering
Centre for Information
Computer Science and Engineering,
PETROLEUM AND ENERGY STUDIES
for Information Technology
School of Computer Science and Engineering
of Petroleum & Energy Studies, Dehradun
Project Proposal Approval Form (2017-18)
Analysis using Artificial Neural Network for Business Prediction
Be it the customer satisfaction or the setup of new
start up, Data Analysis plays a vital role in almost every field. One such
field of Data Analysis is of Business Prediction. There are various techniques
to perform this out of which one such possible method is the use of Artificial
Neural Network. A Neural Network model
can be easily used for time series prediction of business. By using multi-layer
perceptron neural network is built through which more accurate prediction
values can be obtained which would in turn help for better forecasting.
ANN, Neural Network, Data Analysis, Business,
The project entitled Data
Analysis using Artificial Neural Network for Business Prediction is to analyze the
past data and predict the future demand by forecasting it beforehand for
various business firms.
The brain is an enormously
complex system in which distributed information is processed in parallel by
mutual dynamical interactions of neurons. It is still difficult and
challenging, to understand the mechanisms of the brain. The importance and
effectiveness of brain-style computation has become a fundamental principle in
the development of neural networks. There are three different research areas concerning
neural networks. One is the experimental based on physiology and molecular
biology. The second area is engineering applications of neural networks
inspired by the brain-style computation where information is distributed as
analog pattern signal, parallel computations are dominant and learning guarantees
flexibility and robust computation. The third area is concerned with
mathematical foundations of neuro-computing, which searches for the fundamental
principles of parallel distributed information systems with learning
capabilities. Statistics has a close relation with the second application area
of neuronal networks. This area has opened new practical methods of pattern recognition,
time series analysis, image processing, etc. 1
The study aims to
incorporate the Artificial Neural Network in business prediction to discover
various variables which influence the business performance. The combined effect
of each of the variable would help in obtaining values required for forecasting
of demand. The process requires inculcating the skills of statistics in ANN so
that desirable predictions can be made.
To design a system that would be able to perform
analysis of data for computing future predictions for various business for
demand of goods or services based on past demand information.
Artificial Neural Networks (ANN)
have received a great deal of attention in many fields of engineering and
science. Inspired by the study of brain architecture, ANN represent a class of nonlinear
models capable of learning from data. ANN have been applied in many areas where
statistical methods are traditionally employed. They have been used in pattern
recognition, classification, prediction and process control.
Business Prediction is the concept
of analyzing past data or patterns in order to predict or forecast future possibility.
The process focuses on finding methods to benefit individual business firms by
performing statistical techniques. Historic data to be forecasted is gathered,
divided for evaluation and then used to develop model for finding desirable
1. To implement Data Analysis in ANN for Business
prediction of goods and services.
2. Deployment of proper functional software for Forecast
using statistical computation.
for the project is gathered.
? A neural network is set up for data analysis.
? Business Prediction techniques are explored and
most suitable techniques is chosen.
Input is taken
considering the technique chosen.
correction is done until desirable output is fetched.
and debugging is carried out.
? Documentation is done.
Code to write source code.
system platform like Windows or Linux.
MS Word, MS
PowerPoint for documentation.
1 M.Y.I. Idris, Y.Y. Leng, E.M. Tamil, N.M. Noor and Z.
Razak, 2009. Car Park System: A
Review of Smart Parking System and its Technology. Information
Technology Journal, 8: 101-113.
2 Rathi A, Aware A, Shiradkar N, Kothekar
M. Self parking car : Electronic design project.
Centre for Information