Artificial Neural Network for Forecasting Series Data using Multi-Layer Perceptron

International Journal of Research and Scientific Innovation (IJRSI) | Volume VI, Issue V, May 2019 | ISSN 2321–2705

Artificial Neural Network for Forecasting Series Data using Multi-Layer Perceptron

Arpitha K Shetty¹, Pratheksha Rai N², Bhargavi K³

^{1, 2}Assistant Professor, A.J Institute of Engineering and Technology, Kottara Chowki, Mangalore, Karnataka, India
³Assistant Professor, Krupanidhi Degree College, Bengaluru, Karnataka, India

Abstract— Dollar rate prediction is a classification problem, which helps to forecast the next day dollar rate based on the history of dollar rate. The result of the work is the prediction of dollar rate which helps the untrained traders to make decisions. The proposed work is to forecast the dollar rate series data for various applications by using neural network. The advantage of using neural network is that it will predict the future even in the presence of hidden data. The dollar rate prediction using Multi-Layer Perceptron (MLP) model is proposed. The dollar rate prediction problem is built by using the mathematical operations, so that this project is implemented in R language.

Keywords— Data mining, Artificial neural network, Neural Network Training, Neural Network Testing, Multi-Layer Perceptron (MLP) model

I. INTRODUCTION

Predicting the dollar exchange rate is a complex task, due to consequences of unsystematic changes in behaviour of a dollar rate time series. In order to predict the dollar rate we need to have the knowledge of marketing and data mining techniques. Predicting the dollar exchange rate is a complex task, due to consequences of unsystematic changes in behaviour of a dollar rate time series. In recent years, the concept of neural networks has been an emerging technology among them. The Artificial Neural Network (ANN)[1] is built based on association of human brain biological neuron system. Neuron systems are formed from trillions of neurons these will exchange succinct electrical pulses called action potentials. These biological structures are adopted to the computer algorithm formally called Artificial Neural Networks. The challenges of prediction are addressed by implementing this work in R language. It is a software environment and programming language for statistical computing and graphics widely used among statisticians and data miners for data analysis and developing statistical software . In this process, we are using the Neural Networks for prediction.

Read More