University Institute of Technology, Burdwan University

About: University Institute of Technology, Burdwan University is a based out in . It is known for research contribution in the topics: Photovoltaic system & Computer science. The organization has 1227 authors who have published 1361 publications receiving 16823 citations.

Fractal analysis of prime indian stock market indices

Abstract: The purpose of the present work is to study the fractal behaviour of prime Indian stock exchanges, namely Bombay Stock Exchange Sensitivity Index (BSE Sensex) and National Stock Exchange (NSE). To analyze the monofractality of these indices we have used Higuchi method and Katz method separately. By applying Mutifractal Detrended Fluctuation Analysis (MFDFA) technique we have calculated the generalized Hurst exponents, multifractal scaling exponents and generalized multifractal dimensions for the present indices. We have deduced Holder exponents as well as singularity spectra for BSE and NSE. It has been observed that both the stock exchanges are possessing self-similarity at different small ranges separately and inhomogeneously. By comparing the multifractal behaviour of the BSE and NSE indices, we have found that the second one exhibits a richer multifractal feature than the first one.

Stock Price Prediction on Daily Stock Data using Deep Neural Networks

Abstract: The price of a stock is volatile and complex in nature which makes its prediction a difficult task. This paper plans to predict the prices of Tata Consultancy Services (TCS) and Madras Rubber Factory Limited (MRF) stocks on a short-term basis. In this paper, a comparative analysis of various Deep Neural Network techniques applied for a stock price prediction application is done. The networks used are pertinent to the problem include Convolutional Neural Networks, Long Short-Term Memory Networks and Conv1D-LSTM. The different neural network models are trained on daily stock price data which includes Open High, Low, and Close price values. These are used to predict the next day closing price. From the last 5 days of data, the prediction is made. Results of different models a recompared with each other. In this paper, a deep neural network Conv1D-LSTM is proposed which is based on the combining of layers of two different techniques – CNN and LSTM top redict the price of a stock. The performance of the models is evaluated using RMSE, MAE and MAPE. These errors in Conv1D-LSTM model are found to be very low compared to CNN & LSTM. For stock price prediction, Conv1DLSTMnetworkisfoundtobeeffective,depending on the nature of stock hyper-parameters may require some variations.

Model Structure Selection for Multivariable Systems by Cross-Validation Methods

Abstract: Using cross-validation ideas, two procedures are proposed for making a choice between different model structures used for (approximate) modelling of multivariable systems. The procedures are derived under fairly general conditions: the ‘true’ system does not need to be contained in the model set; model structures do not need to be nested and different criteria may be used for model estimation and validation. The proposed structure selection rules are shown to be invariant to parameter scaling. Under certain conditions (essentially requiring that the system belongs to the model set and that the maximum likelihood method is used for parameter estimation) they are shown to be asymptotically equivalent to the (generalized) Akaike structure selection criteria.