Systematic Analysis of Predictive Modeling Methods in Stock Markets

Abstract

The main aim of the proposed study is to develop a hybrid temporal model that provides learning pattern for classifying the temporal data. These results are unusual, which is in contrast with the Hidden Markov Models (HMM). The system is evaluated in terms of the capabilities of a hybrid learning algorithm, which is applied over the temporal data. Performance of the hybrid algorithm depends entirely on the dynamic data, which is fed into the system. The data fitting is an important concern, to find, analyse and predict the future instance. Hence, the difficulty in making a hybrid algorithm to fit the dynamic data is increasing, however, the data fits in better proportion over the expert system. An expensive research is required to build the required module for data pre-processing, analyzing and prediction. Also comparing such systems’ performance with the conventional schemes is required to prove its effectiveness. The study aims at developing a most generic artificial neural network hybrid algorithm, which predicts well the stock market data without the knowledge of past outputs. Hence, the end user does not trouble the recognition system and that is regarded as the virtues of soft computing tools

A Market Analysis of Potential Investment in Green Bonds and it’s Contribution to Sustainable Development

“…We examined the advantages of green bond placements for companies and the relevance of green bonds in changing the present economic system into one that is more ecologically friendly and better able to combat climate change, according to the report's authors (Gautam & Mittal, 2022b;Verma et. al.…”