Big Data Methodology for Credit Card Usage and Account Transaction Based Financial Risk Identification Using Hybrid NBRF Method

Big data is revolutionizing the contemporary economy. Although many economists have employed big data, fewer consider how other people's usage of data impacts market outcomes. This research study begins to investigate how big data can be incorporated into contemporary financial and economic theory. Big data helps participants in the financial sector to make more informed decisions regarding the companies they invest in, among other things. These investment decisions have an effect on the firms' pricing, capital costs, and investment decisions. This research study develops a supervised Bayesian Network model. The Naive Bayes technique is a probabilistic classifier based on the Bayes' Theorem (which you might remember from high school statistics). Even with a small dataset, its simplicity does not make it a bad option because it may provide very accurate predictions (just a few thousand samples). The huge enterprises whose plentiful economic activity creates copious data may also benefit from such data, which is created as a byproduct of economic activity. This research study also investigated and processed Random Forest, gradient boosting, & Hybrid Naive Bayes classifiers to evaluate how well they could predict loan defaults.