Analysis of denoising and signal processing of financial data based on seqARIMA algorithm

As financial data becomes more complex, it's getting harder for traditional time series models to spot signals and make accurate forecasts in a high-noise environment. In this paper, we suggest a way to clean up financial data and process signals using something called the sequential ARIMA algorithm. This should help make stock market forecasts more accurate. The algorithm is based on analyzing gravitational wave data from astronomy. The three-step process—integration, autoregressive, and moving average—is great at dealing with the problems that come from things being non-stationary and noisy in financial data. The main goal of this study is to successfully transfer the sequential ARIMA (i.e., seqARIMA) framework from the field of astronomy to the field of finance and test its applicability in processing high frequency data.