The extensive usage of time series analysis and forecasting in many realworld applications makes it critically important. The stock market is a dynamic and significant component of modern financial markets. In the last ten years, there has been a surge of interest among academics in using stock market time series data for analysis and prediction. There is a lot of interest in the question of how to label financial time series data in order to assess the efficacy of machine learning models for making predictions and, ultimately, to calculate the returns on investments. On the other hand, non-linearity and apparent short-term unpredictability characterise most financial time series data. This research proposes a novel ARIMA model that uses continuous trend labelling to forecast the behaviour of the stock market. One method for forecasting time series values is the ARIMA model, which stands for Auto Regressive Integrated Moving Average. The continuous trend aspects of financi

The extensive usage of time series analysis and forecasting in many realworld applications makes it critically important. The stock market is a dynamic and significant component of modern financial markets. In the last ten years, there has been a surge of interest among academics in using stock market time series data for analysis and prediction. There is a lot of interest in the question of how to label financial time series data in order to assess the efficacy of machine learning models for making predictions and, ultimately, to calculate the returns on investments. On the other hand, non-linearity and apparent short-term unpredictability characterise most financial time series data. This research proposes a novel ARIMA model that uses continuous trend labelling to forecast the behaviour of the stock market. One method for forecasting time series values is the ARIMA model, which stands for Auto Regressive Integrated Moving Average. The continuous trend aspects of financi