Optimizing Forecasting of Dow Jones Stock Index in New York amid Uncertain Global Conditions in 2023: A Combined Approach of ARIMA and Machine Learning Models

Abstract

This research aims to optimize the forecasting of the Dow Jones stock index in New York amid the uncertain global conditions of 2023 using a combined approach of ARIMA and Machine Learning models. This research aims to analyze the movement of the Dow Jones stock index during the uncertainty of the global economic conditions in 2023. The study used a quantitative approach with secondary daily data sourced from yahoo.finance website from january 2020 to may 2023. The current global uncertainty poses challenges to accurate forecasting, and this combined approach offers an effective solution. In this approach, the ARIMA model is employed to capture trends and seasonal patterns in historical data that exhibit stationarity, while the Machine Learning model is used to address more complex patterns and interactions among variables that cannot be handled by ARIMA. The uncertain data of the Dow Jones stock index in New York undergoes preprocessing stages using Machine Learning techniques such as data cleaning, data transformation, feature extraction, and data labeling. The results of the research demonstrate that the combined approach of ARIMA and Machine Learning provides more accurate and reliable forecasts. The integration of the ARIMA and Machine Learning models enables the capture of complex patterns and relationships in the data, resulting in improved forecasting accuracy and valuable insights for investors and market participants in navigating uncertain global conditions. In conclusion, the combined approach of ARIMA and Machine Learning is an effective strategy for optimizing the forecasting of the Dow Jones stock index in New York during uncertain global conditions in 2023. This research contributes to the field of financial forecasting by expanding the understanding of the use of combined approaches to enhance forecasting accuracy and support better decision-making amidst global uncertainty.