• Version
• Download 7
• File Size 298.51 KB
• File Count 1
• Create Date 9 June 2025
• Last Updated 9 June 2025

Artificial Intelligence in Finance Forecasting

Authors:

Prabhat Dubey, Dr. Annapurna Metta

Introduction

The focus of the study is on the application of Al in the banking sector. This study also examines the effects of its application on forecasting, specifically with regard to the financial market and statistical analysis. It will attempt to analyze a plethora of financial aspects involving economic data, stock prices, and currency rates. Although this study employs advanced methodologies like Gradient Boosting Machines, based on the principles of machine learning, it also uses traditional statistical methods such as ARIMA models and Random Forests. These are not artificial intelligence techniques as Random Forests depending on ensemble leaming from decision trees and ARIMA models utilsied in time series forecasting without involvement of nueral networks. Integration of these provide better results by improving the financial decision making and enhancing forecasting accuracy by 30% and raising accuracy for risk assessment and the ability to predict trading volume by 20%. With the advancement in Al the accuracy and simplicity of financial decision-making will be significantly enhanced. The banking sector confronts some problems. when Artificial Intelligence (Al) comes into the picture. These include the question of privacy, machine bias, and unfairness in social and economic terms. The study articulates those researchers, businessmen, and politician all need to work together to fix those issues so that Al is used rightly in finance by being fair and creative.