• Dr. Prakasha S
• Amoda Hegde
• Dhruthi S
• Ghanavi Arun
• Gowri KS

The improvements in machine learning and deep learning algorithms have enabled new opportunities for predictive modelling in highly volatile financial markets. This project aims to statistically examine the performance of ML methods for risk management in financial markets. By leveraging a combination of classical and modern algorithms, the project seeks to mitigate financial risk and improve accuracy of stock price forecasts movements and trends. The study explores machine learning models: Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), K-Nearest Neighbours (KNN), ARIMA and deep learning models: Long Short-Term Memory (LSTM), Gated recurrent units (GRU). The effectiveness of these models will be compared using performance indicators like Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), R-squared values and other statistical methods. The research will focus on financial datasets including stock price data (open, high, low, close prices), technical indicators and macro-economic indicators to predict stock market trends. Additionally, the implementation of ensemble methods like Extreme Gradient Boosting (XGBoost) will further enhance the prediction capabilities, especially for highly volatile stock markets.

Machine Learning, Deep Learning, Statistical methods, LSTM, KNN, GRU, ARIMA, Error metrics

"Statistical Examination of Machine Learning Algorithms for Risk Management in Financial Markets", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 11, page no.g167-g171, November-2024, Available :http://www.jetir.org/papers/JETIR2411613.pdf

"Statistical Examination of Machine Learning Algorithms for Risk Management in Financial Markets", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 11, page no. ppg167-g171, November-2024, Available at : http://www.jetir.org/papers/JETIR2411613.pdf