Financial markets exhibit intrinsic volatility and stochastic behavior, rendering portfolio evaluation an indispensable component of investment strategy. Traditional platforms frequently suffer from fragmented analytical pipelines, lacking cohesive integration of quantitative metrics, intuitive visualization, and intelligent decision-support mechanisms. This paper introduces an advanced Financial Portfolio Evaluation System that synergizes quantitative finance principles, data analytics, and machine learning to achieve a holistic evaluation of portfolio performance and risk exposure. The proposed system autonomously computes critical indicators—including annualized return, historical volatility, Sharpe ratio, maximum drawdown, and 95% Value at Risk (VaR). Furthermore, it incorporates correlation matrix analysis to evaluate asset diversification and deploys a Random Forest Classifier to categorize portfolio resilience intelligently. Experimental validation using historical market data indicates that the proposed model achieves 98% accuracy and improved risk characterization compared to traditional portfolio assessment methods.

Keywords— Portfolio Management, Risk Analytics, Machine Learning, Value at Risk (VaR), Financial Modelling, Quantitative Finance