Adaptive Composite Market Volatility Index (CMVI) for Enhanced Stock Price Forecasting

Investors trying to control portfolios and create sensible trading plans depend on accurate stock price forecasts. Many times, depending just on past stock price data, traditional forecasting techniques can limit predicted accuracy. This work presents an advanced method by combining several technical indicators and financial ratios into a Composite Market Volatility Index (CMVI), therefore addressing this difficulty. T his index considers the special qualities of individual stocks by using adaptive weighting, tuned by grid search. To give a whole picture of market volatility, the CMVI combines important indicators such as Moving Average Convergence Divergence (MACD), Relative Strength Index (RSI), Bollinger Bands (BB), and financial ratios including Price-to-Earnings Ratio (P/E). Using a Long Short-Term Memory (LSTM) network, which is especially successful for temporal dependencies in financial data, we use this adaptive CMVI to stock price prediction. Reduced Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) all point to notable forecasting performance gains in the suggested approach. Empirical data confirm t hat our method provides better prediction accuracy and a more thorough understanding of market dynamics.