Smart Trading in NIFTY-50: ML with MA, RSI & Volume Analysis

Hereis a complete machine learning framework developed to evolve the automated trading strategies derived for the NIFTY-50 index constituents using past stock market data from the National Stock Exchange (NSE) of India from 2000 up to 2021. The research integrates popular traditional technical indicators such as Moving Averages (both Simple and Exponential), Stochastic Relative Strength Index (Stochastic RSI), and Price-Volume based analysis techniques with modern machine learning approaches for better predictive power of the fifty stocks listed under India's premier stock market index. The modeling approach involves the supervised learning paradigms of Support Vector Machines (SVM), Random Forest (RF), and Long Short-Term Memory (LSTM) on the large NIFTY-50 dataset consisting of daily trading data with features such as Open, High, Low, Close prices, Volume, VWAP (Volume Weighted Average Price), Turnover, and Deliverable Volume for major Indian corporations including Reliance Industries, Tata Consultancy Services, HDFC Bank, Infosys, ICICI Bank, and other blue-chip companies spanning diverse sectors. The empirical study employs a huge historical market data set of over two decades covering various market cycles consisting of dot-com bubble, global financial crisis, and recent market volatilities. The framework scores quite higher in trend classification and signal generation as compared to conventional technical analysis methods with a major focus on the inherent characteristics of Indian equity markets and sectoral representation within the NIFTY-50 index encompassing technology, financial services, energy, pharmaceuticals, and consumer goods sectors. Amongst the key findings, machine learning methods coupled with traditional technical indicators are shown to significantly enhance the performance of trading strategies for NIFTY-50 stocks with the LSTM model being very well suited to capturing long-term dependencies in price movements, thus providing useful intelligence in algorithmic trading systems and portfolio management.