The finance domain increasingly relies on intelligent systems to navigate volatile markets and support data driven decisions. This project develops Lursen Finance, a machine learning based smart trading recommendation app that analyzes historical and real time market data including prices, volumes, and technical indicators to uncover patterns and trends. The problem statement highlights how manual trading suffers from emotional biases, incomplete information, and time constraints, often resulting in losses, while many platforms offer only raw data without actionable insights. The proposed method employs preprocessing, feature extraction such as moving averages, RSI, and MACD, and predictive models like Random Forest and LSTM for trend forecasting, followed by a recommendation engine that generates buy, sell, or hold signals with risk assessments. Key evaluation metrics include accuracy, Mean Absolute Error MAE, Root Mean Square Error RMSE, and precision and recall for recommendations. Experimental results demonstrate improved prediction accuracy and reduced risk exposure compared to baselines. In conclusion, Lursen Finance provides an accessible, automated tool that enhances trading efficiency, minimizes human error, and empowers retail investors with timely, intelligent recommendations.
Arun Kumar, Subham Upadhyaya, Yudish, Maheshwaran, Dr. B. Monica Jenefer (Mon,) studied this question.