Stock Price Prediction of IT Midcaps Companies Using ML Models

This research investigates the influence of past quarterly results data on the share price movements of Indian IT midcap companies. Leveraging a dataset comprising quarterly financial reports of ten prominent midcap companies, this study employs a multi-faceted approach to stock price prediction. The dataset was obtained from trusted sources in the financial data domain, ensuring the reliability and comprehensiveness of the data. First, we explore the correlation between various financial parameters found within the quarterly reports. Our findings reveal noteworthy associations, highlighting the impact of key financial metrics such as Operating Profit Margin (OPM %), Expenses, Interest, Depreciation, and Tax Percentage on overall financial performance. Next, employing multiple linear regression, we assess the predictive power of these metrics on stock prices. Our analysis uncovers valuable insights, indicating that variables such as Market Cap, Price-to-Earnings (P/E) ratio, Face Value, Net Profit and Earnings Per Share (EPS) significantly affect share prices. Nevertheless, several other metrics, including Sales, Expenses, and Operating Profit, do not exhibit statistically significant relationships with stock prices. Subsequently, we employ Multiple Linear Regression and Random Forest models to predict stock prices based on past quarterly results data. Our predictions vary in accuracy across the selected companies Discrepancies in predictive performance underscore the importance of feature selection, data quality, and market dynamics in refining our predictive models.