FINANCIAL RISK ANALYTICS OF INDIAN SMALL AND MID-CAP STOCKS: A QUANTITATIVE APPROACH

Abstract

This research project investigates the financial risk landscape of Indian small- and mid-cap (SMID) stocks using a multidimensional and quantitative framework. The study emerges from the increasing vulnerabilities faced by SMID firms due to their limited financial buffers, lower institutional coverage, and greater exposure to macroeconomic shocks compared to large-cap companies. The goal is to develop an integrated, data-driven risk assessment system to identify early signs of financial distress and help stakeholders make informed decisions. The study evaluates three primary dimensions of financial risk: 1. Credit Risk, using: o Altman Z-Score o Debt-to-Equity Ratio o Interest Coverage Ratio o Debt-to-Asset Ratio 2. Liquidity Risk, assessed through: o Current and Quick Ratios o Working Capital to Sales Ratio o Cash Conversion Cycle o Composite score of above 3 factors 3. Market Risk, analyzed via: o Beta (Systematic Risk) o Annualized Return Volatility o Sharpe and Treynor Ratios suggesting diversification & efficient & underperforming stocks o GARCH models to understand volatility clustering using K-means Clustering vi The project employs machine learning techniques, particularly the Random Forest algorithm, to classify companies into Low, Medium, and High-Risk categories. Python and Excel were used for data handling, model development, and analysis. The model achieved 89% accuracy, highlighting strong predictive capability, especially for identifying Low and High-Risk firms. The dataset includes 140 non-financial companies from the Nifty Midcap 100 and Nifty Smallcap 100 indices, analyzed over a single financial year. Sector-wise breakdowns reveal that telecom, power, and healthcare sectors are disproportionately represented in high-risk zones, while FMCG, IT, and capital goods sectors are financially healthier. Mid-cap firms, in general, showed better financial robustness than small-cap counterparts. Key findings indicate:  88–90% of firms are in the "Safe" zone per Altman Z-score, but a critical minority remains in the "Distress" zone.  Small-cap firms exhibit higher liquidity and credit risk.  Risk & Return trade-off has been shown using Sharpe & Treynor ratio analysis  GARCH models confirm volatility clustering, especially in sectors sensitive to macroeconomic trends. The study provides actionable insights for:  Investors: Improved portfolio decisions by flagging risky stocks.  Lenders and Analysts: Early warning signals for credit assessments.  Policymakers and Regulators: Sector-specific risk management strategies. By combining traditional ratio analysis, machine learning classification, and econometric modeling, the research offers a holistic financial risk assessment framework tailored for the Indian SMID segment. It bridges the gap between academic theory and real-world financial risk management, contributing meaningfully to the fields of investment analytics and systemic risk detection.