⚠️ Educational Research Notice
This methodology page describes our educational research framework. All backtests are historical simulations and neither constitute research nor investment advice. Content is published under the proviso to Regulation 2(1)(l) of the SEBI (Investment Advisers) Regulations, 2013 (widely available electronic medium) and Regulation 4(a) (general comments on market trends). T. Desai and BacktestIndia are not responsible for investment decisions based on this methodology. Consult a SEBI-registered Investment Adviser before investing.
1. What is Backtesting?
Backtesting is the process of applying a trading or investment strategy to historical data to see how it would have performed in the past. It's a fundamental tool in quantitative finance for understanding:
- Whether a strategy had positive returns historically
- Maximum drawdown (peak-to-trough decline) the strategy experienced
- How long recovery from losses took
- Risk-adjusted returns (Sharpe ratio, Sortino ratio)
- Strategy behavior across different market conditions (2008 crash, COVID, bull markets)
Critical Distinction: Backtesting shows what happened in the past. It does NOT predict what will happen in the future. Markets change, correlations break down, and past winners often become future losers.
2. Data Sources & Coverage
Data Provider
All historical price and fundamental data is sourced from EODHD Financial APIs, a professional-grade financial data provider used by quantitative researchers worldwide.
Time Period
- Start date: December 2006
- End date: June 2025 (updated quarterly)
- Total period: 18.5 years of NSE data
Stock Universe
- 1,700+ NSE-listed stocks including delisted companies
- Covers companies across all sectors and market caps
- Survivorship bias minimized: Includes companies that went bankrupt, were suspended, or delisted (housing finance firms, mid-sized private banks, real estate developers, IT firms, etc.)
3. Factor Investing Framework
BacktestIndia's methodology is grounded in academic factor investing research, pioneered by Nobel laureate Eugene Fama and Kenneth French.
Core Factors We Test
- Value: Stocks with low price-to-earnings (PE) or price-to-book (PB) ratios
- Momentum: Stocks with strong recent price performance (6-12 month returns)
- Quality: Stocks with high return on equity (ROE), low debt, stable earnings
- Low Volatility: Stocks with lower-than-average price fluctuations
- Size: Small-cap vs large-cap performance differences
Academic References
- Fama, E. F., & French, K. R. (1992). "The Cross-Section of Expected Stock Returns." Journal of Finance
- Jegadeesh, N., & Titman, S. (1993). "Returns to Buying Winners and Selling Losers." Journal of Finance
- Ang, A., Hodrick, R. J., Xing, Y., & Zhang, X. (2006). "The Cross-Section of Volatility and Expected Returns." Journal of Finance
- Novy-Marx, R. (2013). "The Other Side of Value: The Gross Profitability Premium." Journal of Financial Economics
4. Why We Don't Name Specific Stocks
BacktestIndia never shows individual stock names in backtest results—in free tier, premium tier, or any mode. This is a deliberate choice for regulatory prudence.
Regulatory Reasoning
Under SEBI (Securities and Exchange Board of India) regulations, providing specific stock recommendations requires SEBI registration as an Investment Adviser or Research Analyst. BacktestIndia is neither:
- We are not a SEBI-registered Investment Adviser
- We do not provide personalized portfolio recommendations
- We do not assess your risk tolerance, financial situation, or suitability
- All strategies are 100% user-defined—YOU choose the parameters
What You Get Instead
Instead of stock names, you receive aggregate portfolio performance:
- Total portfolio CAGR (compound annual growth rate)
- Maximum drawdown and recovery time
- Year-by-year returns
- Risk metrics (Sharpe ratio, Sortino ratio, volatility)
- Tax-adjusted returns (LTCG/STCG calculations)
- Comparison to Nifty 50 benchmark
The Insight That Matters: The value of backtesting isn't in getting a list of stocks to buy today. It's in understanding whether YOUR factor-based rules created a portfolio that historically withstood crashes, recovered faster, and compounded consistently. That conviction helps you stick with a systematic approach during inevitable drawdowns.
5. Known Limitations of Backtesting
Every backtest has limitations. We transparently acknowledge ours:
Data Quality
- Historical data may contain errors, corporate action adjustments, or missing values
- Fundamental data (PE, ROE) is subject to restatements and accounting changes
- Delisted stock data may be incomplete for companies that failed before 2006
Survivorship Bias
- While we include delisted companies, we cannot perfectly capture all bankruptcies
- Stocks that delisted before December 2006 are not in our dataset
Look-Ahead Bias
- Fundamental data (PE, ROE) is quarterly; we use point-in-time data to avoid look-ahead bias
- However, corporate actions and index reconstitutions are implemented as of effective dates
Transaction Costs
- We model 0.11% per trade (brokerage + STT + GST) and 0.05% slippage
- Actual costs vary by broker, trade size, and market liquidity
Market Impact
- Our backtests assume you can buy/sell at end-of-day prices without moving the market
- For large portfolios or illiquid stocks, this assumption breaks down
Regime Change
- Market structure changes (algo trading, retail participation, SEBI regulations) over 18 years
- Factor performance in 2006-2015 may not repeat in 2025-2035
6. How Our Backtesting Engine Works
Step-by-Step Process
- User defines strategy parameters (via chatbot or custom mode)
- Backend engine loads historical data from EODHD APIs
- Monthly rebalance: On first trading day of each month (or quarterly/annually):
- Filter universe by user criteria (market cap, PE, PB, ROE, momentum, volatility)
- Rank stocks by selected factor
- Select top N stocks (user-defined portfolio size)
- Apply weighting scheme (equal weight, value weight, inverse volatility weight)
- Simulate trades: Calculate portfolio value after transaction costs and slippage
- Track daily returns: Mark-to-market portfolio using end-of-day prices
- Apply taxes: Calculate LTCG (12.5%, holdings >1 year) and STCG (20%, holdings <1 year)
- Compute metrics: CAGR, Sharpe ratio, Sortino ratio, max drawdown, recovery time
Tax Modeling
Based on India's Finance Act 2024:
- LTCG: 12.5% on gains from stocks held >1 year (₹1.25L exemption per year)
- STCG: 20% on gains from stocks held ≤1 year
- Securities Transaction Tax (STT): Embedded in brokerage estimate
7. Backtesting vs Prediction
✅ What Backtesting IS
- Historical simulation
- Educational analysis
- Understanding past risks
- Testing strategy logic
- Learning from market cycles
❌ What Backtesting is NOT
- Future performance prediction
- Investment recommendation
- Guarantee of returns
- Risk-free strategy
- Substitute for SEBI-registered advice
Key Principle: Past performance does not guarantee future results. Markets change. Correlations break. Regulations shift. Use backtesting to understand historical behavior, not to predict future outcomes.
8. Our Educational Mission
BacktestIndia exists to democratize access to quantitative investing education for Indian retail investors. Our goal is to help you:
- Understand how systematic factor strategies work in Indian markets
- Test your own investment ideas using real historical NSE data
- Learn from past market cycles (2008 crash, COVID crash, bull markets)
- Build conviction in rule-based investing through data analysis
- Appreciate the difference between backtesting and prediction
We are not advisers, not portfolio managers, not fortune tellers. We are educators providing tools for self-directed learning.