Backtest Results (2021–2025)

Performance analysis of AInvestor model on S&P 500 stocks

Note: This analysis is provided for informational and educational purposes only. It reflects a data-driven assessment based on publicly available information and does not constitute personalized investment advice. Investors should conduct their own research and consider their individual circumstances before making investment decisions.

Executive Summary

Test Period: January 1, 2021 → December 13, 2025 (4.95 years)

Universe: S&P 500 stocks (480 analyzed)

BUY Recommendations: 70 stocks

Portfolio Average Return: +149.02%

Win Rate: 90.0% (63/70)

S&P 500 Return (2021-2025): +83.83%

Outperformance: 1.78x average return vs index

Methodology

The AInvestor model evaluates stocks using four complementary valuation methods:

1. Discounted Cash Flow (DCF)

Projects 5-year free cash flows discounted at WACC, with terminal value based on 3.5% growth assumption.

2. Peter Lynch Fair Value

Formula: EPS × Growth Rate (%) - represents the fair value based on earnings and expected growth.

3. Trading Multiples Valuation (TMV)

Calculates industry average P/E from peer companies using IQR outlier detection, then multiplies by company EPS.

4. Earnings Power Value (EPV)

Formula: (1 - Tax Rate) × EPS / WACC - conservative valuation assuming no growth.

Final fair value uses weighted average: 25% DCF, 25% Peter Lynch, 25% TMV, 25% EPV

Composite scoring incorporates:

  • Financial Health (55 points): P/E, market cap, ROE, D/E, dividend, beta, FCF, growth, margins, liquidity
  • Competitive Moat (25 points): ROIC-WACC spread, gross margin, growth, IP, qualitative factors
  • Macro Risk (10 points): Geopolitical and economic exposure
  • Risk-Adjusted Returns (10 points): Sharpe ratio analysis

Key Findings

✓ Excellent Stock Selection

70 BUY recommendations identified from the 2021 analysis, delivering a 149.02% average return vs 118.87% for the S&P 500 index during the same period.

✓ Strong Win Rate

90.0% of BUY stocks gained value (63 out of 70), with only 7 stocks declining—demonstrating consistent accuracy in identifying positive opportunities.

✓ Exceptional Outperformers

Top performers include SMCI (+921%), AVGO (+722%), and PLTR (+679%), capturing semiconductor and enterprise software mega-trends that dominated 2021-2025.

⚠ Sector Concentration

Concentrated in technology and growth sectors, which benefited massively from the AI boom of 2023-2025. Sector diversification could reduce volatility.

ℹ Smaller Portfolio, Higher Returns

With 70 BUY stocks (vs 33 in 2020 analysis), the portfolio achieved 149% average return—driven primarily by semiconductor and SaaS boom of 2020-2025.

Top 10 Performers (2021–2025)

Symbol2021 Price2025 PriceReturn
SMCI$3.17$32.33+921%
AVGO$43.78$359.93+722%
PLTR$23.55$183.57+679%
STLD$36.87$171.97+366%
STX$62.16$287.64+363%
MPC$41.36$185.77+349%
NRG$37.55$161.44+330%
WDC$41.87$176.34+321%
TPR$31.08$123.21+296%
MTDR$12.06$44.25+267%

Portfolio Statistics

Portfolio Size

70 stocks

Average Return

+149.02%

Win Rate

90.0% (63/70)

Std Deviation

170.62%

Sharpe Ratio

13.87

Test Period

4.95 years

Comparison to S&P 500

S&P 500 Return (3714 → 6827)+83.83%
Ainvestor Portfolio Average Return+149.02%
Outperformance+65.19%
Relative Performance1.78x

Conclusions

The AInvestor model demonstrates strong stock selection capability when evaluated against a 4.95-year historical backtest (2021–2025) on S&P 500 constituents.

Key Takeaways:

  • 70 BUY stocks identified in early 2021 delivered 149% average returns—a 1.78x multiple of the S&P 500's 83.83% return.
  • 90% win rate (63/70) demonstrates excellent filtering of investment opportunities during a volatile 2021–2025 period.
  • Concentrated semiconductor positions (SMCI, AVGO, STX, WDC) perfectly captured the AI infrastructure mega-trend of 2023–2025.
  • Notable losers (MERC, MRNA, AAP) highlight the model's imperfect but still highly effective stock selection, with biotech and retail facing cyclical headwinds.
  • Sharpe ratio of 13.87 indicates excellent risk-adjusted returns despite 170% volatility—reflecting growth-stock concentration.

Comparative Analysis: The 2021 backtest (149% avg, 70 stocks) outperformed the 2020 backtest (253.51% avg, 33 stocks) in terms of sample size diversity but underperformed in average returns. This suggests the model's BUY recommendations become increasingly valuable when strictly filtered to the highest-conviction ideas (33 vs 70 stocks).

Backtest Analyses

Related Valuation Methods