Skip to main content
No. of Recommendations: 13
Screen: Pick 20 random stocks, attempting to match the S&P 1500 equal weight 5 year CAGR.

Matching the S&P 1500 on average is easy enough. I was more interested in how much scatter there would be in the results. Holding a single portfolio using this screen, I would expect a 3.6% standard deviation in 5 year CAGR.

The S&P 1500 looks for profitable U.S. companies, and so those are the first 2 steps in the screen {Profitable2021}. Turnover is limited by using "hold while passing step0". To use the screen, one would check holdings once a quarter, and sell any with negative EPS. Average CAGR and GSD are close to the benchmark. Standard deviation of {Profitable2021} CAGR over 27 years was 1.2.

Screen             CAGR  GSD   MDD
SP1500EqualWeight 12.3 22.9 -60
Profitable2021 12.8 21.7 -56

from 19941003 to 20210618

Define {Profitable2021}
step0: [PE] > 0
step1: [Security Type] == 11
step2: [Mkt Days Since Security Opened] >= 253
step3: [Average dollar-volume over 63 days] >= 1000000
step4: [Q1End] > 0
step5: [[Mkt Date as Ordinal] - [Q1End]] <= 252
step6: [1*[Q1End] - 252 + 1*[Mkt Days Since Investment Opened] - 1*[Mkt Date as Ordinal]] >= 0
step7: [RandomA] Top 20
Hold while passing step0
Frictional loss of 0.4% applied to all sales
Rebalance to equal weight every 63 mkt days

Excess return for the 63 portfolios (rolling 5 year CAGR minus benchmark) averaged 0.8% since 1994, with a 3.6% standard deviation. Over the most recent 5 years, {Profitable2021} CAGR for the 63 portfolios ranged from 8 to 23. {SP1500EqualWeight} CAGR ranged from 15 to 17. Using three ETFs, CAGR was 14.9 (RSP 14.92, EWMC 13.73, EWSC 15.92).

RandomA varies both daily and by stock, and so each of the 63 portfolios should be different. The parameter 179 was chosen out of 50 values (from 101 to 199) because it had results close to the average CAGR 12.7 GSD 21.5. Going forward the parameter 179 might be lucky or unlucky, but certainly not skillful.

Create [RandomA]: [[[Actual closing Price] + [Mkt Days Since Security Opened] + [[Total Return Multiplier over 17 days]*[PE]]] mod 179]

Similar to the "DIY S&P500 equal weight screen" discussed at
The SP1500EqualWeight backtest can be extended to 1987 with {kindaLikeSP1500EW}
step3 drops illiquid stocks that might have high trading costs as discussed at
step4 through step6 as suggested at
A rand()-like function was discussed at
Print the post  


What was Your Dumbest Investment?
Share it with us -- and learn from others' stories of flubs.
When Life Gives You Lemons
We all have had hardships and made poor decisions. The important thing is how we respond and grow. Read the story of a Fool who started from nothing, and looks to gain everything.
Contact Us
Contact Customer Service and other Fool departments here.
Work for Fools?
Winner of the Washingtonian great places to work, and Glassdoor #1 Company to Work For 2015! Have access to all of TMF's online and email products for FREE, and be paid for your contributions to TMF! Click the link and start your Fool career.