How to build a trading strategy that combines several kinds of data

Cash generators in uptrends, gated by unemployment

Test window

Oct 2021 – Sep 2026

Starting balance

$100,000

Fee per trade

0.1%

Benchmark

SPY

This is the result. The four steps below show how the strategy was built and tested.

1. Describe the idea to Aurora

A prompt like this one describes the strategy in plain English.

“Build a portfolio that follows these rules. Universe: the S&P 500. Keep stocks with positive free cash flow that trade above their 200-day average. Buy the 20 with the best six-month return, equally weighted, on the first trading day of each month. Move to SHY (1-3 year Treasuries) while the unemployment rate is above its one-year average. Backtest it between Oct 1, 2021 and Sep 30, 2026 with $100,000 to start, a 0.1% fee on each trade, SPY as the benchmark.”

2. Check the rules Aurora writes

These are the exact rules the backtest ran.

1. Rule 1

   Universe: the S&P 500.

2. Rule 2

   Keep stocks with positive free cash flow that trade above their 200-day average.

3. Rule 3

   Buy the 20 with the best six-month return, equally weighted, on the first trading day of each month.

4. Rule 4

   Move to SHY (1-3 year Treasuries) while the unemployment rate is above its one-year average.

3. Backtest it against SPY after fees

It held 224 different stocks and moved to Treasuries whenever unemployment rose above its one-year average.

Strategy return

+41.2%

SPY return

+88.5%

Largest fall

−22.7%

Sharpe ratio

0.45

Closed trades

901

Fees paid

$5,908

4. Test it on dates it never saw

Next, run a walk-forward test, which freezes the rules and checks them on later dates they never saw. See a walk-forward test on unseen dates

The results describe historical observations. They do not establish live trading performance.

Continue exploring