algotrading / aitrading / quant / tradingstrategy / buildinpublic
20 steps to build a trading strategy that actually works
A 20-step loop for building a trading strategy, from Austin Starks. Start with a simple idea and backtest it, add layers and backtest again, then find a promising candidate and inspect its backtest events rather than trusting the summary numbers. Reason through the trace, create new strategy variants, re-run the backtests, and pick the best version.
The second half is the discipline that decides whether any of it pays. Run walk-forward optimization, reason through the rules the optimizer produced, and reject the strategy outright if those rules cannot be interpreted. Test out of sample, throw away the failures and start from scratch, and paper-trade the winners for three months while keeping a journal of the idea. Repeat the whole loop across ten strategies and deploy only the most consistent one.
Transcript
0:00Create a simple idea
0:01backtest the strategy
0:03add different layers to it
0:04backtest the strategies
0:05find a promising candidate
0:07inspect the backtest events
0:08reason through the trace
0:10create new strategy variants
0:11re-run the backtests
0:12pick the best version
0:14run walk-forward optimization
0:16reason through the rules
0:17reject it if it's uninterpretable
0:19test it out of sample otherwise
0:20throw it away and start from scratch if it fails
0:23deploy it to paper-trading if it works
0:24keep a journal of the idea
0:26paper-trade for three months
0:27do this for ten strategies
0:29deploy the most consistent good idea
Join the conversation
Loading conversation…