The research

Building the Mine

Building a research system. Testing the data, the backtests, and my own assumptions.

Building the Mine 5 min read

Two weeks, 1,784 commits, zero trades: building the mine

The first two weeks of a microcap research system: almost none of it is about picking stocks, and one timestamp problem could have faked every result.

October 4, 2026

Building the Mine 5 min read

Rule one: don't fool yourself (the backtest is lying)

The best of 200 random strategies made 27% a year in its backtest and 3% afterward. Four ways backtests lie about microcaps, and my defenses.

October 4, 2026