Choose a market and timeframe. One Discovery search tests up to 96 strategy variations, investigates the strongest areas, and returns the strategy families that passed—or explains what came closest. Research Pro can actively search up to 1,920 variations across 20 searches every 30 days.
Discovery provides historical research evidence. It does not place trades, promise future returns, or include a completed ready-made algorithm.
Cost assumptions: Managed benchmark results use the recorded historical bid/ask spread with no separate commission. Slippage and overnight financing are not included. The robustness check doubles the recorded spread. Actual broker costs can differ.
Research Pro: $29 USD/month or $290/year
Up to 1,920 strategy variations across 20 Discovery searches, plus 100 exact backtests, every 30 days. Includes H1/H4/D1 research, saved strategies, reports and comparison. Unused allowances do not roll over; technical failures restore the affected search credit.
Use the deterministic backtester to test the strategy exactly as supplied.
Use Discovery to explore and narrow many combinations automatically.
Browse separately reviewed ready-made algorithm packages when available.
These are completed historical searches under the current managed benchmark—not interface examples. A qualifying result, a useful near-match, and a rejection are all valid outputs.
96 tested · 32 refined · 0 replay errors · 13 qualifying variations
| Period | Modelled return | PF | Trades |
|---|---|---|---|
| Full five years | +79.14% | 2.04 | 137 |
| Earlier 70% | +32.88% | 1.67 | 93 |
| Screening holdout 30% | +34.82% | 3.21 | 44 |
Every fixed screening check passed.
72 tested · 8 refined · 0 replay errors · 0 qualifying variations
| Period | Modelled return | PF | Trades |
|---|---|---|---|
| Full five years | +3.09% | 1.05 | 126 |
| Earlier 70% | -0.15% | 1.01 | 87 |
| Screening holdout 30% | +3.25% | 1.16 | 39 |
64 tested · 0 refined · 0 replay errors · 0 qualifying variations
| Period | Modelled return | PF | Trades |
|---|---|---|---|
| Full five years | +9.51% | 1.09 | 187 |
| Earlier 70% | -7.98% | 0.92 | 136 |
| Screening holdout 30% | +19.01% | 1.64 | 51 |
These cases were selected after an earlier engineering batch to illustrate three different output types. They are not a random sample and do not estimate how often a search will qualify a strategy.
Qualification: At least 30 trades in both periods, profit factor of at least 1.2 in both periods, non-negative yearly return, drawdown no worse than 20R, positive results in at least three time segments, and a positive result when recorded spread is doubled.
Account model: USD 10,000 start, 1% risk per trade, compounding. Split: 70% earlier period / 30% screening holdout.
The screening holdout is used to qualify and present results; it is not a final untouched confirmation period. Historical results do not guarantee future performance.
Checking your account…