arena_get_edge_reports

io.github.Schoasch/backtesting-arena · Verify this server

Which entry filter carries a real edge? Platform-wide aggregated analysis: how each Pro+ entry filter (200 WMA, ATR low/high/expansion, Altcoin Season, Bullmarket confirm/strict) affects strategy CAGR — baseline vs. filtered, asset-equal-weighted (per-asset medians over param-deduplicated runs, then the median across assets — no single asset's run grid can dominate an arm). delta_cagr is the median of PER-ASSET deltas over MATCHED assets only (present in both arms) — so it usually differs from filtered_cagr − baseline_cagr; pairs_matched/pairs_filtered and the baseline pairs count declare the basis. Verdicts come from the effect's 90% paired-bootstrap interval (delta_ci_low/delta_ci_high), not the point estimate: helps (whole interval > +1pp) / hurts (< −1pp) / neutral (inside ±1pp) / insufficient_evidence (runs disagree) / insufficient_data (fewer than 30 runs per arm or fewer than 10 matched assets). Below the gate, derived fields (delta_*, dsr, dsr_pass) are null; every gated null carries its reason (dsr_pass_reason, *_net_reason); the envelope `evidence` block declares the gate's referent and threshold machine-readably. Response is GROUPED by strategy: envelope fields (market, computed_at, n_trials) once, per strategy one baseline block {cagr, net_cagr, sharpe} plus filter cells; filter cells with zero runs are folded into filters_without_data. A full market is a few hundred cells — use limit/offset (strategies per page) plus the truncated flag for partial reads. Filters evaluated in isolation (no stacking); net values are median CAGR after per-side trading costs (verdict/delta stay gross). [Free tier]