SolSpotVolumeConfirmedMomentumLong

SOL Spot Volume-Confirmed Momentum, LONG-ONLY (SOLUSDT.BINANCE_SPOT, 4H — long half of the edge on the scarce spot venue)

Implements the hypothesis exactly: the LONG half of volume-confirmed momentum on the scarce spot venue. Long-only with leverage 1.0 and no funding dependence is precisely the routing rule for BINANCE_SPOT, so venue_type spot is correct and the CASH account can never be asked to short (should_enter returns BUY or None only; SELL is only ever the reducing exit the base template submits). calculate_signal returns the raw continuous decision variable (momentum in ATR units, discounted by participation) on every bar rather than a gated constant, and should_enter thresholds it in the same units. The two ingredients come from a single 4H OHLCV series, so nothing can desynchronise, and there is no supplementary feed whose absence could silently swap the edge mechanism. Spot round-trip cost is ~0.20% -- double the perp -- so the design keeps turnover deliberately low: the surge gate, the up-cross requirement and the exit hysteresis together produce a few dozen round trips per year rather than hundreds, while a volume-confirmed SOL 4H leg (4H ATR ~1.5-3% of price, held via a 3-ATR trail) traverses an order of magnitude more than the cost. Entry frequency sanity: the conjunction is only two conditions (momentum >= 1 ATR AND volume >= 2x its 60-bar median), each firing on the order of 10-20% of bars and positively correlated (big moves come with volume), so on ~2200 4H bars per year this fires comfortably more than the 10-trades/year floor. Performance: bars are addressed by index over bounded windows, the trailing extreme is incremental O(1), and the previous bar's eligibility is memoised, so per-bar work is constant in accumulated history. Only three parameters are tunable (mom_lookback, vol_surge_mult, trail_atr_mult); risk_pct and the entry threshold are locked so an optimizer cannot buy Sharpe with notional instead of edge.

Overfit-to-search / not-statistically-significant death (NOT fee_edge — per-trade 3.06% clears the spot floor with wide margin). The HARD, unwaivable gate PBO 0.6336 > 0.5 means the parameter selection is more likely than not overfitting, so promote is impossible. Robustness confirms best-of-N noise: deflated_sharpe 0.144 << 0.95, is_significant=false, and the candidate does not survive programme-level FDR (keeps 3 of 236, candidate_p 0.856) over 225 trials. The selected Sharpe (0.952) is below the 1.5 promotion floor and the base backtest ceiling is only ~0.84, so even before deflation this single-name 4H momentum sits under the promotion tier (win_rate 0.438<0.45, DD 15.97%>10% also miss). Per the single-name-momentum class prior (survivable only at Sharpe>=1.5 AND PF>=2.0; here 0.95/1.98), and given the SOL volume-confirmed/momentum family has already died repeatedly (Hyperliquid port fee_edge, dual-TF confluence fee_edge, impulse overfit), plus a flat ~0.8-1.2 sensitivity surface with no untapped robust region, iteration has nothing concrete to tune toward and cannot lift a DSR-0.144 signal past the gates. Failure pattern: overfit / high-PBO, not statistically significant after deflation.

Long-only 4H momentum on SOLUSDT Binance SPOT that only buys when a volume surge confirms the move. Every bar it computes a continuous participation-weighted momentum signal: price change over mom_lookback bars in ATR units, multiplied by min(1, current volume / median volume of the prior 60 bars / vol_surge_mult). It goes long on the upward cross of entry_thresh_atr (1.0 ATR) while the surge is genuinely met (participation >= 1), and is otherwise flat in cash. Exits are structural: momentum reversing to -0.25 ATR (with hysteresis so an intra-leg pause does not truncate a winner and bill a second round trip), or a 3-ATR trailing stop from the best close since entry. Sizing risks a fixed 2% of equity to the trailing-stop distance, capped at 95% of equity notional, floored at SOL's 0.001 step and the $10 spot minimum. No leverage, no shorts, no supplementary data.

Confirm the base FactoryStrategy honors a subclass override of min_bars_required for its warm-up gate (the sandbox behavior indicates it does). If the base ignores overrides, rename to avoid confusion; otherwise leave as-is.

min_bars_required(self) overrides the framework method flagged by static analysis (base_shadow). This appears deliberate — the override returns max(vol_window+2, atr_period+2, mom_lookback+2), a sensible warm-up gate, and the synthetic tests + sandbox both produced trades, so the base warm-up path is being satisfied correctly. Not blocking.

Sandbox looks healthy (avg_trade_return_pct 2.09%, PF 1.66, Sharpe 0.84, 228 trades, positive in all three vol regimes), so no immediate profitability doubt. One thing for the analyst to watch: this is a pure-OHLCV single-name trend/momentum mechanism on a 4H spot series, a family that frequently dies on OOS generalization (overfit) at the walk-forward/holdout stage even when in-sample metrics are good. The design commendably locks all but 3 parameters (mom_lookback, vol_surge_mult, trail_atr_mult) and locks risk_pct/entry threshold, which limits the overfit surface, but the small tunable set should still be evaluated for OOS stability rather than raw Sharpe. Information_ratio vs buy-hold is -0.97 in the sandbox (it underperforms holding SOL on a risk-adjusted basis over the truncated window) — expected for a defensive flat-in-cash overlay, but the analyst should confirm the full-history edge is real alpha, not just reduced beta.

avg_trade_return_pct 2.09% is ~10x the ~0.20% spot round-trip cost and well above the 0.25% spot floor — the per-trade edge clears fees with wide margin, not fee-fragile.

PF 1.66 with 228 long trades over a 6-year window (13,295 bars) is a statistically meaningful sample, and it is positive across all three vol regimes (calm/normal/stressed Sharpe 0.58/1.14/1.12).

Mechanism matches the hypothesis: 228 long / 0 short trades on a CASH spot account, low turnover (36.7), 25.7% exposure — a genuine flat-in-cash momentum overlay, not a closet long (beta 0.078, positive alpha 0.071).

No artifact signature: Sharpe modest (0.84), DD 13.6%, end_unrealized_pct 0.09 (headline is realized, not MTM paper), CAGR 16.5% plausible.

Deliberately small tunable surface (3 params: mom_lookback, vol_surge_mult, trail_atr_mult; entry/exit/risk locked) limits the overfit surface for the optimizer.

Single-name 4H OHLCV trend/momentum is a family that frequently fails OOS generalization (overfit) at walk-forward/holdout even with good in-sample metrics — the main risk to watch in the 3-phase run.

Information_ratio vs buy-hold is -0.97: risk-adjusted it underperforms simply holding SOL. Expected for a reduced-beta cash overlay, but the full-history edge must prove to be real alpha, not just lower beta — confirm the WF-OOS Sharpe and holdout, not raw return.

Win rate 41.7% means the edge lives entirely in the win/loss magnitude ratio (avg_win 3982 vs avg_loss 1713); sensitive to trail_atr_mult tuning.

Per-trade edge clears fees with wide margin: avg_trade_return_pct 3.06% is ~15x the ~0.20% spot round-trip cost and far above the 0.25% spot floor. This is NOT a fee_edge death.

Holdout passed the HARD gate: holdout Sharpe 1.17 on 14 trades, ratio 1.319, consistent_with_oos=true, z_vs_oos 0.208 — the forward window itself was positive.

Walk-forward is not flagged overfit (is_overfitted=false; avg IS 1.54 -> avg OOS 0.89, ratio ~1.7 < 3.0), sensitivity grid has zero cliffs, and 4 of 5 pre-registered predictions were met.

HARD gate failure (unwaivable): PBO 0.6336 > 0.5 — the parameter selection is more likely than not overfitting to the search. A promote verdict would be overridden.

Robustness is decisively negative: deflated_sharpe 0.144 << 0.95, is_significant=false, PSR-only aside, and the candidate does NOT survive programme-level FDR (Benjamini-Hochberg q=0.10 keeps 3 of 236, candidate_p 0.856). Over 225 trials (70 effective) the selected Sharpe is indistinguishable from best-of-N noise. High PBO + low DSR together is a decisive abandon.

Optimized Sharpe is only 0.952 (< 1.5 floor) and the base-backtest ceiling is ~0.84; win_rate 0.438 < 0.45 and max_drawdown 15.97% > 10% also miss. Even before deflation this single-name 4H momentum sits below the promotion tier.

Class prior: single-name OHLCV momentum below the ADA-winner tier (Sharpe>=1.5, PF>=2.0; here 0.95/1.98) has repeatedly died in deflation, and the SOL volume-confirmed/momentum family specifically has already died — Hyperliquid port (fee_edge), SOL dual-TF confluence (fee_edge), SOL impulse (overfit). Sensitivity is flat ~0.8-1.2 everywhere with no untapped robust region, so iteration has nothing concrete to tune toward.

min_oos_sharpe pre-registered prediction (0.90) was missed (0.890).

Benjamini-Hochberg at q=0.10 over 236 programme candidates keeps 3. A candidate that does not survive here is not distinguishable from the programme's own noise, however good its individual statistics look.

SolSpotVolumeConfirmedMomentumLong-9bf78d9fb3

SolSpotVolumeConfirmedMomentumLong proposed a disciplined, low-turnover spot momentum overlay that only bought SOL when a volume surge confirmed the move and otherwise held cash, with a tightly restricted 3-parameter tuning surface. The initial backtest looked mechanically sound — 228 long/0 short trades, per-trade return ~2.1% clearing fees, positive across all vol regimes — so the analyst approved it for the full 3-phase optimization. After optimization the numbers improved on paper (Sharpe 0.95, PF 1.98, holdout Sharpe 1.17), but the robustness statistics were decisive against it: PBO 0.6336 breached the unwaivable overfit gate, deflated Sharpe was just 0.144, and it did not survive programme-level FDR. With the selected Sharpe already below the 1.5 promotion floor, a flat sensitivity surface offering nothing concrete to tune toward, and the SOL momentum family having died repeatedly before, the strategy was abandoned after one iteration as an overfit-to-search, not-statistically-significant candidate.

Single-name 4H OHLCV momentum that lands below the ~Sharpe 1.5 / PF 2.0 tier tends to die in deflation even with a positive holdout — a strong per-trade edge and passing holdout cannot rescue a candidate with high PBO and low deflated Sharpe.

The analyst abandoned it after optimization on an unwaivable HARD gate failure — PBO 0.6336 > 0.5 — reinforced by deflated Sharpe 0.144 (<<0.95), is_significant=false, and failure to survive programme-level FDR, indicating the selected parameters were best-of-N noise rather than a real edge.

A long-only, cash-account momentum overlay on SOLUSDT spot (4H bars) that buys SOL only when a volume surge confirms directional momentum and otherwise stands flat, aiming to capture the long half of a volume-confirmed momentum edge on the expensive spot venue.

The optimized backtest over ~6 years (13,295 bars, 112 trades) returned 134.1% total with Sharpe 0.95, profit factor 1.98, 43.8% win rate and 16.0% max drawdown; per-trade return of 3.06% cleared the ~0.20% spot round-trip cost by a wide margin, and the holdout passed (Sharpe 1.17 on 14 trades).