LongTermTrend_V1419

REJECTEDhybrid

llm1) Replaced brittle bubble-only gate with conservative regime gates: allow only UPTREND and LOW/MEDIUM volatility, and NORMAL bubble. 2) Simplified and diversified entry: added sma_50 regime + sma_50_slope condition, kept sma_200 momentum path, removed duplicate hard ret_20d checks and added a milder ret_20d>0.03 momentum filter and vol_pctile<0.7 volatility filter. 3) Improved exits: broadened to exit on 8% 20-day loss, 8% drawdown since entry, or RSI>75 to protect gains. 4) Reduced base position to 0.7 to lower risk/overfitting and improve walk-forward robustness. | rejected: fitness 0.005 below threshold

Fitness

0.0052

Generation

Complexity

Created

2026-10-10

Lineage

Parents (1)

LongTermTrend_V1159S1159 · gen 53ELITEllm

restricted to bubble regimes ['EXPENSIVE', 'EXTREME']

Children (0)

None

Strategy Logic (pseudocode)

# LongTermTrend_V1419  [hybrid]
require regime.trend in ['UPTREND']
require regime.volatility in ['LOW_VOLATILITY', 'MEDIUM_VOLATILITY']
require regime.bubble in ['NORMAL']
if flat and (((close > sma_200 and sma_200_slope > 0.0) or (close > sma_50 and sma_50_slope > 0.0) or ret_20d > 0.05) and ret_20d > 0.03 and vol_pctile < 0.7 and cumret_252d > -0.2):
    position = 0.7
if long and (ret_20d < -0.08 or drawdown < -0.08 or rsi_14 > 75.0):
    position = 0.0  # exit to cash

Backtest Metrics

Metric	Train	Validation	Hidden Test	Full
CAGR	-3.4%	-6.5%	—	—
Total Return	-24.3%	-18.2%	—	—
Sharpe	-0.32	-0.59	—	—
Sortino	-0.16	-0.26	—	—
Calmar	-0.09	-0.23	—	—
Volatility	9.4%	10.4%	—	—
Max DD	-36.1%	-28.7%	—	—
Win Rate	42.9%	46.8%	—	—
Avg Win	1.5%	1.6%	—	—
Avg Loss	-1.6%	-2.1%	—	—
Payoff	0.92	0.75	—	—
Expectancy	-0.3%	-0.4%	—	—
Profit Factor	0.69	0.66	—	—
Trades	84	47	—	—
Avg Holding Days	3.1	2.0	—	—
Turnover	14.7	21.9	—	—
Exposure	6.0%	4.5%	—	—

Walk-Forward Years

year-by-year stability matters more than any single year

Year	CAGR	Sharpe	Max DD	Trades
No walk-forward results

A robust strategy performs acceptably in most years rather than spectacularly in one — look for consistency across regimes, not a single outlier year.

Regime Performance

Period	Regime	Days	Ann. Return	Sharpe	Exposure
No regime results

Trades (full period)

0 trades

Entry	Exit	Entry Px	Exit Px	Return	Days
No trades recorded