LongTermTrend_V1664

REJECTEDhybrid

llmSimplified and strengthened entry: require either SMA50>SMA200 with positive sma_200_slope, strong 20d return, or 20d breakout, plus a moderate ret_20d and improved cumret_252d threshold. Added multi-condition exit (short 20d loss, large drawdown, or extreme RSI) for better stops. Added regime gates to exclude downtrends, high volatility, and bubble states. Added volatility-based position scaling (reduce size when vol_pctile >0.8/0.95). Reason: improve robustness across regimes, reduce drawdown and shrink size in high-volatility periods. | rejected: fitness 0.034 below threshold

Fitness

0.0336

Generation

Complexity

Created

2026-10-16

Lineage

Parents (1)

LongTermTrend_V1343S1343 · gen 61ELITEllm

changed cumret_252d threshold -0.1997 -> -0.4102

Children (0)

None

Strategy Logic (pseudocode)

# LongTermTrend_V1664  [hybrid]
require regime.trend in ['UPTREND', 'SIDEWAYS']
require regime.volatility in ['LOW_VOLATILITY', 'MEDIUM_VOLATILITY']
require regime.bubble in ['NORMAL']
if flat and (((sma_50 > sma_200 and sma_200_slope > 0.0) or ret_20d > 0.06 or breakout_20 > 0.5) and ret_20d > 0.04 and cumret_252d > -0.3):
    position = 1.0
if long and (ret_20d < -0.08 or drawdown > 0.12 or rsi_14 > 85.0):
    position = 0.0  # exit to cash

Backtest Metrics

Metric	Train	Validation	Hidden Test	Full
CAGR	-2.3%	-11.9%	—	—
Total Return	-17.1%	-31.5%	—	—
Sharpe	0.00	-0.39	—	—
Sortino	0.00	-0.25	—	—
Calmar	-0.04	-0.22	—	—
Volatility	22.0%	24.7%	—	—
Max DD	-66.1%	-52.8%	—	—
Win Rate	38.7%	38.5%	—	—
Avg Win	9.9%	15.5%	—	—
Avg Loss	-6.5%	-11.4%	—	—
Payoff	1.52	1.36	—	—
Expectancy	-0.2%	-1.1%	—	—
Profit Factor	0.96	0.85	—	—
Trades	31	13	—	—
Avg Holding Days	16.9	15.6	—	—
Turnover	7.8	8.7	—	—
Exposure	24.6%	25.1%	—	—

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