PriceMomentum_V1349

REJECTEDhybrid

llm1) Added momentum/trend alignment filter (sma_50_slope>0 or short-term momentum) so entries occur only when price momentum aligns with signals. 2) Relaxed bubble gate (allow all bubble regimes) to avoid no-trade validation periods. 3) Replaced hard stop with a multi-condition exit: earlier stoploss (ret_20d<-12%), plus MACD histogram negative and RSI>75 to cut losses/overbought winners. 4) Introduced volatility-based position sizing (vol_pctile tiers) to reduce size in high vol, increase in low vol. 5) Lowered base position to 0.8 to reduce leverage/exposure. | rejected: stage1: sharpe -0.68 below screen

Fitness

—

Generation

Complexity

Created

2026-10-09

Lineage

Parents (1)

PriceMomentum_V0792S0792 · gen 36ARCHIVEDllm

changed ret_20d threshold -0.006 -> -0.1496

Children (0)

None

Strategy Logic (pseudocode)

# PriceMomentum_V1349  [hybrid]
require regime.trend in ['UPTREND']
if flat and ((ret_20d > 0.05 or (breakout_20 == 1 and dist_sma_20 > -0.121 and vol_chg < 1.2007)) and (sma_50_slope > 0.0 or ret_5d > 0.0 or macd_hist > 0.0)):
    position = 0.8
if long and (ret_20d < -0.12 or macd_hist < 0.0 or rsi_14 > 75.0):
    position = 0.0  # exit to cash

Backtest Metrics

Metric	Train	Validation	Hidden Test	Full
CAGR	—	—	—	—
Total Return	—	—	—	—
Sharpe	—	—	—	—
Sortino	—	—	—	—
Calmar	—	—	—	—
Volatility	—	—	—	—
Max DD	—	—	—	—
Win Rate	—	—	—	—
Avg Win	—	—	—	—
Avg Loss	—	—	—	—
Payoff	—	—	—	—
Expectancy	—	—	—	—
Profit Factor	—	—	—	—
Trades	—	—	—	—
Avg Holding Days	—	—	—	—
Turnover	—	—	—	—
Exposure	—	—	—	—

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