Files
fx-quant/config/system.yaml
T
Brent Neale f4734f57c7 Optimize strategy to SMA 50/100 with RSI 80/20 filtering
Added parameter sweep tool that tested 320 combinations across SMA periods,
trade sizes, and RSI filters. Best result: SMA 50/100 on M15 with RSI 80/20
(Sharpe 5.69, 49% win rate). Updated backtester with RSI overbought/oversold
signal filtering and config to match optimal parameters.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-17 14:17:55 +10:00

58 lines
1005 B
YAML

general:
project_name: fx-quant
timezone: UTC
brokers:
- name: oanda
type: oanda_v20
enabled: true
instruments:
- EUR_USD
data:
candle_count: 200
candle_granularities:
- M5
- M15
tick_export: false
features:
sma_windows:
- 3
- 20
- 50
- 100
ema_windows:
- 20
rsi_period: 14
atr_period: 14
vwap_window: 20
volatility_window: 20
ai:
model: local-ensemble
confidence_threshold: 0.75
retriever_enabled: true
retriever_source: supabase
ensemble_models:
- logistic_regression
- random_forest
- gradient_boosting
backtest_validation_window: 50
sanity_checks:
rsi_overbought: 80
rsi_oversold: 20
volatility_multiplier: 3.0
strategy:
rule: sma_cross
params:
short: 50
long: 100
trade_size_pct_of_equity: 0.025
max_drawdown_pct: 0.05
execution:
paper_mode: true
canary_size_pct: 0.01
max_positions: 5
interval_seconds: 60
supabase:
url: https://<your>.supabase.co
key_env_name: SUPABASE_KEY
table: fx_candles