joungmin/upbit-trader
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
44 Commits 1 Branch 0 Tags
main
Commit Graph

9 Commits

Author SHA1 Message Date
joungmin
976c53ed66 feat: 트레일링 스탑 전환 + 사전 필터 강화 + 예산 증액 
- cascade/LLM 매도 제거 -> 트레일링 스탑 (고점 -1.5%, 손절 -2%, 타임아웃 4h)
- 사전 필터 3종 추가: 횡보/고점/연속양봉(>=2) -> LLM 호출 57% 절감
- 현재가 매수 (LLM 가격 제안 제거)
- 종목 30개 -> 10개, BTC 제외
- 예산: 100K/3pos -> 1M/5pos (종목당 200K)
- VOL_KRW_MIN: 2M -> 5M, BUY_TIMEOUT: 60 -> 180초
- LLM 프롬프트: 연패 무시, get_trade_history 제거
- 3월 백테스트: 승률 52.1%, PNL +17,868원
- STRATEGY.md 전면 재작성

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-06 20:33:15 +09:00
joungmin
2499ea08ef docs: rewrite STRATEGY.md for 10m vol-lead strategy 
- Remove legacy 40m resampling, velocity-based entry, Bear regime sections
- Add F&G 3-tier vol threshold system (<=40->6x, 41-50->5x, >50->blocked)
- Add undying signal and vol refresh behavior docs
- Add watch alert (4x-6x approaching threshold) documentation
- Add 1yr 10m backtest results and THRESH sweep table
- Add F&G greed blocking effect comparison table
- Update file list, env vars, and sim run commands
- Add change history from 2026-03-03 to 2026-03-04

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-04 09:51:39 +09:00
joungmin
6580cda017 docs: update STRATEGY.md with F&G filter and project structure changes 
- Add F&G filter section: FNG_MIN_ENTRY=41, 1-year backtest proof
  (no filter: +95K KRW → F&G>=41: +1.72M KRW over 1 year)
- Add F&G backtest result (section D) with adaptive param findings
- Update section E: rename velocity backtest (was D)
- Split file table into production core vs tests/ scripts
- Update simulation commands to use tests/ path prefix
- Update env config: add FNG_MIN_ENTRY=41
- Add changelog entries for F&G filter, project structure, ecosystem.config.js

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-03 16:14:50 +09:00
joungmin
673ce08d84 feat: add velocity entry, fast-poll thread, tighten BEAR threshold 
- Add velocity-based entry signal in strategy.py (VELOCITY_THRESHOLD=0.10,
  VELOCITY_MIN_MOVE=0.5%, VELOCITY_MIN_AGE_M=5)
- Add fast-poll thread in daemon/runner.py (SIGNAL_POLL_INTERVAL=15s)
  for sub-minute velocity event detection
- Add vol_ratio tiered condition and get_active_signals() to strategy.py
- Change BEAR_THRESHOLD -1.0 → -0.5 in market_regime.py to catch
  slow downtrends earlier (weighted 2h score)
- Expand sell_reason VARCHAR2(500) in price_db.py DDL
- Add velocity_backtest.py and sim10m.py for strategy experimentation
- Update STRATEGY.md: correct regime algorithm description (weighted 2h
  score, not BTC 1h ±5%), add fast-poll/velocity sections, add backtest
  section D, add change history table

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-03 10:17:08 +09:00
joungmin
612055162e docs: update backtest results and WF_WINDOW param after tuning 2026-03-02 15:16:00 +09:00
joungmin
6a685a7852 feat: add sim_45m40.py and update STRATEGY.md with 40min backtest results 2026-03-02 15:02:45 +09:00
joungmin
c6c6b0020f docs: clarify backtest sections with candle unit and data source 2026-03-02 14:58:26 +09:00
joungmin
bd802fb896 docs: update STRATEGY.md to 40min candle strategy 2026-03-02 14:55:06 +09:00
joungmin
324d69dde0 feat: volume-lead strategy with compounding, WF filter, and DB-backed simulation 
- core/strategy.py: replace trend strategy with volume-lead accumulation
  (vol spike + 2h quiet → signal, +4.8% rise → entry)
- core/trader.py: compound budget adjusts on both profit and loss (floor 30%)
- core/notify.py: add accumulation signal telegram notification
- ohlcv_db.py: Oracle ADB OHLCV cache (insert, load, incremental update)
- sim_365.py: 365-day compounding simulation loading from DB
- krw_sim.py: KRW-based simulation with MAX_POSITIONS constraint
- ticker_sim.py: ticker count expansion comparison
- STRATEGY.md: full strategy documentation
- .gitignore: exclude *.pkl cache files

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-02 01:46:03 +09:00