메뉴
Time-series market forecasting using the Kronos model with news-aware sentiment adjustment for OHLC price prediction
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Analyze financial text sentiment using FinBERT or LLM, returning a scored label (positive/negative/neutral) from -1.0 to 1.0
Search A-Share and HK stock tickers by name or code and retrieve OHLCV historical price data
Fetch real-time hot finance news and unified trend reports from multiple sources (财联社, WallStreetCN, Weibo, Zhihu, etc.) and Polymarket prediction data
Perform finance web searches across multiple engines (Jina, DuckDuckGo, Baidu) and local RAG document retrieval with smart search caching
Generate Draw.io XML diagrams to visualize finance logic flows, investment theses, and signal transmission chains
Plan, write, and assemble professional financial reports by clustering signals into themes, writing analysis sections, and compiling a final structured report
| name | AlphaEar Predictor |
| description | Time-series market forecasting using the Kronos model with news-aware sentiment adjustment for OHLC price prediction |
| category | financial-modeling/forecasting |
| tags | ["forecasting","time-series","kronos","quantitative"] |
This skill utilizes the Kronos model (via KronosPredictorUtility) to perform time-series forecasting and adjust predictions based on news sentiment.
Workflow:
scripts/kronos_predictor.py (via KronosPredictorUtility) to generate the technical/quantitative forecast.references/PROMPTS.md to subjectively adjust the numbers based on latest news/logic.Key Tools:
KronosPredictorUtility.get_base_forecast(df, lookback, pred_len, news_text): Returns List[KLinePoint].Example Usage (Python):
from scripts.utils.kronos_predictor import KronosPredictorUtility
from scripts.utils.database_manager import DatabaseManager
db = DatabaseManager()
predictor = KronosPredictorUtility()
# Forecast
forecast = predictor.predict("600519", horizon="7d")
print(forecast)
This skill requires the Kronos model and an embedding model.
Kronos Model:
exports/models directory exists in the project root.kronos_news_v1.pt) in exports/models/.Environment Variables:
EMBEDDING_MODEL: Path or name of the embedding model (default: sentence-transformers/all-MiniLM-L6-v2).KRONOS_MODEL_PATH: Optional path to override model loading.torchtransformerssentence-transformerspandasnumpyscikit-learn