| 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"] |
AlphaEar Predictor Skill
Overview
This skill utilizes the Kronos model (via KronosPredictorUtility) to perform time-series forecasting and adjust predictions based on news sentiment.
Capabilities
1. Forecast Market Trends
Workflow:
- Generate Base Forecast: Use
scripts/kronos_predictor.py (via KronosPredictorUtility) to generate the technical/quantitative forecast.
- Adjust Forecast (Agentic): Use the Forecast Adjustment Prompt in
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 = predictor.predict("600519", horizon="7d")
print(forecast)
Configuration
This skill requires the Kronos model and an embedding model.
-
Kronos Model:
- Ensure
exports/models directory exists in the project root.
- Place trained news projector weights (e.g.,
kronos_news_v1.pt) in exports/models/.
- Or depend on the base model (automatically downloaded).
-
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.
Dependencies
torchtransformerssentence-transformerspandasnumpyscikit-learn
