mcpField
A
alphaear-predictor

alphaear-predictor

github.com/rkidingData & databases3.1k585 installsUpdated 30w ago
Repository

About alphaear-predictor

alphaear-predictor is a skill for forecasting market time series with the Kronos model. It combines a quantitative base forecast with agent-led adjustments informed by recent news and reasoning.

Key features

  1. 01Kronos-based base forecasts
  2. 02Adjust forecasts using recent news
  3. 03Configurable forecast horizon
  4. 04Optional news projector model weights

Use cases

  1. 01Generating a market trend forecast
  2. 02Revising a forecast in light of news
  3. 03Using an embedding model with forecasts

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/rkiding/awesome-finance-skills --skill alphaear-predictor

After installing, type/alphaear-predictorin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
PROMPTS.md
scripts/
__init__.py
forecast_agent.py
json_utils.py
kronos_predictor.py
scripts/predictor/model/
__init__.py
kronos.py
module.py
scripts/prompts/
fin_agent.py
forecast_analyst.py
intent_agent.py
isq_prompt_generator.py
report_agent.py
trend_agent.py
visualizer.py
scripts/schema/
isq_template.py
models.py
scripts/utils/
__init__.py
database_manager.py
json_utils.py
logging_setup.py
scripts/utils/llm/
capability.py
factory.py
router.py
scripts/utils/predictor/
evaluation.py
kline_generate.py
training.py
scripts/utils/predictor/model/
__init__.py
kronos.py
module.py

Details

From the project README

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
1. Forecast Market Trends

Workflow:

  1. Generate Base Forecast: Use scripts/kronos_predictor.py (via KronosPredictorUtility) to generate the technical/quantitative forecast.
  2. 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
forecast = predictor.predict("600519", horizon="7d")
print(forecast)

Configuration

This skill requires the Kronos model and an embedding model.

  1. 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).

Caution

Model Security: This skill loads model weights from exports/models. We use weights_only=True and only scan for the kronos_news_*.pt pattern. Ensure you only place trusted checkpoints in this directory.

  1. 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

  • torch
  • transformers
  • sentence-transformers
  • pandas
  • numpy
  • scikit-learn

Comments

Markdown supported