MCP App StoreMCP App Store
from agent-quantspace48
Advanced machine learning tools for quantitative research, including PyCaret training, ML factor generation, and LASSO sparse weight optimization.
This skill provides a comprehensive set of machine learning helpers designed for financial quantitative research. It enables the agent to train models, generate predictions, and handle sparse fitting for index tracking and factor analysis.
Use this skill when you need to perform model training via PyCaret, generate ML-ranked cross-sectional factor pivots, or create rolling LASSO sparse index-tracking weights for portfolio construction.
MLEngine (classification/regression), MLFactorEngine (factor compression), and lasso_track (weight generation).Designed for agents operating within the Agent-QuantSpace framework, likely requiring a Python runtime environment with scientific libraries (pandas, scikit-learn, PyCaret).
This skill has not been reviewed by our automated audit pipeline yet.
ICLR Submission Workflow
Project management for ICLR submissions, from topic selection and anonymization to OpenReview discussion and final camera-ready.
Agentic Data Science Competition
Assistant skill to run and manage Kaggle competition workflows: submission troubleshooting, score stabilization patterns, kernel workflows, and spec-driven dele
Cortex - ML Pipeline Builder
Guided ML pipeline builder that walks an agent through data validation, feature engineering, training, evaluation, and serving endpoints for classification or r
Scikit-learn (Classical ML reference)
Comprehensive scikit-learn guidance for classification, regression, clustering, preprocessing, model evaluation, and production-ready ML pipelines.
Cortex — ML Pipeline Builder
Build a reproducible ML training-to-serving pipeline: data validation, feature engineering, training, evaluation, and a serving endpoint.
Scikit-learn Reference
Comprehensive, practical reference for classical machine learning workflows using scikit-learn: preprocessing, pipelines, supervised and unsupervised algorithms
Scikit-learn — Machine Learning Reference
Comprehensive scikit-learn guidance for classical machine learning: supervised/unsupervised algorithms, preprocessing, pipelines, evaluation and production-read
Scikit-learn Reference — Classical ML Workflows
Authoritative guidance for classical machine learning with scikit-learn: preprocessing, pipelines, model selection, evaluation, and example scripts for producti