AutoML Reference

Document InterSystems AutoML feature engineering and model selection processes.

Updated Feb 2, 2026
One-click install
npx skills add https://github.com/sorodriguezz/skills-objectscript --skill automl-reference
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: AutoML Reference
Source: https://github.com/sorodriguezz/skills-objectscript/tree/main/skills/automl-reference
Command: npx skills add https://github.com/sorodriguezz/skills-objectscript --skill automl-reference

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates the complex and time-consuming process of building accurate predictive machine learning models, making advanced AI accessible without deep expertise.

Core Features & Use Cases

  • Automated Feature Engineering: Intelligently processes various data types (text, lists, numerics) into formats suitable for machine learning.
  • Automated Model Training: Selects and trains multiple algorithms (XGBoost, Neural Networks, Logistic Regression, Random Forest) to find the best performing model.
  • Use Case: A business analyst can use this Skill to quickly build a customer churn prediction model from raw sales data, enabling proactive customer retention strategies.

Quick Start

Use the AutoML Reference skill to understand how to classify columns in a dataset for machine learning.

Frequently Asked Questions about AutoML Reference

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How does automated machine learning handle feature engineering for raw data?

Automated machine learning handles feature engineering by intelligently processing and transforming various data types, including text, lists, and numerics, into suitable formats for predictive modeling. This automated data transformation prepares raw datasets for algorithm training without manual intervention.

What algorithms does AutoML use for regression and classification tasks?

AutoML uses XGBRegressor and Neural Networks for regression tasks, alongside Logistic Regression and Random Forest Classifier for classification tasks. The system automatically selects and trains these algorithms to identify the best performing predictive model for your dataset.

How do I build a predictive model without deep machine learning expertise?

You can build predictive models without deep expertise by using automated machine learning systems that handle model selection and hyperparameter tuning. The system trains multiple algorithms automatically, enabling business analysts to generate predictions like customer churn directly from raw data.

Does InterSystems IRIS support automated model selection and hyperparameter tuning?

Yes, InterSystems IRIS supports automated model selection and hyperparameter tuning through its integrated AutoML system. It automatically evaluates algorithms like XGBoost, Neural Networks, Logistic Regression, and Random Forest to optimize predictive modeling workflows.

How do I classify dataset columns for machine learning in InterSystems IRIS?

You classify dataset columns for machine learning in InterSystems IRIS by referencing the AutoML system's column type classification logic. This mechanism automatically categorizes data columns to apply the correct feature engineering transformations before model training.