20240054406. AUTOMATED MACHINE LEARNING PIPELINE GENERATION simplified abstract (Amazon Technologies, Inc.)

AUTOMATED MACHINE LEARNING PIPELINE GENERATION

Organization Name

Amazon Technologies, Inc.

Inventor(s)

Aditya Vinayak Bhise of Seattle WA (US)

Harnish Botadra of Seattle WA (US)

Jae Sung Jang of Kirkland WA (US)

Jakub Zablocki of Kirkland WA (US)

Jianbo Liu of Bethesda MD (US)

Nikolay Kolotey of Bellevue WA (US)

Prince Grover of Seattle WA (US)

Tanay Bhargava of Seattle WA (US)

Thiago Goes Arjona of Everett WA (US)

Christopher Zachariah Jost of Seattle WA (US)

AUTOMATED MACHINE LEARNING PIPELINE GENERATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240054406 titled 'AUTOMATED MACHINE LEARNING PIPELINE GENERATION

Simplified Explanation

The patent application describes apparatuses and methods for an automated machine learning pipeline service and generator.

• The service receives a request from a user to generate a machine learning solution with a dataset containing values of different user variable types.
• The generator validates the dataset, enriches values using external data sources, transforms values based on pre-defined types, trains a machine learning model, and creates an executable package with enrichment and transformation recipes.
• The service tests the executable package with testing data and provides results to the user.

---

1. 1. 1. Potential Applications

• Automated machine learning solutions for various industries such as finance, healthcare, and marketing.
• Streamlining the process of developing machine learning models for data analysis and prediction tasks.

1. 1. 1. Problems Solved

• Simplifying the process of generating machine learning solutions for users without extensive data science expertise.
• Enhancing the efficiency and accuracy of machine learning model training and deployment.

1. 1. 1. Benefits

• Faster development of machine learning models.
• Improved accuracy and reliability of machine learning solutions.
• Reduction in manual effort and resources required for developing machine learning pipelines.

Original Abstract Submitted

various embodiments of apparatuses and methods for an automated machine learning pipeline service and an automated machine learning pipeline generator are described. in some embodiments, the service receives a request from a user to generate a machine learning solution, as well as a dataset that comprises values with different user variable types, and mapping of the user variable types to pre-defined types. the generator can validate the dataset, enrich the values of the dataset using external data sources, transform values of the dataset based on the pre-defined types, train a machine learning model using the enriched and transformed values, and compose an executable package, comprising enrichment recipes, transformation recipes, and the trained machine learning model, that generates scores for other data when executed. the service can further test the executable package using testing data, and provide results of the test to the user.