18048658. FUTUREPROOFING A MACHINE LEARNING MODEL simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)

FUTUREPROOFING A MACHINE LEARNING MODEL

Organization Name

INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor(s)

Kavitha Hassan Yogaraj of Bangalore (IN)

Frederik Frank Flother of Schlieren (CH)

Vladimir Rastunkov of Mundelein IL (US)

FUTUREPROOFING A MACHINE LEARNING MODEL - A simplified explanation of the abstract

This abstract first appeared for US patent application 18048658 titled 'FUTUREPROOFING A MACHINE LEARNING MODEL

Simplified Explanation

The abstract describes a method, system, and computer program product for futureproofing a machine learning model by generating a futureproofing metric and creating an enhanced machine learning model with historical data and a baseline model as inputs.

• Historical data is received for updates and changes to a baseline machine learning model.
• A futureproofing metric is generated to assess the model's resilience to future changes.
• An enhanced machine learning model is created by incorporating the historical data and baseline model.

Potential Applications

This technology can be applied in various industries such as finance, healthcare, marketing, and e-commerce to improve the robustness and adaptability of machine learning models.

Problems Solved

1. Ensures machine learning models can adapt to changes in data and remain effective over time. 2. Helps in maintaining the performance and accuracy of machine learning models in dynamic environments.

Benefits

1. Increases the longevity and relevance of machine learning models. 2. Reduces the need for frequent retraining and updates of models. 3. Enhances the overall performance and reliability of machine learning applications.

Potential Commercial Applications

Optimizing machine learning models for predictive maintenance, fraud detection, personalized recommendations, and risk assessment in various industries.

Possible Prior Art

There may be prior art related to techniques for updating and enhancing machine learning models with historical data to improve their future performance and adaptability.

How does this technology compare to existing methods for futureproofing machine learning models?

This article does not provide a direct comparison with existing methods for futureproofing machine learning models. It would be helpful to understand the specific advantages and limitations of this approach compared to traditional techniques.

What are the specific metrics used to evaluate the futureproofing of machine learning models in this method?

The abstract mentions a futureproofing metric, but it does not detail the specific metrics or criteria used to assess the resilience of the models. Understanding the key metrics involved would provide insights into the effectiveness of this approach.

Original Abstract Submitted

Provided are a computer-implemented method, a system, and a computer program product for futureproofing a machine learning model, in which historical data for updates and changes to a baseline machine learning model are received. A futureproofing metric is generated. An enhanced machine learning model comprising a futureproofed version of the baseline machine learning model is generated with the historical data and the baseline machine learning model as inputs.