Bank of America Patent for ML Resource Utilization Prediction

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 24th, 2026

Detected March 24th, 2026

Summary

The USPTO has granted Bank of America a patent for a machine-learning-based engine designed to predict and manage resource utilization in computing systems. The patent, titled 'Machine-learning (ML)-based resource utilization prediction and management engine,' was granted on March 24, 2026.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has granted Bank of America Corporation patent US12585501B2 for a system and method related to machine-learning (ML) based resource utilization prediction and management. The patent covers techniques for optimizing resource allocation in computing systems by compiling training data, running an ML model to determine resource parameters, and selecting optimal runtimes for computing jobs based on calculated distance values. The filing date for this patent was February 21, 2022.

This patent grant is primarily an intellectual property development for Bank of America and does not impose new regulatory obligations on other entities. However, it signifies innovation in the application of ML for operational efficiency within financial institutions. Compliance officers in the financial sector may note this as an example of technological advancement in resource management, particularly relevant for entities leveraging AI and ML for IT infrastructure optimization.

Source document (simplified)

← USPTO Patent Grants

Machine-learning (ML)-based resource utilization prediction and management engine

Grant US12585501B2 Kind: B2 Mar 24, 2026

Assignee

Bank of America Corporation

Inventors

Gopal Narayanan, Paparayudu Anaparti, Vishnu Vardhan Sarva, Sai Karthik Nanduri, Saikiran Gunti

Abstract

Systems and methods for optimizing resource utilization in a computing system are provided. Methods include compiling training data, running a machine-learning (ML) model using the training data to determine a set of resource parameters, receiving a request to schedule the computing job on the computing system, computing, for each of a plurality of potential runtimes, an amalgam distance value, selecting the potential runtime with the optimal distance value for scheduling the computing job, and generating a job execution schedule based on the selected potential runtime.