AFTAs 2022: Best AI/machine learning initiative—Bank of America

Project: Sherlock

    • WatersTechnology Staff
  • LinkedIn  
  • Save this article
  • Print this page  

Overview

Sherlock is a machine learning application linking incidents to change requests stored in the bank’s system of record. It was created to help the bank recover from business-impacting incidents faster.

What problem does it solve?   

Previously, incident management functions tended to be reactive and manual, and typically involved a triaged question-and-answer process. On average, it took roughly 90 minutes of manual effort to determine the root cause of change-related incidents. Approximately 15% of all incidents from 2019 to 2020 were identified as business-impacting incidents caused by change.

“By using the latest machine learning technology, Sherlock has closed the gap in application downtime by helping to reduce the amount of time it takes to identify business-impacting incidents. This results in less downtime if there is an incident, which impacts our customers. Sherlock is a key part of operational resiliency, which remains a critical focus for the firm.”

How does it solve the problem?

Sherlock’s incident reports contain a free-form text description of the incident, the incident date, a list of systems affected, a free-form text description of the change request, and the change request date. Using natural language processing, the tool can identify and rank similar past incidents and the corresponding changes. A list of top 10 change requests that likely caused the incident of interest is created, and provides a visual representation of the relationships identified between the impacted applications or configuration items and their association to configuration items and applications on which the change request was executed.

Future developments

After its release, Sherlock helped reduce the amount of time it takes to identify the root cause of a change-related incident from 90 minutes to about 10 minutes. Through Q1 2023, the team will build a new view within Sherlock to provide insight into change requests that have a high likelihood of causing a business-impacting incident.

Why they won

An appreciable number of initiatives entered into this year’s American Financial Technology Awards focused on how capital markets firms can use technology to manage the heaving lifting around operational risk events. Bank of America’s Sherlock platform is a good example of this, helping its IT staff to dramatically reduce the amount of time it takes for them to identify the root cause of change-related incidents, while also using natural language processing to catalogue past incidents so that similar causes in the future can be dealt with even more efficiently.

Only users who have a paid subscription or are part of a corporate subscription are able to print or copy content.

To access these options, along with all other subscription benefits, please contact info@waterstechnology.com or view our subscription options here: http://subscriptions.waterstechnology.com/subscribe

You are currently unable to copy this content. Please contact info@waterstechnology.com to find out more.

Copyright Infopro Digital Limited. All rights reserved.

As outlined in our terms and conditions, https://www.infopro-digital.com/terms-and-conditions/subscriptions/ (point 2.4), printing is limited to a single copy.

If you would like to purchase additional rights please email info@waterstechnology.com

Copyright Infopro Digital Limited. All rights reserved.

You may share this content using our article tools. As outlined in our terms and conditions, https://www.infopro-digital.com/terms-and-conditions/subscriptions/ (clause 2.4), an Authorised User may only make one copy of the materials for their own personal use. You must also comply with the restrictions in clause 2.5.

If you would like to purchase additional rights please email info@waterstechnology.com

More on Awards & Rankings

Most read articles loading...

You need to sign in to use this feature. If you don’t have a WatersTechnology account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account here