Browse Prior Art Database

A Method for Predicting Support Escalations with Machine Learning

IP.com Disclosure Number: IPCOM000236818D
Publication Date: 2014-May-16
Document File: 8 page(s) / 646K

Publishing Venue

The IP.com Prior Art Database

Related People

Scott Kaiser: INVENTOR [+2]

Abstract

This publication describes a solution to predict the probability that a given support case will be escalated based on the text of the support case. Specifically, the solution includes using machine learning techniques to determine how well text (problem statement, notes, transcripts, and the like) from any given support case matches text from known escalated cases. This will produce a confidence level of the fit which can be exposed as the likelihood that the case will be escalated at some point.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 23% of the total text.

Page 01 of 8

 A Method for Predicting Support Escalations with Machine Learning

Scott Kaiser Jason Veit

Symantec Corporation

Abstract

This publication describes a solution to predict the probability that a given support case will be escalated based on the text of the support case. Specifically, the solution includes using machine learning techniques to determine how well text (problem statement, notes, transcripts, and the like) from any given support case matches text from known escalated cases. This will produce a confidence level of the fit which can be exposed as the likelihood that the case will be escalated at some point.

Copyright © 2014 Symantec Corporation. All rights reserved.

1


Page 02 of 8

Copyright © 2014 Symantec Corporation. All rights reserved. Symantec and the Symantec Logo are trademarks or registered trademarks of Symantec Corporation or its affiliates in the U.S. and other countries. Other names may be trademarks of their respective owners. For a full list of Symantec trademarks, please visit http://www.symantec.com/about/profile/policies/trademarks/currentlist.jsp

Any Symantec products described in this document are distributed under licenses restricting their use, copying, distribution, and decompilation/reverse engineering. No part of this document may be reproduced in any form by any means without prior written authorization of Symantec Corporation and its licensors, if any.

THE DOCUMENTATION IS PROVIDED "AS IS" AND ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE OR NON-INFRINGEMENT, ARE DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD TO BE LEGALLY INVALID. SYMANTEC CORPORATION SHALL NOT BE LIABLE FOR INCIDENTAL OR CONSEQUENTIAL DAMAGES IN CONNECTION WITH THE FURNISHING, PERFORMANCE, OR USE OF THIS DOCUMENTATION. THE INFORMATION CONTAINED IN THIS DOCUMENTATION IS SUBJECT TO CHANGE WITHOUT NOTICE.

Symantec Corporation 350 Ellis Street Mountain View, CA 94043 United States

http://www.symantec.com

2

Copyright © 2014 Symantec Corporation. All rights reserved.


Page 03 of 8

A Method for Predicting Support Escalations with Machine Learning

Problem Statement

     Technology companies often offer some form of customer support to help customers use their product or service. Typically, for a particular customer issue, a support case is created and managed by a ticketing system or self-service automation. Service quality review is often a manual process which is extremely time consuming and only marginally successful at spotting key trends due to the low sample rate(s). Because of this challenge, poor overall support experience for customers can occur because customer support is unable to effectively anticipate which cases/situations that may become escalated thus are unable to take proactive measures to correct a situation.

Solution Description

     This solution predicts the probability that a given support case will be...