How Machine Learning Might Offer Opportunities to Preempt Escalations

Machine Learning to Preempt Escalations

Traditional customer support escalation processes focus on mitigating vs. avoiding user dissatisfaction. This often adds to the customer’s already-present frustration; lowers service satisfaction ratings; and increases support costs by requiring intervention from senior staff and management. We believe that Machine Learning (ML) can help support organizations shift the paradigm from reactive to proactive by systematically predicting escalation triggers and driving interventions before customers get frustrated — improving the service experience, lowering costs, and increasing staff efficiency along the way. This article examines the author’s experience in building an ML tool to predict service escalations and describes key takeaways from his journey.

By Sameer Patkar, VP – Oracle Support Services

Business Problem

Escalations comprise only a small percentage of most support teams’ overall ticket volumes. While proportionally few, each escalated incident incurs a higher transnational cost to resolve by requiring additional time from managers and technical resources for monitoring, follow-up, and customer communication. Preempting escalations can therefore help support organizations produce better outcomes for their customers and themselves.

To that end, support teams have utilized various approaches in the past to try and identify tickets that might escalate; most have proven to be partial solutions that either did not scale or could not reliably predict triggers. For example, one effective way to avoid escalations that occur due to lack of timely response is for ticket owners to seek help from others if they are stuck on how to proceed with an incident. While some do, most support engineers prefer to resolve problems themselves rather than seek help. Consequently, organizations have enacted external review and monitoring processes wherein managers and/or peers review open within another team member’s queue. This approach is time-consuming and does not scale.

Another popular approach is to use rules-based reports that run on all open tickets in backlog and apply logic meant to identify markers of missed expectations. While more scalable than manual audits, rules-based reports tend to identify too many potential escalations to be used reliably; the volume of “false positives” they produce can quickly inundate support personnel with additional work that may or may not legitimately require investigation.

This occurs because rules have limitations: they must be written to know about ALL potential conditions that could lead to escalation and they must have data available on which to operate. Conversely, customer dissatisfiers are not always explicitly stated in ticket data, but must instead be derived forensically by examining each individual interaction from the inception of the ticket to identify missed expectations. The relationship between this derived data and the reasons why customers escalate can be complex and not reducible to simple rules. Furthermore, customers express dissatisfaction in text updates that also convey their sentiment. Rules-based approaches are not very effective at assessing text-based sentiment and then correlating that sentiment with derived data. Finally, relationships across data elements can change over time, which can require rule reprogramming.

This article is an excerpt from a longer article Sameer wrote for the ASP.  To read the rest of this article you must be logged as an ASP Member.


Please Login:

Not an ASP Member? Learn about the benefits of joining the Association of Support Professionals
Learn More about the ASP

Related Articles

3 Questions to Ask–and 3 Ways to Improve Your Surveys Today!

Have you ever wondered if those surveys companies relentlessly send are missing the point? You’re right. Most surveys are so flawed they’re broken. In this post, I’ll look at three ways to improve your surveys—because if flawed surveys are everywhere, possibly yours have a few problem areas too!

Changing Expectations of Support

People are far less willing to “go somewhere” on the web to get support. They expect it to be where they are. You might think it’s unfair, but if a user today is having a problem (especially in a mobile experience), they are very unlikely to go to your website, navigate to support, log in, and only then engage with you.

ASP Best Support Websites Replaces the Top Ten

Think of challenging times as a chance to build a stronger team. Going through tough times together, if done well and successfully, bonds team members together, quickly and deeply. This is your chance as a leader. How do you do that?

Use the Forced Working-From-Home to Build a Stronger Team

Think of challenging times as a chance to build a stronger team. Going through tough times together, if done well and successfully, bonds team members together, quickly and deeply. This is your chance as a leader. How do you do that?

6 Ways to Apply AI to Technical Support

Support has been relentless in the pursuit of continuous improvement, yet the function of Support has remained fundamentally unchanged for decades. AI is a critical catalyst that will help enable an inevitable Support transformation. This article introduces 6 ways to apply AI to technical support.