FINAL WORD
Machine learning
and ITSM
When machine learning is applied to IT service management,
end users can expect to see benefits in IT usage writes
Ashwin Ram R at ManageEngine.
Resolving incidents
Ashwin Ram R is an ITSM evangelist
at ManageEngine.
T
he field of machine learning is
a hot topic. Processing online
search requests, filtering spam
automatically out of our email inboxes
and understanding and replying to speech
commands on smartphones are all machine-
learning tasks being done on a daily basis.
Sooner or later, machine learning
will also be applied to IT service
management or ITSM to change the way
help desks work. The benefits might
include predicting issues and problems
proactively, improving search capabilities
and knowledge management, and
classifying and routing issues with greater
ease. To be more specific, you can expect
the following scenarios in the near future:
Auto approvals
With the implementation of machine
learning, help desks can be trained to
auto-approve service requests based on
the employee’s role, department, work site
and other parameters. For example, when
a designer requests additional design tools
or software, the help desk will be able to
automatically approve the request and
initiate a workflow without waiting for the
manager’s approval.
The help desk also can be trained
to automatically check the workstation
assigned to that designer for minimum
system requirements to install the
requested tools or software and create
a request to upgrade the system, if
necessary, by itself.
End users will be able to search for
solutions and resolve incidents without
the involvement of any technicians.
Through machine learning, help desks
can be trained to scan incoming tickets
and provide end users with solutions
automatically, based on the system’s
previous experience. Google Assistant-style
chat boxes will also help end users resolve
incidents or get information without even
logging a ticket into the help desk.
Help desks also could learn from past
experience and data to route tickets or tasks
to the appropriate technicians or support
groups, thereby automating the ticket
assignment process without having to create
any rules or workflows. Machine learning
would help reduce resolution times and
improve the efficiency of the help desk team.
Problem anticipation
With machine learning, help desks will
be able to analyse incident patterns and
anticipate problems. In addition, trained
help desks could automatically trigger
notifications or create problem tickets for
anticipated issues so that the help desk
technicians can investigate at the earliest.
Say the performance of an application
server starts deteriorating, help desks
would be able to anticipate any application
failures from the past performance data of
that particular server, warn end users who
might be affected, create a problem ticket
and associate any relevant incident tickets
with the problem ticket.
Change management
Change implementations are always
associated with a certain level of risk.
Without a proper plan and workflow in
place, change implementations can be
costly. Help desks can learn from previous
change implementation data and experience
to help create highly dynamic workflows.
For example, with the implementation
of machine learning, help desk systems
might recognise potential signs of change
implementation failure and prompt
administrators to stop the implementation
and execute the backup plan even before
the failure occurs. Change management
modules guided by machine learning will
also be able to make recommendations
during the planning phase based on
previous experiences.
Asset life cycle
A sizeable number of incidents occur due
to old IT assets whose performance has
degraded. Machine learning can help
automatically identify which assets might
repetitively break down based on factors
such as their performance levels and
incidents associated with them.
Once those assets are detected, the help
desk can use machine learning to send
notifications to technicians and facilitate
ordering replacements. The simplest
case could be the help desk automatically
creating requests for printer toner
replacements after a specific number of
pages have been printed.
ITSM is full of opportunities for
machine learning. These scenarios are
some of the simplest use cases showing
how machine learning can make life easier
for both the help desk team and end
users. Though these might not be readily
available as out-of-the-box solutions, they
are not too far away into the future.
65