this video is part of the process optimization use case Series where we'll focus on different techniques to identify process and efficiencies non-conformant activities and general Improvement opportunities now self-service channels such as a portal or email allow quick customer or Employee Service however unlike phone walkup or a virtual agent experience it is mostly a one-way communication which makes intake a little bit more challenging not everyone knows how to describe their problem or what they need accurately or completely consequently tickets created by self-service often have higher reassignment counts or they more frequently require us to go back to the requester for some additional information these situations where additional information is required are frustrating for customers and employees and they have a negative impact on satisfaction scores as well as the service team's productivity process optimization or servicenows in platform process mining solution can be used to help analyze work coming in Via different channels and nicely opportunities to improve intake experiences as well show us some ways in which we might be able to create some new self-service offerings which will increase the speed and productivity of the organization so let's take a look at this this quick example here of of how we might do some Channel analysis what we're looking at here is about 22 000 incidents that we've mined with process optimization we chose incident for this use case but we could apply this to let's say customer service cases or HR cases what we're going to be doing here is we'll quickly come down here and what we'll want to focus in on is the node or in this case incidents that are coming in Via this awaiting caller info or not coming into your channel but going into the awaiting caller info State at some point and we can see here that we have about eight eighty four hundred unique incidents that took this trip and 10 200 total occurrences so that means that there's at least 1800 incidents that went into a waiting caller info more than once that's that's certainly something that we're going to want to focus in on at some point right now though let's just look at those 8400 that went into this state at least once so I'll hit apply transition we'll click apply and this is going to narrow the map down to just those 8 400 incidents that went into a waiting caller info and now what we can do is we can start using our breakdown analysis to analyze these tickets by intake Channel and what we can see is that a good portion of them came in via cell service in Portal but the one that jumps out to me is this third one on the list email and why that jumps out is look at the average duration of tickets that came in via email and went into a waiting caller info it's almost 15 days almost a whole week greater than these other two channels now that might be to expect it might be expected email is a very unstructured channel so we'd expect some back and forth but still a whole additional week there's got to be some improvement opportunities in there so we're going to click on email and we're going to hit apply to focus in on just the incidents that came in via email that went into a waiting caller info and now that I've narrowed it down to these 1300 incidents I'm going to want to start digging into the incidents themselves of course because I'm in the platform I can go to this show records piece and just look at the instant themself but I want to take a little bit of a smarter approach we're going to use our in-platform machine learning to do some cluster analysis of the unstructured data within these tickets the short descriptions and descriptions and see if there's any patterns inside of them and what I can see is I start to see some clusters of incidents I had 61 that kind of matched these criteria where there was talk about email and password reset which would be expected um here's another opportunity it looks like we have a bunch of things coming in via email going to a waiting corner from which we're changing a manager or a cost center that seems like a very structured interactivity we should be able to improve the intake experience to eliminate some of this back and forth and then I've also got a whole set of tickets here or that came in or incidents that came in around people who just want to update their past their email address and their profile that seems like something that we should already have the catalog item for or self-service option four and maybe we just need to understand who's opening these and Market that option a little bit better it certainly is something that we should potentially create a virtual agent conversation for to drive a little bit more self-service there but what you can see in just a matter of minutes here we were able to isolate some opportunities to in improve in intake experience potentially or drive a new self-service option thank you for spending the time with us here today and happy mining