Predictive OSS

In yesterday’s blog we discussed Ben Evans’ models of search and discovery (as follows) as well as how that overlays on OSS:

  1. There is giving you what you already know you want (Amazon, Google)
  2. There is working out what you want (Amazon and Google’s aspiration)
  3. And then there is suggesting what you might want (Heywood Hill).

Benedict Evans here.

Now if you think of OSS as being:

  • Efficiency engines
  • Insight engines

what possibilities do you come up with that don’t (or rarely) exist in OSS today?

CLASS 1 (traditional query-based OSS).
This functionality is what you get from any existing OSS so I’ll skip this one in this blog.

CLASS 2 (Predictive OSS)
We’ve all heard about the predictive analytics buzz, where we use big historical data sets to identify patterns that repeat and therefore we can intervene (eg degradations in network health or customer experiences likely to lead to churn).

What about these:

  • Given a historical set of activities performed, what activity should an operator work on next (ie automation of skills-based routing)
  • Given a historical set of data recorded on faults and follow-up remediation activities, what actions should an operator work on next (eg automating fault restoration through dynamic root cause analysis rather than the pre-coded, algorithmic RCA of Class 1)
  • What they can learn from other operator actions, especially in terms of doing an often-repeated activity in the most optimised way according to historical measurements
  • Using aggregated activity data to identify optimised processes and then use decision support to inform / guide operators performing a task is future (as opposed to having a BA design and record a fixed process)
  • Working out what an operator (or customer) has been interested in before and therefore what they might want to know next (eg identifying a customer, querying their usage patterns for anomalies and recommending better network or service configurations)
  • Optimisating designs of planned network expansions or augmentations based on recorded data

Well this post got a bit longer than l expected so we’ll carry over the precognitive list to Monday’s blog

If this article was helpful, subscribe to the Passionate About OSS Blog to get each new post sent directly to your inbox. 100% free of charge and free of spam.

Our Solutions


Most Recent Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.