Showing results for 
Search instead for 
Did you mean: 
Sign up Log in

Earn badges and make progress

You're on your way to the next level! Join the Kudos program to earn points and save your progress.

Deleted user Avatar
Deleted user

Level 1: Seed

25 / 150 points

Next: Root


1 badge earned


Participate in fun challenges

Challenges come and go, but your rewards stay with you. Do more to earn more!


Gift kudos to your peers

What goes around comes around! Share the love by gifting kudos to your peers.


Rise up in the ranks

Keep earning points to reach the top of the leaderboard. It resets every quarter so you always have a chance!


Come for the products,
stay for the community

The Atlassian Community can help you and your team get more value out of Atlassian products and practices.

Atlassian Community about banner
Community Members
Community Events
Community Groups

Using templates for training machine learning models

Does anyone have data or experience related to training machine learning models for determining effective project management strategies?  I am looking to analyze some data surrounding project management, to see if there are inferences I can gain that could lead to more efficient project management practices.


I wish to learn from this, so I follow the discussion.

Hi Lowell,


I started a project where I took ticket data from several projects.  The assumption that I made was that lower ticket time indicates greater efficiency.  This goes for ticket in Closed status as well as Resolved status, because tickets that are ultimately Closed for longer periods of time may be abandoned at the end, but more work that ultimately does not have use or implementation indicates reduced efficiency.  Then, I made a calculated field for whether the Creator of the ticket is a bot or a human.  I am hoping to see in regression testing whether a bot or a human is more efficient.  I will consider how many tickets the bot opens up that are abandoned, and how many tickets the human opens up that are abandoned as well.  Other variables I am considering are number of watchers and number of comments.  I wanted to include number of associated tickets, but that proved to be unreliable to extract at this point in time.  I'll let you know how this goes :)



I have finished up my project.  I made some changes to the categorization of my variables (I went with all tickets in a resolved status).  I had some significant findings when I analyzed the dependent variables (number of comments, number of watchers, number of attachments) affects on total ticket time in different projects.  I further categorized the different projects that had bot capabilities into Created by Bot and Created by Human data sets, and analyzed the likelihood of relationships of my dependent variables on my independent variable.  Ultimately, I was able to bring my findings to leadership to open the discussion of what independent variables likely did and likely did not have an affect on total ticket time in minutes.


Log in or Sign up to comment
AUG Leaders

Atlassian Community Events