nav[aria-label="Primary Navigation"] { padding: 0; & ul { list-style: none; width: 100%; display: flex; flex-direction: row; justify-content: start; align-items: start; gap: 30px; padding: 0; & li { margin: 0; } & ul li { list-style: none; } } }

Using templates for training machine learning models

Lucy Buecking

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.

Comments

Lowell Liwat

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

Lucy Buecking

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

Lucy

Lucy Buecking

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.