Understanding and managing machine learning in Zero Time

Zero Time uses machine learning to make associations between user activity and timesheet labels. It uses this information to make recommendations for label selections, with the goal of making time capture more efficient, accurate, fast, and easy.

Zero Time makes its suggestions based on learned associations between timesheet labels and other input from entries, such as titles and comments. These are ‘soft’ suggestions, meaning the user can always choose to reject them.

Machine learning operates on a feedback loop, whereby the user’s denial or acceptance of suggestions influences future suggestions.

Machine learning data is not retained forever, and is continuously cleaned out over time, so the app will eventually forget associations if they’re not in use.

The machine learning process

This is an outline of the machine learning process in Zero Time:

  1. User adds timesheet labels (like client, project, task or location) to notes, chatbot entries, and collector-mediated entries. They may include a # to help train the system.
  2. Zero Time learns to associate timesheet labels with the content of the entry from the note and comment fields, and with other labels. 
  3. Based on such criteria as correlation frequency, accuracy (based on feedback), and number of entries, Zero Time reaches a confidence threshold for associations that triggers its recommendation engine.
  4. When the user adds notes or collectors generate entries, Zero Time begins suggesting timesheet labels based its learned patterns.
  5. User gives feedback to the system by confirming or denying suggestions.
  6. Based on user feedback, Zero Time updates its associations and improves the accuracy of its recommendations.

Disabling  machine learning for a collector

When you install a collector, machine learning is enabled by default.

You can disable machine learning if you no longer want timesheet label recommendations to be given for entries.

To do this:

  1. Go to Administration > Employees and Organization > Permission Sets.
  2. In the Zero Time role assigned to administrators, disable the Enable Machine Learning permission.

If you later reconnect machine learning, it will begin learning again from scratch .


How long does it take for Zero Time to learn a new association?

This depends. The recommendation engine doesn’t start making suggestions until a certain threshold level of associations is detected – that is, you have to associate two terms a certain number of times within a certain timeframe.

Related links

Accepting or denying suggestions in Zero Time
Introducing Zero Time
Setting up Zero Time
Understanding Zero Time data collectors
Setting up and managing data collectors in Zero Time

Want all the latest industry updates, news on Replicon products and tips to better manage projects and time?

Sign up for our newsletter today and be the first to know!

Start a free Replicon trial today based on your business needs

Start Free Trial