Overstock develops an internal HR chatbot to automate the process when an employee calls in sick

Machine Learning Chatbot

What to do when someone calls in sick

Overstock is an american online retailer with over 450 employees in its salt lake city branch. As any other large employee, it has to deal with staff calling in sick and this is a recurring issue. Overstock used to have a dedicated hotline where employers could call and leave a message. A real human being would then hear all messages one by one and deal with the situation.
Needless to say, this was a repetitive, mundane and time consuming task that needed to be automated.


Chatbots are not only for customers

This article was written inspired by the original story published here.
The HR folks at Overstock decided to improve user experience for employers by developing an internal chatbot called "Mila" and made it available through a dedicated hotline.
After the employee calls in sick, he gets a sympathetic message, like "I am very sorry, I hope you get better soon" and then asks a few questions to deal with the required paperwork related to employer's absence. Mila then notifies the manager and even finds the necessary replacement.
Mila does not take holidays, she works 24/7 and what's best, she will never need to call in sick herself !


chatbot hr


Ask Mila anything (HR related)...

After implementation and successfully deploying Mila, the HR department of Overstock decided to expand her capabilities and automate other boring and mundane HR tasks, like:

  • Schedule holidays
  • know about payment
  • Asks questions about benefits
  • Update the work schedule
  • etc

Building a chatbot does not necessarily need to be a difficult or lengthy project. There are several technology vendors with highly competitive prices and there are even platforms that could allow you to easily build a chatbot that understands and can automate any task that could be done by a human assistant.

MLab, the Machine Learning specialists at your service!


If Machine Learning inspires you and you think you would like to implement a use case in your organisation, please contact us. We are independant and we will recommend and integrate the technology that adapts the best to your needs. If available technologies don't satisfy your needs, we can always develop a custom model tailored to your project.

Best of all, you would be surprised to learn the implementation cost of such a solution :-)


DisclaimerMLab was not directly involved in the development of this project. We simply publish this case study as a source of inspiration on what Machine Learning can achieve.