Anchor increases candidate conversion rate by 25% and hires 86 staff with a dedicated chatbot
When candidates are difficult to follow up
Anchor provides care and support to senior citizens. It is also the largest UK non-for-profit housing association and as such, it is in constant need of hiring motivated care assistants.
A high number of individuals apply each day through Anchor's career website, but as they have a busy schedule, it is very difficult and often impossible for the hiring team to reach them afterwards and follow up on the application process. There is also a large number of skilled candidates who are unable to translate their experience on a CV and abandon the application process halfway through.
Getting all information in less than a minute
This article was written inspired by the original story published here.
The goal for Anchor was to find a way to quickly scan, engage and fix a call with potential hires. They decided to develop a purpose-built recruitment chatbot in Facebook Messenger as it is currently used by more than a billion people around the world.
In order to drive traffic to the chatbot, Anchor aired ads in facebook that instantly opened the chatbot in messenger if someone clicked on them.
Getting to the point
In less than a minute, the chatbot was able to engage one to one conversations with potential candidates and:
- Establish which role the candidate was interested in.
- Whether the job location was within commutable distance.
- Whether the candidate had the required experience.
- Fix a phone call with a recruiter.
- Capture multiple data points such as name, email address and postcode.
And if the candidate had a question the chatbot did not know how to answer to, it would pass it along to a member of the recruitment team.
Sometimes simple is better
Since deployment of this hiring chatbot, Anchor hired 86 candidates and grew its conversion rate from 2.04% to 27.35% !
The chatbot also allowed Anchor to automatically manage over 1000 discussions, increasing the amount of monthly applicants by 82%, while decreasing the cost per applicant.
Where does Machine Learning fit in all this?
Although strictly speaking, this chatbot does not implement Machine Learning models to talk with people, the development team uses it under the hood to constantly evolve the chatbot's responses. This is achieved by using logistic regression algorithms and classifying discussions in two groups, the ones that made it to the end and the ones that abandoned halfway through. One of the conclusion from this analysis was that using gifs and emojis greatly improved the user experience and gave even better conversion results.
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 :-)
Disclaimer: MLab 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.