Written by Laura Belfield

2022 Year in Review

We’re taking a quick look behind us before we crack on with making hiring fairer for even more candidates in 2023.

Product Highlights

This year we built and upgraded 17 of our customers to our new secure platform, Edge 3; and released a host of features that have transformed our candidate and hiring team experience.

Candidate Experience

In the early part of the year we made a bunch of nifty design improvements to make Chat Interview even more intuitive. Then we added features like reminder emails, a progress bar, improved the experience of entering phone numbers for global candidates and introduced a planned delay in sending My Insights profiles.

In the world of video, we enabled customers to use standalone Video Interviews, and added some smaller changes like improving the compression of our video platform, and adding the ability for hiring teams to use pre-recorded videos to ask questions or play scenarios to candidates.

Hiring Team Experience

After we completely rebuilt our platform to make it more secure, user friendly and flexible; we continued to improve the experience for hiring teams with features like optimizing Talent Insights on mobile devices; improving ease of access while maintaining security with ‘remember this device’; and improving candidate search and management.


Alongside a number of additions to our people insights product, Discover Insights, our new Integrations dashboard taps into valuable data from ATS’s to give integrated customers a holistic view of candidate experience, efficiency and inclusivity along the hiring journey.

Partnerships & Integrations

Our Integration Warriors did us proud this year. We completed 7 new ATS integrations, enabling a seamless candidate and user experience for customers of SmartRecruiters, Workday, SuccessFactors, eArcu, Greenhouse, PageUp and Avature.

We were also accepted into the Crown Commercial Service Marketplace, making it easy for UK government departments to access our offering; and we continued to work with some of the largest RPO partners globally to help transform the hiring process of some incredible brands.


Security and compliance are always a priority at Sapia. With Edge 3 came multi-region data hosting, more secure login features, and user hierarchies to ensure secure storage and access to candidate data.

And as a gift to round out the year, our auditor AssuranceLab completed our SOC 2 Type 2 surveillance, and we’re on track for successful accreditation, with a report available in Q1 2023.

Looking forward to 2023

Next year brings new challenges as we’ll continue to improve our offering while expanding our customer base globally.

On the horizon are some exciting improvements to Talent Insights; a host of new integrations including Workable, iCIMS, Oracle, Cornerstone, Bullhorn, Lever, Jobvite, JazzHR… and one release that we’re not quite ready to announce just yet.

Let’s just say it’ll be muy, muy grande, et très excitant!


This AI Model Can Predict If You Are A Job Hopper Or Not

Voluntary employee turnover can have a direct financial impact on organisations. And, at the time of this pandemic outbreak where the majority of the organisations are looking to cut down their employee costs, voluntary employee turnover can create a big concern for companies. And thus, the ability to predict this turnover rate of employees can not only help in making informed hiring decisions but can also help in saving a substantial financial crisis in this uncertain time.

What Drives Job-Hopping?

Acknowledging that, researchers and data scientists from Sapia, a AI recruiting startup, built a language model that can analyse the open-ended interview questions of the candidate to infer the likelihood of a candidate’s job-hopping. The study — led by Madhura JayaratneBuddhi Jayatilleke — was done on the responses of 45,000 job applicants, who used a chatbot to give an interview and also self-rated themselves on their possibility of hopping jobs.

The researchers evaluated five different methods of text representations — short for term frequency-inverse document frequency (TF-IDF), LDS, GloVe Vectors for word representations, Doc2Vec document embeddings, and Linguistic Inquiry and Word Count (LIWC). However, the GloVe embeddings provided the best results highlighting the positive correlation between sequences of words and the likelihood of employees leaving the job.

Researchers have also further noted that there is also a positive correlation of employee job-hopping with their “openness to experience.” With companies able to predict the same for freshers and the ones changing their career can provide significant financial benefits for the company.

Regression Model To Infer Job Hopping

Apart from a financial impact of on-boarding new employees, or outsourcing the work, increased employee turnover rate can also decrease productivity as well as can dampen employee morale. In fact, the trend of leaving jobs in order to search for a better one has gained massive traction amid this competitive landscape. And thus, it has become critical for companies to assess the likelihood of the candidate to hop jobs prior to selections.

Traditionally this assessment was done by surfing through candidates’ resume; however, the manual intervention makes the process tiring as well as inaccurate. Plus, this method only was eligible for professionals with work experience but was not fruitful for freshers and amateurs. And thus, researchers decided to leverage the interview answers to analyse the candidates’ personality traits as well as their chances of voluntary turnover.

To test the correlation of the interview answers and likelihood of hopping jobs, the researchers built a regression model that uses the textual answers given by the candidate to infer the result. The chosen candidates used the chatbot — Chat Interview by Sapia for responding to 5-7 open-ended interview questions on past experience, situational judgement and values, rated themselves on a 5-point scale on their motives of changing jobs. Further, the length of the textual response along with the distribution of job-hopping likelihood score among all participants formed the ground truth for building the predictive model.

Some examples of questions asked.

To initiate the process, the researchers leveraged the LDA-based topic modelling to understand the correlation between the words and phrases used by the candidate and the chances of them leaving the company. Post that, the researchers evaluated four open-vocabulary approaches that analyse all words for understanding the textual information.

Open vocabulary approaches are always going to be preferred over closed ones like LIWC, as it doesn’t rely on category judgement of words. These approaches are further used to build the regression model with the Random Forest algorithm using the scores of the participants. Researchers used 80% of the data to train the model, and the rest of the 20% was used to validate the accuracy of the model.

Additionally, researchers also experiment with various text response lengths, especially with the shorter ones, which becomes challenging as there is not much textual context to predict. However, they found a balance between the short text responses along with the data available and trained the model predicts for even those.

Model accuracy vs minimum text length in words

To test the accuracy, the models are evaluated based on the actual likelihood of the turnover with relation to the score produced by the model. To which, the GloVe word embedding approach with the minimum text of 150 words achieved the highest correlation. This result demonstrated that the language used in responding to typical open-ended interview questions could predict the chances of candidates’ turnover rate.

Wrapping Up

Leveraging data from over 45,000 individuals researchers built a regression model in order to infer the likelihood of the candidates leaving the job. It will not only remove the dependency of companies on candidate resumes and job histories but also enhances the process of hiring into a multi-measure assessment process that can be conducted digitally for recruiting.

By Sejuti Das, Analytics India Magazine, 02/08/2020

Join the movement

To keep up to date on all things “Hiring with Ai” subscribe to our blog!

You can try out Sapia’s Chat Interview right now, or leave us your details here to get a personalised demo.

Read Online

30 days? 3 days? Nup, 3 minutes! Time-to-fill metrics, reset.

Has the time it takes to fill a role genuinely improved?

I think back to my days as a recruiter, you filled jobs by posting adverts. That was 15 years ago. The saying was: “Post and pray” because you never knew what would come back.

The average time to fill a role, as we advised the business, was 30 days.

Even then, there was flexibility on that because of the ‘war on talent’. It was hard to find people. Skilled people. The ‘right’ talent. When we needed to find talent fast than from time-to-time, we would engage a 3rd party recruiting agency to help us. However, that was costly.

So, even with the proper sourcing tools in hand – the business just needed to wait. Here were the reasons that recruiters gave for not delivering quickly: 

  • We’ve had a really low response rate 
  • The calibre of applications aren’t quite right 
  • Our salaries aren’t fitting with what the market demands

Sound familiar?

Reasons, and perhaps excuses. And the business just had to wait. 

Fast forward 15 years, and from my observations, we are still seeing similar time-to-fill projections. 

According to a Job Vite – time to fill remains anywhere between 25 (retail) or 48 (hospitality) days (when I read this, I nearly fell off my chair!). This is surprising since technology has come such a long way since then. 

Why are hiring managers waiting this long for these high-volume skills? And the wait will undoubtedly be increased due to the volumes of applications – thanks to C-19. What is the cost associated with waiting? A straightforward formula I found published by Hudson (for non-revenue generating employees) is: 

(Total Company Annual Revenue) ÷ (Number of Employees) ÷ 365 = Daily Lost Revenue

Here’s a working example. Let’s take a retailer. They generate 2.9 billion in revenues and have 11,000 employees. This means that their daily lost revenue PER vacant position is $722. 

If it takes 25 days to fill this position, then it costs the business $18,057 in lost revenue. The time it is taking to fill roles is costing the business too much.  Speed is of the essence.

Volume recruiting and time-to-fill considerations:

I’ve observed talent teams who recruit in high volume scenarios; spending hours screening thousands of CV’s – with inherent bias’s creeping in by the 13th CV. Then fatigue sets in. And by the 135th CV, unconscious biases have turned into bold conscious judgements; 

  • Their CV is not long enough – “reject”
  • Their CV is too short – “reject”
  • The layout of their CV wasn’t professional enough – “reject”
  • Don’t put education at the back,  have it at the front – “reject”
  • They are not descriptive enough – “reject”
  • They do not enough retail experience – “reject”. And what even is this arbitrary requirement of years of experience? If you have hit the two-year mark within a profession, how does that automatically make you qualified?

Keeping your process consistent and fair is a challenge and the quality of the screening process diminishes. 

If it takes 6 seconds to review a CV, that’s 1.6 hours to get through 1000.

Then there is the phone screen. If you only took 30 into this stage and spoke to them for 10 minutes each, then it will take the recruiter five hours. 

And time is not concentrated nor time-bound to one session – it elapses. You aren’t sitting for 1.6 hours at a time nor can you schedule back-to-back phone screens, so the realistic time frame for this is about a week. 

From there, it’s coordinating Hiring Manager interviews, conducting their interviews, getting feedback, making decisions, giving offers, taking reference checks and finalising compliance steps to make the hire. This is where it ends up being a long and drawn-out process. 

By automating the first pre-screening steps recruiters can seriously slash the time it takes to fill.

Plus they can drive a far better process. How? By getting a trustworthy understanding of the candidate and their personality modelled against the organisations’ success DNA (the “Success DNA” is the profile of what success looks like in your organisation).  

When candidates apply their first step is an automated interview.

It takes 15-20 minutes to complete, and all candidates receive a personality assessment based on what they wrote (which they love).  

Personality can be deduced from the text that candidates write (scientifically proven) and then there is also the feedback from thousands of candidates talking to the accuracy of these personality assessments. 

Here’s a tiny sample of all the feedback >>




What took weeks to get to the interview stage can now be done in minutes following an application.

For Talent Acquisition to build its credibility in the business, it needs to demonstrate its impact on the bottom line and provide tangible solutions to address this need for speed. Tools like Sapia can help with solving for these speed and cost challenges, and the benefits of providing a consistent, bias-free candidate experience are just the icing on the cake. 

Join the movement

To keep up to date on all things “Hiring with Ai” subscribe to our blog!

You can try out Sapia’s FirstInterview right now, or leave us your details here to get a personalised demo.

Read Online

Time for HR to level up

Now is the time for HR to Level Up on Ai literacy 

2020 sucked. For everyone. We were all totally unprepared and many of us just got through it. Yes, it dispelled that long-held myth that ‘I need to see you to trust you are doing the work’ but flexibility is only fabulous when you aren’t surrounded by kids at home 24/7 or under lockdown in a global pandemic. What will 2021 bring and can we be better prepared?

With two massive workforce movements in one year – the forced move to distributed work (we prefer this term to remote work), and Black Lives Matter, HR has to get better prepared in its understanding of the human impact of technology in use, especially Ai.

The innate power of Ai is to uncover patterns in large volumes of data and the data-driven thinking that comes with the adoption of Ai in your processes can challenge human decision making. This is not a bad thing because it allows us to interrupt unconscious biases we inherit thanks to our evolutionary hard-wiring.

Whilst HR technology has evolved, there are many pseudoscientific claims around Ai – almost more than there are genuinely scientifically backed claims. Using the wrong Ai-technology creates a huge legal risk and brand risk for companies, for which HR is ultimately responsible.  Now is the time for HR to step up and educate themselves about which technology is genuinely innovative and moves humanity forward.

The bar must be held high when you are making life-changing decisions on the basis of data.

The work that HR needs to do is:

  • Self-education
  • Self-regulation
  • Use thorough impact assessments looking at the holistic candidate experience, not just the algorithmic components overseen by a joint team comprising HR, legal and cybersecurity
  • Create a guiding framework for making the right decision

The team that needs to do the work ought to be cross-functional including  HR, legal and cybersecurity.

To help HR leaders make smart decisions about these new Ai technologies, we are making available our FAIR™ Framework, a set of measures and guidelines to make sure that both candidates and hiring managers can trust the Ai tools that they use.

Understanding FAIR™ – Fair Ai for Recruitment

Go here to download >

A global standard for the responsible use of Ai in recruitment.

Ai can deliver powerful and better outcomes for recruiters and candidates, but we must ensure that all recruiting Ai is fair.

For hiring managers and organisations, this guide provides an assurance as well as a template to query fairness related metrics of Ai recruitment tools.

For candidates, FAIR™ ensures that they are using a system built with fairness as a key performance metric. This set of guidelines helps HR leaders make smart decisions so they can trust the Ai tools that they use. Here’s the FAIR Framework >

Read Online