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 Jayaratne, Buddhi 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.
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.
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.
Related
Blog
Neuroinclusion by design. Not by exception.
Why neuroinclusion can’t be a retrofit and how Sapia.ai is building a better experience for every candidate.
In the past, if you were neurodivergent and applying for a job, you were often asked to disclose your diagnosis to get a basic accommodation – extra time on a test, maybe the option to skip a task. That disclosure often came with risk: of judgment, of stigma, or just being seen as different.
This wasn’t inclusion. It was bureaucracy. And it made neurodiverse candidates carry the burden of fitting in.
We’ve come a long way, but we’re not there yet.
Shifting from retrofits to inclusive-by-design
Over the last two decades, hiring practices have slowly moved away from reactive accommodations toward proactive, human-centric design. Leading employers began experimenting with:
- Sharing interview questions in advance
- Replacing group exercises with structured simulations
- Offering a variety of assessment formats
- Co-designing assessments with neurodiverse candidates
But even these advances have often been limited in scope, applied to special hiring programs or specific roles. Neurodiverse talent still encounters systems built for neurotypical profiles, with limited flexibility and a heavy dose of social performance pressure.
Hiring needs to look different.
Insight 1: The next frontier of hiring equity is universal design
Truly inclusive hiring doesn’t rely on diagnosis or disclosure. It doesn’t just give a select few special treatment. It’s about removing friction for everyone, especially those who’ve historically been excluded.
That’s why Sapia.ai was built with universal design principles from day one.
Here’s what that looks like in practice:
- No time limits — Candidates answer at their own pace
- No pressure to perform — It’s a conversation, not a spotlight
- No video, no group tasks — Just structured, 1:1 chat-based interviews
- Built-in coaching — Everyone gets personalised feedback
It’s not a workaround. It’s a rework.
Insight 2: Not all “friendly” methods are inclusive
We tend to assume that social or “casual” interview formats make people comfortable. But for many neurodiverse individuals, icebreakers, group exercises, and informal chats are the problem, not the solution.
When we asked 6,000 neurodiverse candidates about their experience using Sapia.ai’s chat-based interview, they told us:
“It felt very 1:1 and trustworthy… I had time to fully think about my answers.”
“It was less anxiety-inducing than video interviews.”
“I like that all applicants get initial interviews which ensures an unbiased and fair way to weigh-up candidates.”
Insight 3: Prediction ≠ Inclusion
Some AI systems claim to infer skills or fit from resumes or behavioural data. But if the training data is biased or the experience itself is exclusionary, you’re just replicating the same inequity with more speed and scale.
Inclusion means seeing people for who they are, not who they resemble in your data set.
At Sapia.ai, every interaction is transparent, explainable, and scientifically validated. We use structured, fair assessments that work for all brains, not just neurotypical ones.
Where to from here?
Neurodiversity is rising in both awareness and representation. However, inclusion won’t scale unless the systems behind hiring change as well.
That’s why we built a platform that:
- Doesn’t rely on disclosure
- Removes ambiguity and pressure
- Creates space for everyone to shine
- Measures what matters, fairly
Sapia.ai is already powering inclusive, structured, and scalable hiring for global employers like BT Group, Costa Coffee and Concentrix. Want to see how your hiring process can be more inclusive for neurodivergent individuals? Let’s chat.
Blog
Skills Measurement vs Skills Inference – What’s the Difference and Why Does It Matter?
There’s growing interest in AI-driven tools that infer skills from CVs, LinkedIn profiles, and other passive data sources. These systems claim to map someone’s capability based on the words they use, the jobs they’ve held, and patterns derived from millions of similar profiles. In theory, it’s efficient. But when inference becomes the primary basis for hiring or promotion, we need to scrutinise what’s actually being measured and what’s not.
Let’s be clear: the technology isn’t the problem. Modern inference engines use advanced natural language processing, embeddings, and knowledge graphs. The science behind them is genuinely impressive. And when they’re used alongside richer sources of data, such as internal project contributions, validated assessments, or behavioural evidence, they can offer valuable insight for workforce planning and development.
But we need to separate the two ideas:
- Skills Measurement: Directly observing or quantifying a skill based on evidence of actual performance.
- Skills Inference: Estimating the likelihood that someone has a skill, based on indirect signals or patterns in their data.
The risk lies in conflating the two.
The Problem Isn’t Inference of Skills. It’s the Data Feeding It
CVs and LinkedIn profiles are riddled with bias, inconsistency, and omission. They’re self-authored, unverified, and often written strategically – for example, to enhance certain experiences or downplay others in response to a job ad.
And different groups represent themselves in different ways. Ahuja (2024) showed, for example, that male MBA graduates in India tend to self-promote more than their female peers. Something as simple as a longer LinkedIn ‘About’ section becomes a proxy for perceived competence.
Job titles are vague. Skill descriptions vary. Proficiency is rarely signposted. Even where systems draw on internal performance data, the quality is often questionable. Ratings tend to cluster (remember the year everyone got a ‘3’ at your org?) and can often reflect manager bias or company culture more than actual output.
Sophisticated ≠ Objective
The most advanced skill inference platforms use layered data: open web sources like job ads and bios, public databases like O*NET and ESCO, internal frameworks, even anonymised behavioural signals from platform users. This breadth gives a more complete picture, and the models powering it are undeniably sophisticated.
But sophistication doesn’t equal accuracy.
These systems rely heavily on proxies and correlations, rather than observed behaviour. They estimate presence, not proficiency. And when used in high-stakes decisions, that distinction matters.
Transparency (or Lack Thereof)
In many inference systems, it’s hard to trace where a skill came from. Was it picked up from a keyword? Assumed from a job title? Correlated with others in similar roles? The logic is rarely visible, and that’s a problem, especially when decisions based on these inferences affect access to jobs, development, or promotion.
Presence ≠ Proficiency
Inferred skills suggest someone might have a capability. But hiring isn’t about possibility. It’s about evidence of capability. Saying you’ve led a team isn’t the same as doing it well. Collecting or observing actual examples of behaviour allows you to evaluate someone’s true competence at a claimed skill.
Some platforms try to infer proficiency, too, but this is still inference, not measurement. No matter how smart the model, it’s still drawing conclusions from indirect data.
By contrast, validated assessments like structured interviews, simulations, and psychometric tools are designed to measure. They observe behaviour against defined criteria, use consistent scoring frameworks (like Behaviourally Anchored Rating Scales, or BARS), and provide a transparent, defensible basis for decision-making. In doing this, the level or proficiency of a skill can be placed on a properly calibrated scale.
But here’s the thing: we don’t have to choose one over the other.
A Smarter Way Forward: The Hybrid Model
The real opportunity lies in combining the rigour of measurement with the scalability of inference.
Start with measurement
Define the skills that matter. Use structured tools to capture behavioural evidence. Set a clear standard for what good looks like. For example, define Behaviourally Anchored Rating Scales (BARS) when assessing interviews for skills. Using a framework like Sapia.ai’s Competency Framework is critical for defining what you want to measure.
Layer in inference
Apply AI to scale scoring, add contextual nuance, and detect deeper patterns that human assessors might miss, especially when reviewing large volumes of data.
Anchor the whole system in transparency and validation
Ensure people understand how inferences are made by providing clear explanations. Continuously test for fairness. Keep human oversight in the loop, especially where the stakes are high. More information on ensuring AI systems are transparent can be found in this paper.
This hybrid model respects the strengths and limits of both approaches. It recognises that AI can’t replace human judgement, but it can enhance it. That inference can extend reach, but only measurement can give you higher confidence in the results.
The Bottom Line
Inference can support and guide, but only measurement can prove. And when people’s futures are on the line, proof should always win.
References
Ahuja, A. (2024). LinkedIn profile analysis reveals gender-based differences in self-presentation among Indian MBA graduates. Journal of Business and Psychology.
Blog
Making Healthcare Hiring Human with Ethical AI
Hiring for care is unlike any other sector. Recruiters are looking for people who can bring empathy, resilience, and energy to the most demanding human roles. Whether it’s dental care, mental health, or aged care, new hires are charged with looking after others when they’re most vulnerable. The stakes are high.
Hiring for care is exactly where leveraging ethical AI can make the biggest impact.
Hiring for the traits that matter
The best carers don’t always have the best CVs.
That’s why our chat-based AI interview doesn’t screen for qualifications. It screens for the the skills that matter when caring for others. The traits that define a brilliant care worker, things like:
Empathy, Self-awareness, Accountability, Teamwork, and Energy.
The best way to uncover these traits is through structured behavioural science, delivered through an experience that allows candidates to open up. Giving candidates space to give real-life, open-text answers. With no time pressure or video stress. Then, our AI picks up the signals that matter, free from any demographic data or bias-inducing signals.
Candidates’ answers to our structured interview questions aren’t simply ticking boxes. They’re a window into how someone shows up under pressure. And they’re helping leading care organisations hire people who belong in care and those who stay.
Inclusion, built in
Inclusivity should be a core foundation of any talent assessment, and it’s a fundamental requirement for hirers in the care industry.
When healthcare hirers use chat-based AI interviews, designed to be inclusive for all groups, candidates complete their interviews when and where they choose, without the bias traps of face-to-face or phone screening. There are no accents to judge, no assumptions, just their words and their story.
And it works:
- 91.8% of carer candidates complete their interviews
- Carer candidates report 9/10 Candidate Satisfaction with their interview experience
- 80% of candidates would recommend others to apply
- Every candidate receives personalised feedback, regardless of the outcome
Drop-offs are reduced, and engagement & employer brand advocacy go up. Building a brand that candidates want to work for includes providing a hiring experience that candidates want to complete.
Real outcomes in care hiring
Our smart chat already works for some of the most respected names in healthcare and community services. Here’s a sample of the outcomes that are possible by leveraging ethical AI, a validated scientific assessment, wrapped in an experience that candidates love:
Anglicare – a leading provider of aged care services
- Time-to-offer dropped from 40+ days to just 14
- Candidate pool grew by 30%
- Turnover dropped by 63%
Abano Healthcare – Australasia’s largest dental support organisation
- 1,213 recruiter hours saved in the first month (67 hours per individual hiring team member)
- $25,000 saved in screening and interviewing time
Berry Street – a not for profit family & child services organisation
- Time-to-hire down from 22 to 7 days
- 95.4% of candidates completed their chat interviews
A smarter way to hire
The case study tells the full story of how Sapia.ai helped Anglicare, Abano Healthcare, and Berry Street transform their hiring processes by scaling up, reducing burnout, and hiring with heart.
Download it here: