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.

The following is an excerpt from our Talent Acquisition Transformation Guide, a comprehensive playbook to help you audit and improve your recruitment strategy.

Winning more talent means getting your team in ship shape. In many organizations, the Talent Acquisition business operates in an isolated camp – no one sees or hears from you unless you have good or bad news about a particular candidate or role vacancy. 

Efficiency in recruitment requires absolute alignment. Your people leaders and your executive team must be in alignment with your new strategy, because they are equally responsible for executing it. Gone are the days when, for example, marketing managers could pass a job description for a copywriter to a Talent Acquisition specialist and wash their hands of the prospecting dirty work. Now, more than ever, the hiring manager and the specialist must form a partnership, sharing the duties of advertising, promoting, vetting, interviewing and assessing. After all, candidates for said copywriter role will expect it.

To get cooperation and buy-in from your people leaders, you need to form a visible, purposeful A-team.

Step 1: Create your recruitment A-team

Your crack recruitment task force should comprise:

• Your chiefest people leader (be it a CPO, CHRO, or Head of Talent Acquisition)
• Talent Acquisition specialists and representatives (obviously)
• Representatives from each department in the organization
• Importantly, a representative from the marketing team

Once your team is formed, you need to complete a basic audit to see where your recruitment pipeline is at – and the roadblocks stopping you from securing the talent you need.

Step 2: Fill out this Talent Requirements Matrix

This step sounds obvious on the face of it, but it actually requires some speculation and problem-solving. Consider this simple matrix, filled in with examples – it’s a good starting point on getting alignment with the A-team on your hiring needs.

Once you’ve filled out your Talent Requirements Matrix, the next step is effective triage. Almost everyone in the A-team will already be aware of your highest hiring priorities, but by filling out this matrix, you can focus talent acquisition efforts on coming up with weird and wonderful ideas for attracting the right candidates. Times like these require outside-the-box thinking!

What every business needs to know about unconscious bias in hiring

Is unconscious bias holding your business back? When it comes to building your team, it’s easy to fall into a pattern of choosing a candidate who seems like a good ‘cultural fit’.

But what if that means you’re missing out on a candidate who would be a great ‘cultural add’? Or the candidate that’s actually the perfect fit for the role and the team.  When you make an effort to overcome bias and cultivate a workplace that values diversity – of background, experience, world view and so many more attributes – you’ll cultivate a workplace that’s not just great for your team, it’s great for your business too.

Hiring on a gut feeling that someone will be a good fit for the team is just one indication that your decision has probably been influenced by unconscious bias. Don’t be alarmed, it’s more common than you think. In fact, we all have unconscious bias and we are all affected by it.

Bias can be easy to see in other people.

You might observe it in the way someone treats or talks about others, or perhaps you’ve been at the uncomfortable end of bias yourself.  When it comes to recognising our own ‘built-in’ biases, however, it can be challenging. And that’s why they call it unconscious.

Unconscious bias training has become not just a buzzword but a big business in itself. In this article, we explore the big questions around bias: What is unconscious bias? How does it impact the hiring process? Can unconscious bias be defeated? If you’ve already jumped to your own conclusions on those questions, that’s unconscious bias too!

We need to talk about bias

Since the first humans gathered around campfires, bias has existed.

It is simply the way we feel in favour of something – an idea, a thing, a person or group – or how we feel against that something.  Bias usually suggests that these feelings are judgemental, unfair or discriminatory.

Bias is about making assumptions, stereotyping or a fear of the unknown.  It can be innate or it can be learned and unconscious bias is created and reinforced by our personal experiences, our cultural background and environment.  Bias can be of little consequence – I hate broccoli – or potentially very damaging – I hate {insert name here!}.

Why does unconscious bias matter in the hiring process?

The objective of overcoming bias in the workplace is creating a work environment where every employee can feel that the workplace is welcoming, safe and free from discrimination, harassment or unfair treatment. While that may sound ‘warm and fuzzy’, diverse and inclusive workplaces can help lift employee satisfaction, boost engagement and productivity and enhance the reputation of your business as a great employer. It can also lower your exposure to potential legal action from unfair or unjust employment practices.

The most common types of unconscious bias in the workplace

When it comes to hiring, there are some biases that are more common than others. Some need no explanation – gender bias, ageism, racism, name bias – however psychologists and researchers have identified over 150 types of bias that impact the way we engage and interact with others. Here, we look at just a few. Chances are you’ve let one or more of these biases influence your decisions and, as a result, missed out on a perfect candidate.

Confirmation bias – where an opinion is formed quickly on a single detail (bad suit, good school) and the interviewer ‘fills in’ their own assessment of the candidate with questions that they believe confirm or justify their initial impression or judgement.

Overconfidence bias  –  can be closely connected to confirmation bias, when the recruiter lets their confidence in their own ability choose the best candidate in the way of objective assessment.

Illusory correlation – where a recruiter believes certain questions are revealing insights about the candidate that actually don’t exist or are not relevant to their ability to perform in a role.

Beauty Bias –  this one speaks for itself. Will a great looking person necessarily be the most successful choice for the role? The simple answer? No.

Conformity bias – this bias can occur with group assessments when recruiters fall in with the majority even if their opinion about a candidate differs. Peer pressure can have a lot to answer for.

Contrast effect  – also called judgement bias, this is where a candidate is compared with the resume and candidate that went before, rather than being reviewed on their own skills and merit against the requirements of the role.

How are you scoring in bias roulette?!

Here’s some more:

Affect heuristics – this unconscious bias sounds very scientific, but it’s one that’s being a very human survival mechanism throughout history. It’s simply about making snap judgements on someone’s ability to do a job based on superficial and irrelevant factors and your own preconceptions  – someone’s appearance, tattoos, the colour of their lipstick.

Similarity attraction – where hirers can fall into the trap of essentially hiring themselves; candidates with whom they share similar traits, interests or backgrounds. They may be fun to hang out with, but maybe not the best match for the job or building diversity.

Affinity bias – so you went to the same school, followed the same football team and maybe know the same people. That’s nice, but is it really of any relevance to the hiring decision?

Expectation anchor – where the hirer is stuck on what’s possibly an unrealistic preconception of what and who the candidate should be

Halo effect –  Your candidate is great at one thing, so that means they’re great at everything else, right? Judging candidates on one achievement or life experience doesn’t make up for a proper assessment of their qualifications and credentials

Horn effect – It’s the devil’s work. The opposite of the halo effect where one negative answer or trait darkens the hirer’s judgement and clouds the assessment process.

Intuition – going with that gut feeling again? While the emotional and intellectual connection may come into the process, it’s largely irrelevant. Focus on their actual experience and capabilities instead.

Can unconscious bias be eliminated? Can bias be unlearned?

In an ideal world, every hire would be approached in an objective way, free of unconscious basis and based on the candidate’s ability to do the job well. However, we don’t live in that perfect world and, time and time again, bias can cloud our judgement and lead to the wrong recruitment decisions. So what can we do? Let’s first talk about what doesn’t work.

Why unconscious bias training does not work

The efforts of any business to drive affirmative change in their business are to be respected. However, there’s a very good reason why unconscious bias training simply can’t work. Why?

Because unconscious bias is a universal and inherently human condition. Training targets individuals and their well-worn attitudes and world views.

While awareness and attitudes may change, inherent bias will remain because that’s the human condition.

So if humans can’t solve a very human problem, what can? Sapia is challenging the issue of unconscious bias in hiring by promoting ‘top-of-funnel’ screening that entirely avoids humans and their bias. Instead, candidates are interviewed and assessed through automation and algorithms.  The data that trains the machine is continuously tested so that if ever the slightest bias is found, it can be corrected.

According to an Article Published By Fast Company:
(Ref. https://www.fastcompany.com/90515678/science-explains-why-unconscious-bias-training-wont-reduce-workplace-racism-heres-what-will)

From a scientific perspective, there are reasons to be cautious that unconscious bias training will have a significant impact on racism, sexism, and other forms of workplace discrimination.

1. MOST BIASES ARE CONSCIOUS RATHER THAN UNCONSCIOUS

Contrary to what unconscious bias training programs would suggest, people are largely aware of their biases, attitudes, and beliefs, particularly when they concern stereotypes and prejudices. Such biases are an integral part of their self and social identity.

2. THERE IS ONLY A WEAK RELATIONSHIP BETWEEN ATTITUDES AND BEHAVIORS

Contrary to popular belief, our beliefs and attitudes are not strongly related to our behaviours. There is rarely more than 16% overlap (correlation of r = 0.4) between attitudes and behavior, and even lower for engagement and performance, or prejudice and discrimination.

3. THERE IS NO ACCURATE WAY TO MEASURE UNCONSCIOUS BIAS

The closest science has come to measuring unconscious biases is via so-called Implicit Association Tests (IAT), like Harvard’s racism or sexism test. (Over 30 million people have taken it, and you can try it for free here. These have come under significant academic criticism for being weak predictors of actual behaviours. For example, on race questions (black vs. white), the reported meta-analytic correlations range from 0.15 to 0.24.

4. IT’S HARD TO CHANGE PEOPLE’S BELIEFS, ESPECIALLY WHEN THEY DON’T WANT TO

The hardest thing to influence through any D&I initiative is how people feel about concepts such as gender or race. Systematic reviews of diversity training concluded: “The positive effects of diversity training rarely last beyond a day or two, and a number of studies suggest that it can activate bias or spark a backlash.”

Algorithms do the job humans can’t

Using machines and artificial intelligence to augment and challenge decisions is fast becoming mainstream across many applications and industries. To reduce the impact of unconscious bias in hiring decisions, testing for bias and removing it using algorithms is possible. With humans, it’s not.

Sappia tackles bias by screening and evaluating candidates with a simple open, transparent interview via a text conversation.  Candidates know text and trust text.

Unlike other Ai Hiring Tools, Sapia has no video hookups and no visual content. No CVs.

All of these factors carry the risk that unconscious bias can come into play. Nor is data extracted from social channels as our solution is designed to provide every candidate with a great experience that respects and recognises them as the individual they are.

A better experience for candidates, recruiters and clients alike

A research study by The Ladders found that recruiters only spend about 6 seconds looking at a resume. With bulk-hiring, it’s probably less. That’s 6 seconds to make or break a candidate’s hope.

Sapia’s AI-based screening comes into to its own with high volume briefs, with the capability to conduct unlimited interviews in a single hour/day, assessing >85 factors – from personality traits to language fluency and other valuable talent insights. Candidates receive personalised feedback, coaching tips for their next interview and faster decisions on their progress in the hiring process.

Sapia is not out to replace human recruiters but we are here to work as your co-pilot, helping you to make smarter, faster and unbiased hiring decisions.

Understand where unconscious bias has held your business back

AI-enabled enabled interviewing and assessment also tracks and measures bias at a micro level so businesses can understand the level and type of bias that may previously have influenced decisions. With candidate and client satisfaction rated 95%+, it’s a game-changer for changing behaviours.

Hiring’s a team sport and we’re rewriting the rules

The ability to measure unconscious bias is just one more reason to use AI-based screening tools over traditional processes.

Everyone has a story that’s bigger than their CV.

Sapia gives every candidate an opportunity to tell theirs. Through our engaging, non-threatening process where unconscious bias can be taken out of the equation (literally!), we will help you get to the best candidates sooner.

You’ll get a shortlist of candidates with the right traits and values for your business so you can move ahead to interviews with confidence and clarity. With time and resources saved on upfront screening, your team can concentrate on making the interviewing stage more rewarding for hirers and candidates alike.

With Sapia, you can soon be on your way to building more diverse, inclusive and happier workplaces. We know we can work for your business, so we’d love to work with your business. Let’s talk.

Have you seen the Inclusive e-Book? It offers a pathway to fairer hiring in 2021.

Get diversity and inclusion right whilst hiring on time and on budget. In this Inclusivity e-Book, you’ll learn: 

• How to design an inclusive recruitment path. From discovery to offer and validation of the process.
• The hidden inclusion challenges that are holding your organisation back.
• How to tell if Ai technology is ethical.

Download Inclusivity Hiring e-Book Here >