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

In an earlier blog, we talked about HR’s role in managing business risk. Today we turn our focus on one risk area that occupies CHRO’s, CEOs and Boards- the risk presented by bias and how to maximise fairness by removing bias. 

Despite all the attention generated by International Women’s Day year a few months back and year on year, and myriad other initiatives, Boards, CEO’s and CHRO’s know that bias goes beyond gender and fixing it requires more than a training session or two. 

Humans are full of bias and none of us like admitting that.

Most of us would not even know when are being biased…

‘I just had a feeling he wasn’t going to be any good’

‘he just wasn’t a good culture fit’

‘she just doesn’t have the requisite experience’ 

‘we had such an awesome interview, we could have chatted forever we had so much in common ‘

Bias in recruitment is even less measured and reported on than quality of hire.

It starts with having the data. The data revolution has been happening for decades in every other function but where is the data around recruitment?

• Do you know if there is bias in screening? hiring? promotion?
• Do the leaders and Board know those stats?
• When you run your 5000 graduate applicants through a personality assessment do you probe HR on what the success profile is that is defining screening criteria?
• Is that profile preferring a certain type (eg over-indexed to qualities like drive, initiative, agility) or does it balance out hiring to include some of those all-important cultural traits like empathy and humility? 
• Is your hiring profile going to give you more ‘Satya’s’ or more ‘Travis’s’? 

More on bias measurement later…

How can bias be removed from people decisions?

Daniel Kahneman, Psychologist & Nobel Laureate, has this to say about managing bias in human decision-making. 

“When making decisions, think of options as if they were candidates. Break them up into dimensions and evaluate each dimension separately. Then – delay forming an intuition too quickly. Instead, focus on the separate points, and when you have the full profile, then you can develop your intuition.”  

Regarded as the father of behavioural economics, after 5 decades of research he has concluded that the research is unequivocal: When it comes to decision-making, algorithms are superior to people

For further reading on how AI can remove bias in recruitment, download our whitepaper here.

It’s now well established that a wider talent pool means more opportunities for recruiting diverse candidates and this results in higher returns, increased productivity, and creativity benefit companies with a diverse workforce. The issue isn’t that we need these thighs to be proven anymore, but rather that nothing we’ve been doing to create the change we need has worked. 

Though well-intentioned, DEI has not delivered. Companies have been motivated by the optics of their DEI programmes rather than taking consequential actions to bring about change. Unconscious bias training has been proven ineffective because it cannot address the systemic issues that lead to bias in the first place.

Companies have also spent large sums of money and resources improving their cultures that celebrate belonging, but neglecting their recruitment metrics because they excuse lack of diverse talent as a ‘pipeline problem’.

To address this we need to do something radical. Because what we are doing just isn’t working. 

This is where Ai is, where the power of technology can really have a positive impact on the world. 

You need to find undiscovered talent. 

What is undiscovered talent?

Undiscovered talent is the talent that you overlook when using traditional hiring practices that rely on CVs, which are limited in communicating real skills, and job interviews, which are beset with bias and limited in their insight. By using radical new talent intelligence that uncovers people for their job fit, based on science-backed insights, you start to uncover undiscovered talent. These are people who might have been dismissed because of things like age, past experience, ethnicity, gender or other preconceptions and biases that we have about who we think is a good fit for a job.

Our technology has uncovered some amazing talent for the companies that we work with, that they would have otherwise missed out on. This is a massive advantage when it comes to making an impact on this issue.

This is how we start to move the dial on Diversity, Equity and Inclusion. 

Want to know if technology can give everyone a fair go?

____________________

We cover this and so much more in our report: Hiring for Equality. Download the report here.

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.