Better Ways To Predict Who Is Going To Leave Your Organisation

Better Ways To Predict Who Is Going To Leave Your Organisation


Employee turnover directly affects the income and productivity of businesses. For instance, the estimated cost of a lost employee earning $8 an hour at a retail chain store is $3,500 to $25,000, according to the magazine "Organization Science". Aspects that contribute to this include hiring expenses, training labor, sales lost and productivity lost. Clearly, the effect of the sales can be much higher depending on the sector, the status of the employee and the salary.

Major predictors of staff turnover are demographic variables.  You already have enough data within your organisation to run a turnover prediction model. With this data, you can predict which employee is likely to leave your organisation and when.

 

Companies understand that the turnover of workers is costly and destructive. And they know that retaining their best and brightest employees not only helps them save money but helps maintain competitive advantages as well as protecting cognitive capital.

 

Advertisment

Nonetheless, most retention measures are focused on two retrospective methods. Firstly, exit interviews are performed to better understand why people have chosen to leave the organisation, though by this point, it is usually too late to rely on them. Second, annual employee engagegent surveys are used to assess engagement. These results of the survey are later compared to people who left the organization, hoping they will yield any appropriate departure predictors. The major issue is that such data don't give managers a real-time picture about who might be thinking about leaving the organisation.

 

Harvard Business School conducted a research that centered on using big data and machine-learning algorithms to build an individual's turnover propensity index. Their model was an indicator in real time of who's probably thinking about quitting. Harvard Business School has grounded the development of these predictive models in academic turnover research and has carried out a series of studies afterwards. The results of Harvard Business School show that it is possible to develop indices which predict a person's likelihood of considering an external offer in real time and eventually leaving the firm.

 

Past research points to two main reasons why people leave their jobs. The reasons are turnover shocks and low job embeddedness. Turnover shocks are incidents that cause people to reconsider staying with the company. Many surprises are organizational, and others are personal (e.g. getting a job offer from outside). Work embedding is when people are intimately connected to an organization. If people don't believe their job matches well with their interests, skills and beliefs, they have low job embeddedness and are a higher risk of flight.

 

Harvard Business School partnered with a talent intelligence firm to gather a large sample of freely available corporate data on possible attrition. They also collected personal factors tied to embeddedness that were in the public domain, such as the number of past jobs, anniversary of employment and tenure, skills, education, gender, and geography. They accumulated these potential turnover indicators across various organisations and industries for more than 500,000 individuals working in the U.S.

 

Based on an assessment of these turnover factors by Harvard Business School, they used machine learning to classify each individual as unlikely, less likely, more likely, or more likely to be receptive to new job opportunities. A turnover propensity index (TPI) score was given to each individual in their sample, and then they conducted two studies to see how well this score predicted their openness to outside opportunities and their likelihood of quitting.

 

First, Harvard Business School wanted to see how well the TPI predicted openness to recruitment messagesHarvard Business School sent e-mail invitations to a smaller sample of 2,000 employed individuals who had been identified by their algorithm as unlikely, less likely, more likely, or highly likely to be receptive to an invitation to view available jobs tailored to their specific skills and interests. Of the 2,000 employees, 1,473 received the e-mail; 161 opened the invitation; and 40 clicked through. Harvard Business School find out that those who were rated as “most likely” to be receptive opened the e-mail invitation at more than twice the rate of those rated as least likely (5.0% versus 2.4%). Additionally, among those who opened the email, those rated as “most likely” to be receptive were significantly more likely to click through it. This suggests that Harvard Business School TPI score could identify employees at greater risk of leaving. This finding also suggests that companies can strategically target top talent that might be more open to an outside offer – remember this all came from publicly available data.

 

Second, to look at the TPI score's ability to predict actual turnover, Harvard Business School used the rest of the 500,000-person sample. Over a three-month time period, those identified as “most likely” to be receptive to new opportunities were 63% more likely to change jobs, as compared to those who were “unlikely” to be receptive. Those identified as “more likely” were 40% more likely to quit.

 

Harvard Business School's work in this area demonstrates that organisations can track turnover propensity indicators by using big data, and identify employees who may be at high risk of leaving the organisation. This proactive anticipation may enable leaders to intervene in order to increase the chances of retaining top talent. In addition, organisations have a considerable advantage over external researchers in developing their own TPI using internal data. Organisational shocks such as litigation or regulatory actions can be anticipated by companies. Organisations have access to other turnover shock data as well as publicly available data, such as job anniversaries, new educational qualifications and birth or wedding announcements, although they have to be vigilant not to breach employee privacy. And firms can track factors that signal embedded employment, such as participation in career development opportunities, initiatives for organisational improvement, or peer recognition programs.

 

Companies that are committed to data-driven decision-making will need to make an investment in the careful collection and analysis of the right turnover risk indicators. Then their leaders can proactively engage valued employees at risk of leaving through interviews to understand better how the company can increase their chances of staying.

 

Taurai Masunda is a Business Analytics Consultant at Industrial Psychology Consultants (Pvt) Ltd a management and human resources consulting firm. https://www.linkedin.com/in/taurai-masunda-b3726110b/ Phone +263 4 481946-48/481950/2900276/2900966 or cell number +263 779 320 189 or email: taurai@ipcconsultants.com  or visit our website at www.ipcconsultants.com


Taurai Masunda
Guest
This article was written by Taurai a Guest at Industrial Psychology Consultants (Pvt) Ltd

Related Articles





Notifications

Sign up now to get updated on latest posts and relevant career opportunities