The True Cost of Employee Turnover - Part Two.

My last looked at the potential cost of turnover to the organisation. The post resonated with some people, so discussing how we can predict turnover and possibly take preventative measures to manage turnover may be beneficial. It is essential to mention that not all turnover is bad turnover; the focus here is regrettable turnover. Some call regrettable turnover, dysfunctional turnover.   


It goes without saying predicting employee turnover is complex, considering the various factors that impact turnover. Factors include salary structure, work-life balance, job satisfaction, comfort in the working environment, and relationships with supervisors. These factors are variables that can be used to identify employees at risk of leaving the organisation. This is where HR analytics comes into its own. To predict turnover, four main types of HR analytics can help us predict turnover.   

1. Descriptive Analytics: This type of analytics focuses on what has happened in the past. It uses data aggregation and data mining techniques to provide insight into the past and answer: "What has happened?". Data such as retention rate, turnover rate, average tenure within business units and roles, and internal mobility within the organisation are valuable metrics. This set of metrics focuses on the general data patterns and distributions of turnover in an organisation.
      
2. Diagnostic Analytics: Diagnostic analytics is a form of advanced analytics that examines data or content to answer the question, "Why did it happen?" and is characterised by techniques such as drill-down, data discovery, data mining, and correlations. Data such as reasons for leaving, where they are going to, in terms of the type of employer and location, job level, age, length of tenure in the role at the time of departure, length of tenure in the organisation, travel distance and whether or not they relocated for the role, performance reviews, relationship with management, the condition of the external labour market, the talent market for the positions etc. This set of metrics focuses on the leavers and understanding the individual drivers for their exit.
   
   
3. Predictive Analytics: Predictive analytics uses statistical models and forecasting techniques to understand the future. It uses various techniques from data mining, machine learning, and artificial intelligence to analyse current data and predict the future. Using all the information identified in the descriptive and diagnostic phase, employee behaviour can be predicted. Models such as decision trees or other complex machine learning algorithms are used for classification and regression (Support Vector Machines and Random Forest). You may need the help of your business intelligence team here as intermediate statistics are involved. Predictive analytics helps to identify what factors influence resignations. Based on this data, you may successfully target and decide your retention strategy, which is not based on gut feeling or anecdote.   
   
   
4. Prescriptive Analytics: Prescriptive analytics prescriptive is used to suggest various strategies to reduce employee turnover based on the results of predictive analytics. It goes beyond predicting future outcomes by suggesting actions to benefit from the predictions and showing the decision maker the implications of each decision option. It uses techniques like algorithms, machine learning, and computational modelling procedures. Prescriptive analytics helps to reduce the rate of resignations by identifying and ranking all of the factors that contribute to resignations in real-time. It also helps to retain high-performing or critical employees by comparing resignation rates across positions, locations, tenure, age groups, diversity, and other groups.  Even though valuable insights can be gained through this method, considerations must be given to the unique context and constraints of the organisation.  
   
   
   

A note of caution here, the methods described above don't give us a fail-proof approach for dealing with turnover. Sometimes, one outcome may make an employee stay, and another may leave despite the interventions. 


Regardless, organisations should continue to analyse the various motivations for individuals' choices to depart companies and how employees decide these things. It is essential to gain organisational equilibrium by ensuring that the motivating factors it provides (such as adequate salary, pleasant work environment, and growth possibilities) are equivalent to or higher than the sacrifices (time, effort) demanded of the employee.   
​

In conclusion, understanding and managing employee turnover is a complex but necessary task. By leveraging HR analytics and understanding the motivations of employees, organisations can better predict and manage regrettable turnover, leading to a more stable and engaged workforce.  
 

---