Reducing Employee's Churn with Predictive Analytics

Analytics
Teradata Employee

Reducing Employee's Churn with Predictive Analytics

Most business leaders would agree that a key to a company’s success is an ongoing stream of happy recurrent customers, willing to invest in the company’s goods and services. The key to achieving customer happiness through guaranteed customer satisfaction is to focus on employee happiness first. Are the employees serving your customers dedicated and happy to be doing so?

In order to make their business a success organization often invest in their employees, to enable them and enhance their capabilities to play pivotal roles in the organization to make business a success. The key to achieving customer satisfaction, happiness and in turn recurrence and loyalty, is to focus on employee satisfaction and happiness first. Organizations these days are thus focusing a few vital players that drive their business and are devising strategies to retain them or make them stay for a longer period.

A leading telecom company in Pakistan realized the importance of employee’s role in business success and took up the task to identify the top performing employees within the organization and predict the possibility of their churn, with the help of predictive analytics. Building on the existing idea, as once quoted by Bill Gates,

“You take away our top 20 employees and we (Microsoft) become a mediocre company”.

 

How we did it?

Based on the data sources, different behavioral traits and trends of employees were identified to establish a baseline foundation. The next step was segment employees based on their performances, engagement activities and contribution towards the organization. Top 10% were marked as High Profile (HiPo) employees, next 60% were marked as Medium and rest as Low respectively. Following the segmentation phase, a predictive solution was designed to identify employees who are likely to churn in upcoming quarter and also those employees who have the potential to become HiPo in the coming year.

 

Insights

One of the interesting insights showed that the biggest chunk of predicted churn is within the first 2 years of employment, which is 23% and the 2nd biggest predicted churn is at 10 to 12 years of employment. It was suggested, to contain the biggest chunk of predicted churn; policies should be devised to retain these employees. Suggestions included; offering different loans and incentives which can bind employees for a longer period or incentives like gratuity which mature after a certain period of time etc.Screen Shot 2019-04-22 at 12.28.51.png

From another standpoint another insight brought to light was that one of the departments was predicted to have the highest churn (28%). Secondly for the same department in question the average predicted churn was an estimated 7 years as opposed to the general organizational trend of predicting a churn within 1-2 years of the employee lifecycle.

Results showed, that predicted churners at the most junior grade Level 1, had gotten less %age of recent increment as compared to the rest of the employees in the same grade. The churn at level 1 was predicted to be 9% at and tenure of predicted churners in Level 1 was less than non-churners by 3.74 years. The churn at level 2 was 10%; employees were predicted to stay longer in Level 2 before churning. The Age of predicted churning employees was lower than average as well. For Level 3, employees who were younge3r than the average age were predicted to churn. Their tenure is was less, and they were given less increments which resulted in a 14% predicted churn for level 3. There was not any significant difference in the variables’ distribution for Level 4 grade but still the highest churn predicted was for this grade; 30%.

Based on the age of employee at the time of joining, the following insights were attained to predict which employee has the potential to become a HiPo.  The biggest chunk of people who have the potential to become a top performer joined at the age between 25 to 28 years. A significant decrease was visible after this age bracket, which depicted the employees at early ages are more career oriented and put in an effort to mark their foot print within the organization. This also shows that employees with a certain amount of prior years of experience have the potential to perform better.Screen Shot 2019-04-22 at 12.38.33.png

Employees joining in from telecom and banking sectors showed potential to become HiPo and employees with Computer software industry background didn’t show potential to become top performers within our analysis.

Most of the employees did join with a certain number of years of experience; major chunk of employees had 4 years or less of experience before joining. These employees showed to have the most potential to grow and become HiPos.

 

Conclusion

The results achieved by the champion model were promising. The predictive trend analysis depicted the actual circumstance of the organization related to employee engagement and attrition. Human Resource department devised policies and strategies to control the employee attrition, by using the analytical model, which in turn brought up the retention policies.

On the other hand, this solution also made the management answerable to justify prominent churn figures under certain managers. The Outcome of the model also highlighted short comings in employee evaluation process.

Collectively, the model increased human resource management awareness within the organization and allowed the management to focus on areas that could prove promising in employee retention and satisfaction.

Faraz Shahid

Accepted Solutions
Teradata Employee

Re: Reducing Employee's Churn with Predictive Analytics

Faraz - this is excellent, have you thought about posting it internally on Connections?  You can also publish blog posts on here...I would recommend posting this as a blog post instead of a forum topic.  Thanks so much for posting it though, very interesting.

1 ACCEPTED SOLUTION
2 REPLIES 2
Teradata Employee

Re: Reducing Employee's Churn with Predictive Analytics

Faraz - this is excellent, have you thought about posting it internally on Connections?  You can also publish blog posts on here...I would recommend posting this as a blog post instead of a forum topic.  Thanks so much for posting it though, very interesting.

Teradata Employee

Re: Reducing Employee's Churn with Predictive Analytics

Thanks for the advice ts. 

Faraz Shahid