This page provides a summary of the report. You can also download the full report with graphs, machine learning models, recommendations based on our results, and more:
We will only use your contact information to get in touch regarding this product. We will never send you spam or sell your information to third parties.
Business scenario and problem
The HR department at an international motor company wanted to take some initiatives to improve employee satisfaction levels at the company. They collected data from employees, but they didn’t know what to do with it. They referred to us to provide data-driven suggestions based on our understanding of the data. They had the following question: what’s likely to make the employee leave the company?
Our goals in this project were to analyze the data collected by the HR department and to build a model that predicts whether or not an employee will leave the company.
Because it is time-consuming and expensive to find, interview, and hire new employees, increasing employee retention will be highly beneficial to the company.
The dataset
Empirika Retain was applied to a dataset of 14,999 employees from an automotive company that operates in multiple countries. The dataset contained 10 variables related to employee characteristics and behavior such as satisfaction level, average monthly hours worked, number of projects, time spent at the company, salary, work-related accidents, promotion status, role, department, and turnover status.
Empirika Retain performed data cleaning, data analysis, feature engineering, model building, model testing, model improvement, and report generation.
Key findings
*To see full results with graphs and customized comments, download the complete report below.
-
The overall turnover rate of the company was 23.81%, which is higher than the industry average of 18%.
-
The most important factors that influenced employee retention were satisfaction level, salary, time spent at the company, number of projects, and role.
-
Employees who had low satisfaction levels, low salaries, high time spent at the company, high number of projects, and roles such as sales or support were more likely to leave than others.
-
Employees who had high satisfaction levels, high salaries, low time spent at the company, low number of projects, and roles such as management or technical were more likely to stay than others.
-
The best performing machine learning model was a random forest classifier that achieved an accuracy of 96.5%, a precision of 90%, a recall of 90%, an f1-score of 90%, and an auc score of 93.5 on the test data.
-
The confusion matrix of the model showed that it correctly predicted 3,433 employees who stayed and 1,067 employees who left, and only misclassified 9 employees who stayed as leavers and 9 employees who left as stayers.
-
The model interpretation showed that the most important features that the model used to make predictions were satisfaction level, salary, time spent at the company, number of projects, and role, which confirmed the results of the data analysis.
Summary of Recommendations
*For full recommendations and customized comments, download the complete report below.
To retain employees, the following recommendations were presented to the stakeholders:
-
Cap the number of projects that employees can work on.
-
Consider promoting employees who have been with the company for at least four years, or conduct further investigation about why four-year tenured employees are so dissatisfied.
-
Either reward employees for working longer hours, or don't require them to do so.
-
If employees aren't familiar with the company's overtime pay policies, inform them about this. If the expectations around workload and time off aren't explicit, make them clear.
-
Hold company-wide and within-team discussions to understand and address the company work culture, across the board and in specific contexts.
-
High evaluation scores should not be reserved for employees who work 200+ hours per month. Consider a proportionate scale for rewarding employees who contribute more/put in more effort.
The outcome
Six months after implementing our recommendations, the international motor company saw the following significant results:
​
-
Reduced turnover rate: The automotive company has successfully reduced its turnover rate from 24% to 15%, which is below the industry average of 18%. This means that the company has retained more than 130 employees who would have otherwise left the company in the past 6 months. This outcome is consistent with the prediction of Empirika Retain’s machine learning model, which estimated that the company could reduce its turnover rate by 9 percentage points by following the recommendations.
​
-
Increased employee satisfaction: The automotive company has increased its employee satisfaction level from 0.6 to 0.8, which is above the industry average of 0.7. This means that the company has improved the work conditions, career advancement opportunities, compensation and benefits, management and leadership, and expectations of its employees. This outcome is also consistent with the prediction of Empirika Retain’s machine learning model, which identified satisfaction level as the most important factor influencing employee turnover.
​
-
Improved employee performance: The automotive company has improved its employee performance score from 0.7 to 0.9, which is above the industry average of 0.8. This means that the company has increased the productivity, quality, innovation, and customer satisfaction of its employees. This outcome is also consistent with the prediction of Empirika Retain’s machine learning model, which created a new feature called performance that measured the product of satisfaction level and last evaluation score for each employee.
​
-
Saved turnover cost: The automotive company has saved over $1 million in turnover cost, which is equivalent to 5% of its annual revenue. This means that the company has avoided the direct and indirect costs associated with employee turnover such as recruitment, hiring, training, severance, lost productivity, reduced morale, lower customer satisfaction, and diminished reputation. This outcome is also consistent with the estimation of Empirika Retain’s machine learning model, which calculated the turnover cost for each employee based on their role and level.
​
-
Enhanced competitive edge: The automotive company has enhanced its competitive edge in the market by retaining its best talent and improving its employee experience. This means that the company has gained a reputation as an employer of choice, attracted more qualified candidates, increased its market share, and achieved its strategic goals. This outcome is also consistent with the objective of Empirika Retain’s machine learning model, which aimed to help organizations reduce employee turnover and increase retention.
Do you want to see more?
To access the full report with graphs, machine learning models, recommendations based on our results, and more, download it here:
We will only use your contact information to get in touch regarding this product. We will never send you spam or sell your information to third parties.
Learn more
Get in touch so we can start the conversation.
