Sorry, page not found Please enable cookies and refresh the page. HR Analytics Using Machine Learning to Predict Employee Turnover. Employee turnvover attrition is a major cost to an organization, and predicting turnover is at the forefront of needs of Human Resources HR in many organizations. Until now the mainstream approach has been to use logistic regression or survival curves to model employee attrition. However, with advancements in machine learning ML, we can now get both better predictive performance and better explanations of what critical features are linked to employee attrition. In this post, well use two cutting edge techniques. First, well use the h. BI 41SL PAM v11. 214. Semantic Layer Relationally Exposed DATA SOURCES Product Release. FREE automatic machine learning algorithm, h. ML accuracy. Then well use the new lime package that enables breakdown of complex, black box machine learning models into variable importance plots. We cant stress how excited we are to share this post because its a much needed step towards machine learning in business applications Enjoy. Employee Attrition A Major Problem. Bill Gates was once quoted as saying,You take away our top 2. Microsoft become a mediocre company. His statement cuts to the core of a major problem employee attrition. An organization is only as good as its employees, and these people are the true source of its competitive advantage. Organizations face huge costs resulting from employee turnover. Some costs are tangible such as training expenses and the time it takes from when an employee starts to when they become a productive member. However, the most important costs are intangible. Consider whats lost when a productive employee quits new product ideas, great project management, or customer relationships. With advances in machine learning and data science, its possible to not only predict employee attrition but to understand the key variables that influence turnover. Well take a look at two cutting edge techniques Machine Learning with h. This function takes automated machine learning to the next level by testing a number of advanced algorithms such as random forests, ensemble methods, and deep learning along with more traditional algorithms such as logistic regression. The main takeaway is that we can now easily achieve predictive performance that is in the same ball park and in some cases even better than commercial algorithms and MLAI software. Feature Importance with the lime package The problem with advanced machine learning algorithms such as deep learning is that its near impossible to understand the algorithm because of its complexity. This has all changed with the lime package. Install Microsoft Excel 15.0 Object Library' title='Install Microsoft Excel 15.0 Object Library' />To install TextCSVXS, simply copy and paste either of the commands in to your terminal. TextCSVXS. CPAN shell. MCPAN e shell install. Original release date November 27, 2017 The USCERT Cyber Security Bulletin provides a summary of new vulnerabilities that have been recorded by the National. The major advancement with lime is that, by recursively analyzing the models locally, it can extract feature importance that repeats globally. What this means to us is that lime has opened the door to understanding the ML models regardless of complexity. KB/vb/WordAutomationPart1/Word_Demo.jpg' alt='Install Microsoft Excel 15.0 Object Library' title='Install Microsoft Excel 15.0 Object Library' />Now the best and typically very complex models can also be investigated and potentially understood as to what variables or features make the model tick. Employee Attrition Machine Learning Analysis. With these new automated ML tools combined with tools to uncover critical variables, we now have capabilities for both extreme predictive accuracy and understandability, which was previously impossible Well investigate an HR Analytic example of employee attrition that was evaluated by IBM Watson. IBM Watson Where we got the dataThe example comes from IBM Watson Analytics website. You can download the data and read the analysis here To summarize, the article makes a usage case for IBM Watson as an automated ML platform. The article shows that using Watson, the analyst was able to detect features that led to increased probability of attrition. Automated Machine Learning What we did with the dataIn this example well show how we can use the combination of H2. O for developing a complex model with high predictive accuracy on unseen data and then how we can use LIME to understand important features related to employee attrition. Packages. Load the following packages. Load the following packages. Loads tidyverse and several other pkgs. Super simple excel reader. Professional grade ML pkg. Explaincomplexblack box. MLmodels. Data. Download the data here. You can load the data using readexcel, pointing the path to your local file. Read excel data. WAFn Use. C HR Employee Attrition. Lets check out the raw data. Its 1. 47. 0 rows observations by 3. The Attrition column is our target. Well use all other columns as features to our model. View first 1. First 1. Age. Attrition. Business. Travel. Daily. Rate. Department. Distance. From. Home. Education. Education. Field. Employee. Count. Employee. Number. Environment. Satisfaction. Gender. Hourly. Rate. Job. Involvement. Job. Level. Job. Role. Job. Satisfaction. Marital. Status. Monthly. Income. Monthly. Rate. Num. Companies. Worked. Over. 18. Over. Time. Percent. Salary. Hike. Performance. Rating. Relationship. Satisfaction. Standard. Hours. Stock. Option. Level. Total. Working. Years. Training. Times. Last. Year. Work. Life. Balance. Years. At. Company. Years. In. Current. Role. Years. Since. Last. Promotion. Years. With. Curr. Manager. Yes. TravelRarely. Sales. 12. Life Sciences. Female. 94. 32. Sales Executive. Single. 59. 93. 19. YYes. 11. 31. 80. No. TravelFrequently. Research Development. Life Sciences. 12. Male. 61. 22. Research Scientist. Married. 51. 30. 24. YNo. 23. 44. 80. 11. Yes. TravelRarely. Research Development. Other. 14. 4Male. Laboratory Technician. Single. 20. 90. 23. YYes. 15. 32. 80. No. TravelFrequently. Research Development. Life Sciences. 15. Female. 56. 31. Research Scientist. Married. 29. 09. 23. YYes. 11. 33. 80. No. TravelRarely. Research Development. Medical. 17. 1Male. Laboratory Technician. Married. 34. 68. 16. YNo. 12. 34. 80. 16. No. TravelFrequently. Research Development. Life Sciences. 18. Male. 79. 31. Laboratory Technician. Single. 30. 68. 11. YNo. 13. 33. 80. 08. No. TravelRarely. Research Development. Geometry Dash Game Engine on this page. Medical. 11. 03. Female. Laboratory Technician. Married. 26. 70. 99. YYes. 20. 41. 80. No. TravelRarely. Research Development. Life Sciences. 11. Male. 67. 31. Laboratory Technician. Divorced. 26. 93. YNo. 22. 42. 80. 11. No. TravelFrequently. Research Development. Life Sciences. 11. Male. 44. 23. Manufacturing Director. Single. 95. 26. 87. YNo. 21. 42. 80. 01. No. TravelRarely. Research Development. Medical. 11. 33. Male. Healthcare Representative. Married. 52. 37. 16. YNo. 13. 32. 80. 21. The only pre processing well do in this example is change all character data types to factors. This is needed for H2. O. We could make a number of other numeric data that is actually categorical factors, but this tends to increase modeling time and can have little improvement on model performance. Attrition,everythingLets take a glimpse at the processed dataset. We can see all of the columns. Note our target Attrition is the first column. Observations 1,4. Variables 3. 5. Attrition Yes, No, Yes, No, No, No, No, N. Age 4. Business. Travel TravelRarely, TravelFrequentl. Daily. Rate 1. Department Sales, Research Development,. Distance. From. Home 1, 8, 2, 3, 2, 2, 3, 2. Education 2, 1, 2, 4, 1, 2, 3, 1, 3, 3, 3. Education. Field Life Sciences, Life Sciences, O. Employee. Count 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1. Employee. Number 1, 2, 4, 5, 7, 8, 1. Environment. Satisfaction 2, 3, 4, 4, 1, 4, 3, 4, 4, 3, 1. Gender Female, Male, Male, Female, Mal.