After stock prediction, the most exciting thing to predict for any industry is predicting when the employee is going to leave the company and why? This is a major problem faced by most of the industries today. Currently, many companies are trying to predict attrition using data science and artificial intelligence. Now in this article, we will see how and why we need attrition prediction.
According to a Deloitte study, in FY15, the highest voluntary attrition across sectors was seen in the IT services sector at 21.9%, whereas the lowest was in the energy and natural resources sector at 10.5%.
Need for Attrition analysis:
Organizations face huge costs resulting from employee turnover. Some costs are material such as training costs and the time it takes from when an employee starts to when they become a productive member. However, the most important costs are immaterial. Consider what’s lost when a productive employee quits: new product ideas, great project management, or customer relationships, his network and etc. If this happens on a huge scale in large organizations then organically they will face loss.
IBM’s Attrition analysis:
According to Ginni Rometty IBM receives more than 8,000 resumes a day, but roughly 35,000 workers, know who in the workforce is currently searching for a new position. IBM artificial intelligence technology is now 95 percent accurate in predicting workers who are planning to leave their jobs.
As we can see in the above graph they got this accuracy using many data points like employee job satisfaction, age, job role and etc. AI has so far saved IBM nearly $300 million in retention costs, Ginni Rometty claimed.
Problems faced in Attrition analysis:
It is not always possible for all the companies to collect this huge amount of data about employee and knowing where to draw the privacy line. Also, the work environment is different in each organization. Nowadays building predictive machine learning models is easy because of Auto-ML technologies like h2O, google’s Auto-ML models, etc. But the here the most difficult thing is to collect relevant data about employees which really cause the attrition. Like getting the distance from home or how satisfied employee is? or maybe his passion towards the work is the most challenging thing get. These are the problem faced by the data scientist and HR analytics companies today.
Many startups are trying their luck in HR analytics mainly in attrition and performance management. At Up Your Game we are continuously experimenting for getting the best predictive model for attrition. Getting the best model is directly dependent on the best data and we are collecting data which directly based on employee performance like employee sentiment, employee workload, etc.
Machine learning, Deep learning, and Attrition:
Using sample data provided by IBM simple machine learning ensemble model achieved nearly 95% accuracy. But because ensemble models are hard to interpret. Using deep learning models will more useful for how and why we got the prediction. But again deep learning models need more data otherwise it will cause problems like overfitting and it will end up giving a bad result. So the best thing is to get huge and diverse data and use deep learning models to predict attrition.
From all this analysis we can conclude that the most important thing in attrition prediction is collecting the relevant data which really causes the attrition and how important attrition prediction is for all industries. If you like this article then kindly give claps and if you have any questions please fill free to ask in comments. Until my next blog happy learning.