Proactive Talent Retention Capability using ML and Advanced Analytics
Learn how Intel created a proactive capability to predict employees at risk of attrition, and proactively retain the best talent in the world.
Overall, HR is mainly equipped for reactive talent retention measures. These “dive and catches” are time consuming and generally ineffective.
By empowering HR to support managers with real-time risk signals to determine if proactive measures are needed, and utilise a library of content to generate a targeted approach, the planned actions can be more effective by considering various data inputs, and focusing on highest priority populations to proactively identify where the hotspots are, and who is likely to leave next.
This session will explore:
- Predictive Turnover Industry perspective
- End to end Predictive Turnover Capability Structure - Methodology: CRISP-DM [Cross Industry Standard Process for Data Mining]
- Business cases (Examples)- Methodology: Design Thinking
- Conclusions and Predictive Turnover Capability Evolution.
Learning outcomes:
- Learn (high-level) how to implement a End-to-End Predictive Turnover Capability
- Understand applicability of predictive turnover capability and its relationship with other data signals to define an integrated retention strategy
- Learn how to link predictive turnover capability with non-monetary actions
- Understand how to systematically implement a predictive turnover machine learning model.
Learn how Intel created a proactive capability to predict employees at risk of attrition, and proactively retain the best talent in the world.
Overall, HR is mainly equipped for reactive talent retention measures. These “dive and catches” are time consuming and generally ineffective.
By empowering HR to support managers with real-time risk signals to determine if proactive measures are needed, and utilise a library of content to generate a targeted approach, the planned actions can be more effective by considering various data inputs, and focusing on highest priority populations to proactively identify where the hotspots are, and who is likely to leave next.
This session will explore:
- Predictive Turnover Industry perspective
- End to end Predictive Turnover Capability Structure - Methodology: CRISP-DM [Cross Industry Standard Process for Data Mining]
- Business cases (Examples)- Methodology: Design Thinking
- Conclusions and Predictive Turnover Capability Evolution.
Learning outcomes:
- Learn (high-level) how to implement a End-to-End Predictive Turnover Capability
- Understand applicability of predictive turnover capability and its relationship with other data signals to define an integrated retention strategy
- Learn how to link predictive turnover capability with non-monetary actions
- Understand how to systematically implement a predictive turnover machine learning model.
