Salifort Motors - EXECUTIVE SUMMARY

Data Driven Solutions to assist in improving employee retention

https://rodders.me/projects/salifort_project/salifort-motors/

The Salifort HR Project Overview

Data driven suggestions towards improving employee retention

Objective

Using data analytics and machine learning to identify key factors to predict future attrition

Methodology

Develop a machine learning model to identify predictors of employee departure

Key Findings from Data Analysis

Main Predictors of Turnover

  • Low or medium employee satisfaction scores.
  • Working hours exceeding 175 per month.
  • Imbalance in project assignments and salary levels.

Model Performance and Predictions

Model Accuracy

Probability Model Accuracy
High Risk >90% 72%
Medium Risk > 70% 91%
General Risk >50% 92%

Current Risk Assessment:

67 employees identified above low risk, with 12 at high risk and 33 at medium risk.

Strategic Importance

Impact of Turnover

High costs associated with recruiting and training, alongside potential damage to company culture and employee morale.

Industry Benchmark

Aiming for a 10% turnover rate versus the current average of 20% in comparable industries.

Retention Goals

Enhance employee engagement to build a more stable workforce

Proposed Retention Strategies

Professional Development Recognition Programs
Training and development programs Recognition of
commitment and excellence
Compensation and Benefits Work Environment
Ensure competitiveness
and fairness 		Flexible working to accommodate employee needs

Next Steps and Recommendations

  • Review and adjust policies affecting at-risk employees

  • Enhance data collection for more accurate modeling, including start/end dates and specific reasons for leaving.

Long-term Strategy

  • Regular reviews and updates to retention strategies based on ongoing data analysis and industry trends.
  • Establish a schedule for follow-up meetings and updates to monitor progress and adapt strategies as needed.

Closing Note

Acknowledgment of Limitations

  • While the predictive model provides valuable insights, it does not capture the full complexity of individual motivations and behaviors.

  • Continuous engagement and adaptation of strategies are essential for success