Related Concept Videos
Survival Tree
Building a Survival Tree
Constructing a...
Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
Multiple Regression
Farmers can use multiple regression to determine the crop yield based on more than one factor, such as water availability, fertilizer, soil properties, etc. Here, the crop yield is the response or dependent variable as it depends on the other independent variables. The analysis requires the construction of a scatter plot...
Microsoft Excel: Regression Analysis
To perform regression...
Variation
When independent and dependent variables are plotted on a scatter plot, the slope of a line is a value that describes the rate of change between the two...
Regression Toward the Mean
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Using machine learning-based binary classifiers for predicting organizational members' user satisfaction with collaboration software.
What is holding back business process virtualization in the post-COVID-19 era? Based on process virtualization theory (PVT).
Related Experiment Video
Updated: Jul 5, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
Developing an advanced prediction model for new employee turnover intention utilizing machine learning techniques.
Jungryeol Park1, Yituo Feng2, Seon-Phil Jeong3
1Technology Policy Research Division, Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea.
High turnover among new college graduates is a growing concern. This study uses machine learning to predict turnover intention, finding job security is a key factor, outperforming traditional predictors.
Area of Science:
- Organizational Behavior
- Human Resource Management
- Data Science
Background:
- Intensifying turnover among new college graduates poses significant financial challenges for businesses due to recruitment and training costs.
- Previous studies identified factors influencing turnover intention but lacked predictive power for actual job changes.
- Effective identification and management of new employees at risk of turnover are crucial for organizational stability.
Purpose of the Study:
- To develop a machine learning-based model for predicting the turnover intention of new college graduates.
- To overcome the limitations of traditional econometric models in predicting employee turnover.
- To identify key predictors of turnover intention in early-career professionals.
Main Methods:
- Utilized data from the Korea Employment Information Service's Job Movement Path Survey for college graduates.
- Employed Ordinary Least Squares (OLS) regression to analyze predictor influences.
- Implemented machine learning classifiers including Logistic Regression (LR), K-Nearest Neighbor (KNN), and Extreme Gradient Boosting (XGB) for model learning and classification.
Main Results:
- Job security emerged as the most significant predictor of turnover intention, surpassing traditional factors like workload importance and major relevance.
- The Extreme Gradient Boosting (XGB) model achieved the highest prediction accuracy at 78.5%.
- Demonstrated a diminished or reversed influence of certain traditional factors on turnover intention compared to previous research.
Conclusions:
- Machine learning models, particularly XGB, offer a significant advancement in predicting new graduate turnover intention.
- Job security and organizational satisfaction are critical factors for retaining early-career talent.
- Organizations should re-evaluate traditional factors influencing turnover and prioritize job security to improve retention strategies.

