Introducing effective parameters for predicting job burnout using a self-organizing method based on group method of...

Area of Science:

• Occupational Health
• Artificial Intelligence in Healthcare
• Organizational Psychology

Background:

• The COVID-19 pandemic significantly impacted workers' mental well-being and created unique challenges for startups.
• Understanding the factors contributing to job burnout is crucial for supporting employees in high-pressure startup environments.

Purpose of the Study:

• To analyze the relationship between demographic factors, COVID-19 stress, resilience, and job burnout in startups.
• To develop and validate a predictive model for job burnout using a Group Method of Data Handling (GMDH) neural network.

Main Methods:

• Quantitative methodology involving 384 startup directors and representatives.
• Data collection using the BRCS, MBI-GS, and custom COVID-19 stress assessments.
• Application of a GMDH neural network for feature selection and burnout classification.

Main Results:

• The GMDH neural network effectively identified key predictors of burnout, including marital status, COVID-19 stress, job experience, professional efficiency, gender, age, and resilience.
• The trained network demonstrated high accuracy in classifying job burnout.
• The study successfully reduced computational load by utilizing a parsimonious set of 7 parameters.

Conclusions:

• The GMDH neural network is a powerful tool for accurately predicting job burnout in the startup sector.
• Resilience and COVID-19 related stress are significant factors in determining job burnout among startup professionals.
• The identified key characteristics provide valuable insights for developing targeted interventions to mitigate burnout.