PREDICTION OF FINANCIAL FRAUD RISKS AMONG OLDER ADULTS: THE APPLICATION OF GA-XGBOOST MODEL
2024

Predicting Financial Fraud Risks in Older Adults

publication Evidence: moderate

Author Information

Author(s): Zhao Jin, Li Yuanyuan, Jin Hao, Zhang Xuemin

Primary Institution: Hebei University of Technology, TianJin, Tianjin, China

Hypothesis

Can a GA-XGBoost model accurately identify financial fraud risks among older adults?

Conclusion

The GA-XGBoost model effectively predicts financial fraud risks, highlighting key factors such as education level and loneliness.

Supporting Evidence

  • Lower education level, older age, and loneliness increase financial fraud risks.
  • Increased awareness of rights protection and better sleep quality have protective effects.
  • The model was compared with established machine learning algorithms like LightGBM and Random Forest.

Takeaway

This study created a smart model to help find out who might be tricked into financial scams, especially older people.

Methodology

The study used a genetic algorithm to optimize the XGBoost model for predicting financial fraud risks.

Participant Demographics

Older adults in China, with factors like education level and loneliness considered.

Digital Object Identifier (DOI)

10.1093/geroni/igae098.1396

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication