Paper
17 May 2022 Global suicide rates insight and prediction
Zhiyi Sun
Author Affiliations +
Proceedings Volume 12259, 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2022); 122595D (2022) https://doi.org/10.1117/12.2639476
Event: 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing, 2022, Kunming, China
Abstract
Against the background that suicide has become a serious global public health issue, this study is dedicated to analyzing global suicide trends and prediction, so as to provide suggestions for future suicide prevention and treatment. It mainly includes exploratory data analysis, correlation analysis, hypothesis testing, as well as model establishment and prediction. Through the data analysis and statistical hypothesis tests, it can be found that to a certain extent, different suicide populations categorized by sex, age, and generation, the three factors have a very significant impact on the suicide rate. To be precise, men are more likely to commit suicide than women, and 35-54 years and the generation of boomers have the highest number of suicides. In addition, by the hypothesis test, it turns out that there is no significant difference in the suicide rate among the youth in 2015 compared with that in 1985, thirty years past. Moreover, judging from the global suicide rate in 2015, the suicide rate has no significant connection with a country’s GDP or GDP per capita. Overall, the XGBoost model, with a highest Test Accuracy of 0.988 and smallest Test RMSE of 0.134, is the best one for global suicide rate prediction and it may be useful to suicide prevention in the future.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhiyi Sun "Global suicide rates insight and prediction", Proc. SPIE 12259, 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2022), 122595D (17 May 2022); https://doi.org/10.1117/12.2639476
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Data modeling

Performance modeling

Data analysis

Machine learning

Statistical analysis

Computer programming

Detection and tracking algorithms

Back to Top