What question did this study set out to answer?

The aim is to evaluate the predictive performance of traditional statistical methods versus machine learning models in understanding perceived safety in South Africa.

May 10, 2026Open Access

Predictive Accuracy of Statistical and Machine Learning Models on Perceived Feelings of Safety in South Africa

Puntos clave

The aim is to evaluate the predictive performance of traditional statistical methods versus machine learning models in understanding perceived safety in South Africa.
Analysis of secondary data from the Governance, Public Safety, and Justice Survey (2013/2014-2023/2024) with 215,301 observations.
Statistical models (VARMA) and ML models (Random Forest, LightGBM) evaluated for predictive accuracy.
Socio-economic characteristics such as age, sex, province, and income included as predictors.
Machine learning models demonstrated higher predictive accuracy compared to traditional statistical methods.
Random Forest model outperformed LightGBM and VARMA in capturing nonlinear relationships and short-term dynamics.
VARMA models provided the best fit for safety perceptions during the day and after dark, but were less accurate than ML models.

Resumen

This study compares the predictive performance of traditional multivariate time series models and machine learning (ML) techniques in modelling perceived feelings of safety among South African residents. The analysis uses secondary data from the Governance, Public Safety, and Justice Survey conducted by Statistics South Africa, covering 2013/2014 to 2023/2024 and comprising 215,301 observations. Perceived safety while walking alone in the neighbourhood during the day and after dark served as the response variables, while socio-economic characteristics such as age, sex, province, and main source of income were included as predictors. A Vector Autoregressive Moving Average (VARMA) model was estimated alongside Random Forest (RF) and Light Gradient Boosting Machine (LightGBM) algorithms. VARMA (2,2) and VARMA (3,1) provided the best statistical fit for daytime and after-dark safety perceptions, respectively. However, ML models achieved higher predictive accuracy overall, with RF outperforming both LightGBM and VARMA in capturing nonlinear relationships and short-term dynamics. The findings underscore the value of integrating ML into public safety modelling to enhance evidence-based planning and socio-economic policy development in South Africa. Future research should consider integrating higher-frequency and alternative data sources, such as administrative crime statistics and real-time behavioural data to improve model sensitivity and forecasting accuracy.

Leer artículo completoexternamente

Me gusta

Guardar

Ver artículo completo