This paper describes a variety of approaches used to assess the efficiency of a sample of major insurance companies in Angola between 2003 and 2012. Starting out with the bootstrapping technique, several data envelopment analysis (DEA) estimates were generated, allowing the use of confidence intervals and bias correction in central estimates to test for significant differences in efficiency levels and input‐decreasing/output‐increasing potentials. Previous studies have focused on the measurement and explanation of the factors affecting the performance rather than the prediction. The use of neural networks combined with DEA results as part of an attempt to produce a model for insurance companies’ performance with effective predictive ability is investigated. The findings indicate that older insurance companies with Portuguese origin tend to be more efficient. Results also suggest that opportunities for accommodating future demand appear to be scarce.

No abstract

No abstract