To build adequate predictive models, a substantial amount of data is desirable. However, when expanding to new or unexplored territories, this required level of information is rarely always available. To build such models, actuaries often have to: procure data from local providers, use limited unsuitable industry and public research, or rely on extrapolations from other better-known markets. Another common pathology when applying machine learning techniques in actuarial domains is the prevalence of imbalanced classes where risk events of interest, such as mortality and fraud, are under-represented in data.

In this work, we show how an implicit model using the Generative Adversarial Network (GAN) can alleviate these problems through the generation of adequate quality data from very limited or highly imbalanced samples. This presentation will provide an introduction to GANs and how they are used to synthesize data that accurately enhance the data resolution of very infrequent events and improve model robustness. Overall, we show a significant superiority of GANs for boosting predictive models when compared to competing approaches on benchmark data sets.

Practical Outcomes:

• Thorough theoretical, empirical and practical applications of GANs, with possible leverage in actuarial science for inter alia new sample creation, data augmentation, boosting actuarial models, anomaly detection, missing data imputation, time series simulations and projections in life insurance, short-term insurance, health and care, banking, investment, enterprise risk management, and other non-traditional actuarial areas, such as telecommunications, economics, medicine, engineering, and other wider fields.
• Essentially, show that synthetic data generated using GANs can augment imbalanced data sets, leading to significantly higher predictive power of possible actuarial models fitted after.