Improving Insurance Catastrophic Data with Resampling and GAN Methods
This work addresses data quality issues for insurers dealing with catastrophic events, but it appears incremental as it combines existing resampling and GAN techniques.
The paper tackled the problem of improving insurance catastrophic data quality by proposing three methods based on bootstrap, bootknife, and GAN algorithms, and found that these methods reduced errors in simulations, with specific MSE and MAA improvements noted in experiments.
The precise and large dataset concerning catastrophic events is very important for insurers. To improve the quality of such data three methods based on the bootstrap, bootknife, and GAN algorithms are proposed. Using numerical experiments and real-life data, simulated outputs for these approaches are compared based on the mean squared (MSE) and mean absolute errors (MAE). Then, a direct algorithm to construct a fuzzy expert's opinion concerning such outputs is also considered.