A Deep Learning Integrated Cairns-Blake-Dowd (CBD) Sytematic Mortality Risk Model
Autor: | Patrick Weke, Philip Ngare, Joab Odhiambo |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2021 |
Předmět: |
Mortality model
Computer science systematic mortality risk 01 natural sciences 010104 statistics & probability Risk model 0502 economics and business ddc:330 recurrent neural networks Autoregressive integrated moving average 0101 mathematics Network architecture 050208 finance Actuarial science business.industry Deep learning 05 social sciences deep learning Recurrent neural network Cohort effect HD61 Long memory HG1-9999 CBD Risk in industry. Risk management Artificial intelligence business long short-term memory Finance |
Zdroj: | Journal of Risk and Financial Management, Vol 14, Iss 259, p 259 (2021) Journal of Risk and Financial Management Volume 14 Issue 6 |
ISSN: | 1911-8066 1911-8074 |
Popis: | Many actuarial science researchers on stochastic modeling and forecasting of systematic mortality risk use Cairns-Blake-Dowd (CBD) Model (2006) due to its ability to consider the cohort effects. A three-factor stochastic mortality model has three parameters that describe the mortality trends over time when dealing with future behaviors. This study aims to predict the trends of the model, kt(2) by applying the Recurrent Neural Networks within a Short-Term Long Memory (an artificial LSTM architecture) compared to traditional statistical ARIMA (p,d,q) models. The novel deep learning (machine learning) technique helps integrate the CBD model to enhance its accuracy and predictive capacity for future systematic mortality risk in countries with limited data availability, such as Kenya. The results show that Long Short-Term Memory network architecture had higher levels of precision when predicting the future systematic mortality risks than traditional methods. Ultimately, the results can be implemented by Kenyan insurance firms when modeling and forecasting systematic mortality risk helpful in the pricing of Annuities and Assurances. |
Databáze: | OpenAIRE |
Externí odkaz: |