Neighbouring prediction for mortality
We propose a new neighbouring prediction model for mortality forecasting. For each mortality rate at age x in year t, mx,t, we construct an image of neighbourhood mortality data around mx,t, that is, Ꜫmx,t (x1, x2, s), which includes mortality information for ages in [x-x1, x+x2], lagging k years (1...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/155461 |
| _version_ | 1811692146605948928 |
|---|---|
| author | Wang, Chou-Wen Zhang, Jinggong Zhu, Wenjun |
| author2 | Nanyang Business School |
| author_facet | Nanyang Business School Wang, Chou-Wen Zhang, Jinggong Zhu, Wenjun |
| author_sort | Wang, Chou-Wen |
| collection | NTU |
| description | We propose a new neighbouring prediction model for mortality forecasting. For each mortality rate at age x in year t, mx,t, we construct an image of neighbourhood mortality data around mx,t, that is, Ꜫmx,t (x1, x2, s), which includes mortality information for ages in [x-x1, x+x2], lagging k years (1 ≤ k ≤ s). Combined with the deep learning model – convolutional neural network, this framework is able to capture the intricate nonlinear structure in the mortality data: the neighbourhood effect, which can go beyond the directions of period, age, and cohort as in classic mortality models. By performing an extensive empirical analysis on all the 41 countries and regions in the Human Mortality Database, we find that the proposed models achieve superior forecasting performance. This framework can be further enhanced to capture the patterns and interactions between multiple populations. |
| first_indexed | 2024-10-01T06:31:09Z |
| format | Journal Article |
| id | ntu-10356/155461 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:31:09Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1554612023-05-19T07:31:18Z Neighbouring prediction for mortality Wang, Chou-Wen Zhang, Jinggong Zhu, Wenjun Nanyang Business School Business::General Mortality Forecasting Neighbourhood Effect We propose a new neighbouring prediction model for mortality forecasting. For each mortality rate at age x in year t, mx,t, we construct an image of neighbourhood mortality data around mx,t, that is, Ꜫmx,t (x1, x2, s), which includes mortality information for ages in [x-x1, x+x2], lagging k years (1 ≤ k ≤ s). Combined with the deep learning model – convolutional neural network, this framework is able to capture the intricate nonlinear structure in the mortality data: the neighbourhood effect, which can go beyond the directions of period, age, and cohort as in classic mortality models. By performing an extensive empirical analysis on all the 41 countries and regions in the Human Mortality Database, we find that the proposed models achieve superior forecasting performance. This framework can be further enhanced to capture the patterns and interactions between multiple populations. Ministry of Education (MOE) Nanyang Technological University Accepted version Wang acknowledges the support of MOST (107-2410-H-110-010-MY3). Zhang thanks the research funding support from the Nanyang Technological University Startup Grant (04INS000509C300) and the Ministry of Education Academic Research Fund Tier 1 Grant (RG55/20). Zhu also thanks the research funding support from the Nanyang Technological University Start-Up Grant (04INS000384C300), Singapore Ministry of Education Academic Research Fund Tier 1 (RG143/19), and the Society of Actuaries Education Institution Grant. 2022-03-02T02:00:45Z 2022-03-02T02:00:45Z 2021 Journal Article Wang, C., Zhang, J. & Zhu, W. (2021). Neighbouring prediction for mortality. ASTIN Bulletin: The Journal of the IAA, 51(3), 689-718. https://dx.doi.org/10.1017/asb.2021.13 0515-0361 https://hdl.handle.net/10356/155461 10.1017/asb.2021.13 3 51 689 718 en 04INS000509C300 RG55/20 04INS000384C300 RG143/19 ASTIN Bulletin: The Journal of the IAA © 2021 The Author(s). Published by Cambridge University Press on behalf of The International Actuarial Association.. All rights reserved. This paper was published in ASTIN Bulletin: The Journal of the IAA and is made available with permission of The Author(s). application/pdf |
| spellingShingle | Business::General Mortality Forecasting Neighbourhood Effect Wang, Chou-Wen Zhang, Jinggong Zhu, Wenjun Neighbouring prediction for mortality |
| title | Neighbouring prediction for mortality |
| title_full | Neighbouring prediction for mortality |
| title_fullStr | Neighbouring prediction for mortality |
| title_full_unstemmed | Neighbouring prediction for mortality |
| title_short | Neighbouring prediction for mortality |
| title_sort | neighbouring prediction for mortality |
| topic | Business::General Mortality Forecasting Neighbourhood Effect |
| url | https://hdl.handle.net/10356/155461 |
| work_keys_str_mv | AT wangchouwen neighbouringpredictionformortality AT zhangjinggong neighbouringpredictionformortality AT zhuwenjun neighbouringpredictionformortality |