A tensor-based approach to cause-of-death mortality modeling

In various situations, a researcher analyses data stored in a matrix. Often, the information is replicated on different occasions that can be time-varying or refer to different conditions. In these situations, data can be stored in a multi-way array or tensor. In this work, using the Tucker4 model, we apply a tensor-based approach to the mortality by cause of death, hence considering data stored in a four-dimensional array. The dataset here considered is provided by the World Health Organization and refers to causes of death, ages, years, and countries. A deep understanding of changing mortality patterns is fundamental for planning public policies. Knowledge about mortality trends by causes of death and countries can help Governments manage their health care costs and financial planning, including public pensions, and social security schemes. Our analysis reveals that the Tucker4 model allows for extracting meaningful demographic insights, which are useful to understand that the rise in survival during the twentieth century was mostly determined by a reduction of the main causes of death.