Assessing the sustainability of General Insurance Business through Real Time Monitoring of KPIs using Recurrent Neural Network
Creators
- 1. Doctorial Research Scholar, Department of Mathematics and Computer Science, Sri Sathya Sai Institute of Higher Learning, Puttaparthi,, India
- 2. Master's Student, Department of Mathematics and Computer science, Sri Sathya Sai Institute of Higher Learning, Puttaparthi India
- 3. Senior Tech Actuarial Consultant, Hon. Professor in Department of Mathematics and Computer Science, Sri Sathya Sai Institute of Higher Learning Puttaparthi, India
- 4. , Visiting faculty, Sri Sathya Sai Institute of Higher Learning, Puttaparthi, India
- 5. Associate Professor, Department of Mathematics and Computer Science, Sri Sathya Sai Institute of Higher Learning, Puttaparthi, India
Contributors
- 1. Publisher
Description
Acompany’s sustainability is driven significantly by its operational efficiency. Operational efficiency plays a significant role in the growth and the profitability of a company. Thus, operational efficiency of a company forms the basis for the metrics known as the Key Performance Indicators(KPIs). These KPIs bridge the concept of performance an operation and a means to measure the same quantitatively. In this work, we used Recurrent Neural Network (RNN) with the Long Short Term Memory(LSTM) cells for projecting the public disclosure data of select General Insurance(GI) companies operating in India to the future. We use this data to calculate the KPIs pertaining to the operations of general insurance companies and calculate how the operations of the GI company affect its performance at various levels. Since this analysis is done for the projected data, we get a framework to assess the sustainability of the GI companies by monitoring these KPIs in real-time. The complex RNN and LSTM algorithms were implemented with the help of the Google Colaboratory platform by using the GPUs of the Google Hardware with the help of the Cloud Computing framework.
Files
C4679099320.pdf
Files
(771.8 kB)
Name | Size | Download all |
---|---|---|
md5:e8148b011675b3acbf56b1a8cbde9d7f
|
771.8 kB | Preview Download |
Additional details
Related works
- Is cited by
- Journal article: 2277-3878 (ISSN)
Subjects
- ISSN
- 2277-3878
- Retrieval Number
- 100.1/ijrte.C4679099320