Health Insurance Claim Prediction Using Artificial Neural Networks

Abstract

A number of numerical practices exist that actuaries use to predict annual medical claim expense in an insurance company. This amount needs to be included in the yearly financial budgets. Inappropriate estimating generally has negative effects on the overall performance of the business. This study presents the development of artificial neural network model that is appropriate for predicting the anticipated annual medical claims. Once the implementation of the neural network models was finished, the focus was to decrease the mean absolute percentage error by adjusting the parameters, such as epoch, learning rate, and neurons in different layers. Both feed forward and recurrent neural networks were implemented to forecast the yearly claims amount. In conclusion, the artificial neural network model that was implemented proved to be an effective tool for forecasting the anticipated annual medical claims for BSP Life. Recurrent neural network outperformed the feed forward neural network in terms of accuracy and computation power required to carry out the forecasting.

Random forest regression with hyper parameter tuning for medical insurance premium prediction

“…Because of the proliferation of data and developments in business intelligence, the review process may be automated to speed up submissions or programmes. The research in [4] sought to identify methods to apply prediction insights to assess risk analysis for health insurance businesses. The study made use of a data set including over a hundred anonymized features.…”

Primary Mobile Image Analysis of Human Intestinal Worm Detection

“…The concept takes three forms, thus, image pre-processing, feature extractions (Gupta & Shanker, 2021;Aggarwal, Mittal, & Bali, 2021), and classification (Lim, 1990;Jahne, 2005). Techniques adapting these fundamentals concepts in the diagnosis of intestinal worm depending on the characteristic of the dataset are artificial neural networks (Yang, Park, Kim, Choi, & Chai, 2001;Goundar, Prakash, Sadal, & Bhardwaj, 2020), adaptive network-based fuzzy inference system (Dogantekin, Yilmaza, Dogantekin, Avcic, & Sengurc, 2008), MultiClass Support Vector Machine classifier (Avci & Varol, 2009;Panda, 2019;Goundar, Sam;Bhardwaj, Akashdeep, 2021), active contours (Gupta, Bharadwaj, & Rastogi, 2021) and Bayesian classification system (Castañon, Fraga, Fernandez, Gruber, & Costa, 2007). Though computational tools are proven to be usual, the story is slightly different with the African context given the type of dataset captured from the community.…”