Health Insurance Claim Prediction Using Artificial Neural Networks

Goundar, Sam; Prakash, Suneet; Sadal, Pranil; Bhardwaj, Akashdeep

doi:10.4018/ijsda.2020070103

Cited by 22 publications

(13 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A similar approach to ours is done by Olszowy (2013), which advocated that gross written premiums in the Polish insurance market follow a seasonal pattern and thus can be modeled by a SARIMA(0,1,2)(1,0,0,4) model. Contrary to classic time series methods, Goundar et al (2020) study the predictability of medical claims through artificial neural networks (ANN), confirming their effectiveness in forecasting. Contrary to our approach, Quan and Valdez (2018) find that multivariate tree models marginally outperform univariate tree models for insurance claims.…”

Section: Literature Reviewmentioning

confidence: 94%

Is the Claims Ratio Dynamic Predictable? A Study of the Macedonian Non-Life Insurance Sector

Peovski,

Ivanovski

2023

Proceedings of the International Conference "Economic and Business Trends Shaping the Future"

View full text Add to dashboard Cite

Insurance, simplified to a risk management concept, offers protection against unexpected losses arising from adverse events. As a financial service of structural importance in modern economies, it requires specific attention due to its risk protection component. Consequently, insurance companies devote sufficient resources towards stable, resilient, and profitable operations. However, a scarce amount of research treats the topic of financial stability maintenance and claims management with even fewer studies dealing with its prediction. This study deals with claims ratio (CR) dynamics in the Macedonian non-life insurance sector and its prediction. Utilizing a data set of 138 monthly observations between January 2012 and June 2023, this paper models the CR indicator through multiple approaches i.e., naïve, ARIMA, ETS exponential smoothing, and random forest (RF) thus making suitability and accuracy comparisons. Results suggest that the SARIMA(4,0,2)(2,1,2,12) model is superior in predicting the claims ratio in both the training and test samples. Moreover, the random forest algorithm shows good performances in the test set but is only superior to the ETS(A,N,A) model.

show abstract

Section: Literature Reviewmentioning

confidence: 94%

Is the Claims Ratio Dynamic Predictable? A Study of the Macedonian Non-Life Insurance Sector

Peovski,

Ivanovski

2023

Proceedings of the International Conference "Economic and Business Trends Shaping the Future"

View full text Add to dashboard Cite

show abstract

“…Predicting health insurance claims with the help of artificial neural networks which involve both recurrent neural networks and feedforward neural networks is shown in [4]. The annual claims amounts were predicted using both models.…”

Section: Literature Reviewmentioning

confidence: 99%

Survey on Insurance Claim analysis using Natural Language Processing and Machine Learning

Sapana Kolambe

2023

IJRITCC

View full text Add to dashboard Cite

In the insurance industry nowadays, data is carrying the major asset and playing a key role. There is a wealth of information available to insurance transporters nowadays. We can identify three major eras in the insurance industry's more than 700-year history. The industry follows the manual era from the 15th century to 1960, the systems era from 1960 to 2000, and the current digital era, i.e., 2001-20X0. The core insurance sector has been decided by trusting data analytics and implementing new technologies to improve and maintain existing practices and maintain capital together. This has been the highest corporate object in all three periods.AI techniques have been progressively utilized for a variety of insurance activities in recent years. In this study, we give a comprehensive general assessment of the existing research that incorporates multiple artificial intelligence (AI) methods into all essential insurance jobs. Our work provides a more comprehensive review of this research, even if there have already been a number of them published on the topic of using artificial intelligence for certain insurance jobs. We study algorithms for learning, big data, block chain, data mining, and conversational theory, and their applications in insurance policy, claim prediction, risk estimation, and other fields in order to comprehensively integrate existing work in the insurance sector using AI approaches.

show abstract

“…Inaccurate estimation usually has a detrimental impact on a company's overall success. Goundar et al [8] explained how to build an artificial neural network (ANN) that can predict yearly medical claims. The aim was to lower the mean absolute percentage error by changing factors of the configuration, such as the epoch, learning rate, and neurons, in various layers once the neural network models were constructed.…”

Section: Related Workmentioning

confidence: 99%

Machine Learning-Based Regression Framework to Predict Health Insurance Premiums

Kaushik

Bhardwaj

Dwivedi

et al. 2022

IJERPH

Self Cite

View full text Add to dashboard Cite

Artificial intelligence (AI) and machine learning (ML) in healthcare are approaches to make people’s lives easier by anticipating and diagnosing diseases more swiftly than most medical experts. There is a direct link between the insurer and the policyholder when the distance between an insurance business and the consumer is reduced to zero with the use of technology, especially digital health insurance. In comparison with traditional insurance, AI and machine learning have altered the way insurers create health insurance policies and helped consumers receive services faster. Insurance businesses use ML to provide clients with accurate, quick, and efficient health insurance coverage. This research trained and evaluated an artificial intelligence network-based regression-based model to predict health insurance premiums. The authors predicted the health insurance cost incurred by individuals on the basis of their features. On the basis of various parameters, such as age, gender, body mass index, number of children, smoking habits, and geolocation, an artificial neural network model was trained and evaluated. The experimental results displayed an accuracy of 92.72%, and the authors analyzed the model’s performance using key performance metrics.

show abstract

Health Insurance Claim Prediction Using Artificial Neural Networks

Cited by 22 publications

References 47 publications

Is the Claims Ratio Dynamic Predictable? A Study of the Macedonian Non-Life Insurance Sector

Is the Claims Ratio Dynamic Predictable? A Study of the Macedonian Non-Life Insurance Sector

Survey on Insurance Claim analysis using Natural Language Processing and Machine Learning

Machine Learning-Based Regression Framework to Predict Health Insurance Premiums

Contact Info

Product

Resources

About