International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 04 | Apr 2024
p-ISSN: 2395-0072
www.irjet.net
Health Insurance Cost Prediction Using Machine Learning Dr. S. M. Iqbal1, Sayali D. Ghatol2, Prerana V. Jadhav3, Nikita D. Raspalle4 1Professor, Dept. of CSE Engineering, PRMIT&R college, Maharashtra, India 2Student, Dept. of CSE Engineering, PRMIT&R college, Maharashtra, India
3 Student, Dept. of CSE Engineering, PRMIT&R college, Maharashtra, India 4Student, Dept. of CSE Engineering, PRMIT&R college, Maharashtra, India
---------------------------------------------------------------------***------------------------------------------------------------------Abstract - Insurance is a policy that helps to cover up all losses or decrease losses in terms of expenses incurred by various risks. Several factors influence the insurance cost. Various factors contribute to the determination of insurance policy costs. Predicting medical insurance costs remains a challenging issue in the healthcare industry. Predicting medical insurance costs is still a problem in the healthcare industry and thus it requires more investigation and improvement. Machine learning is one of the computational intelligence aspects that may address diverse difficulties in a wide range of applications and systems when it comes to the exploitation of historical data. Using a series of machine learning algorithms, a computational intelligence approach will be proposed for predicting healthcare insurance costs. The system will predict the approximate cost of health insurance for a person by using the dataset from KAGGLE. A medical insurance cost dataset was acquired from the KAGGLE repository for this purpose, and machine learning algorithms were used to show how different regression models can predict insurance costs and to compare the models’ accuracy. Keywords: Machine learning (ML), Artificialintelligence(AI), Health insurance(HI), Premium cost, Regression algorithm(RA).
1. Introduction Healthcare systems in developing countries depend heavily on out-of-pocket payments, the mechanism that is a barrier to universal health coverage, as it contributes to inefficiency, inequity, and cost. Health insurance serves as a means for individuals in different countries to manage the financial risk associated with medical expenses. It provides coverage against the costs incurred from medical treatment and related services. However, due to the high rates that are charged by insurance companies, many people are without health insurance and so fail to access timely health services which results in high death rates. A health insurance policy is a policy that covers or minimizes the expenses of losses caused by a variety of hazards. Accurately predicting individual healthcare expenses using prediction models is crucial for various stakeholders and health departments, as numerous factors influence the cost of insurance or healthcare. Accurate cost estimates can help health insurers and, increasingly, healthcare delivery organizations to plan for
© 2024, IRJET
|
Impact Factor value: 8.226
|
the future and prioritize the allocation of limited care management resources. Furthermore, knowing ahead of time what their probable expenses are for the future can assist patients in choosing insurance plans with appropriate deductibles and premiums [1]. These factors contribute to the formulation and development of insurance policies. However, health insurance rates calculations are often complex as they need to determine the rates that are acceptable to both insurance companies and beneficiaries; Insurance companies need to make money by collecting more money than they spend on the medical expenses of their beneficiaries, hence making a profit and continue to stay in businesses. These companies price the premiums based on the probability of certain events occurring among a pool of people [2]. However, the medical expenses and other associated costs are difficult to estimate because the costliest conditions are rare and seemingly random. Another complex part of estimating medical expenses is that the occurrence of certain diseases differs from one person to another and from one segment of the population to another. Therefore, there is a need for a fair premium calculation model that suits the unique population factors. In this regard, this study used demographic and behavioral data from the patients to develop a predictive model. While previous studies used conventional statistical methods, this study used machine learning logarithms to develop a predictive model. It compares the performance of several models to find the most suitable. In the insurance sector, machine learning can help enhance the efficiency of policy wording. In healthcare, machine learning algorithms are particularly good at predicting high-cost, high-need patient expenditures. machine learning can be categorized into three different types. There are three main types of machine learning: supervised, unsupervised, and reinforcement learning. Supervised machine learning involves tasks such as classification and regression, where the data is labeled, and the algorithm learns from provided input-output pairs. Unsupervised machine learning, on the other hand, is used for tasks like clustering, where the data is unlabeled, and the algorithm discovers patterns or structures within the data. Reinforcement learning is a type of learning where the algorithm learns through trial and error by interacting with an environment to achieve a goal [5].
ISO 9001:2008 Certified Journal
| Page 1012