An Efficient Medical Cost Prediction System with Machine Learning and Deep Learning Model

Insurance is a policy which reduces or eliminates the costs associated with various types of risk. Unforeseen circumstances have an effect on insurance rates. These factors influence the design of an insurance policy. The cost of health care is rising at an alarming rate. Predicting health costs has never been more important than it is today, with an increasing number of new viruses entering the human population. Governments can use this form of forecasting to make decisions about health care. In addition, the public understands the importance of health care prices. There is a wide range of applications for machine learning. Several health-related applications make use of ML algorithms in the healthcare system. In this paper, the authors proposed ML and DL models for forecasting insurance costs. We used a Kaggle dataset, which has 1338 samples with features, 'gender of person', 'whether person is smoker or not','person age', 'BMI', 'Number of children', 'region of person', and insurance charges. Health insurance companies billing records and patient medical information are included in the data. We used a variety of regression models to estimate medical expenses from this dataset. The proposed model given good prediction rate when compared to existing models.