Medical_Insurance_Cost_Recommendation: Insureit(Website)

Introduction:

• With the constant increasing prices of healthcare in our country, and with the ever-rising instances of diseases, health insurance today is a necessity.
• Health insurance provides people with a much-needed financial backup at times of medical emergencies.

Objectives:

1.To build a Machine learning model to recommend insurance policy.

2.To help the customer to be financially prepared in case of medical emergency.

Problem Statement:

To develop a machine learning model which can recommend the cost of an insurance policy that a customer should purchase. This model will be able to recommend the cost of insurance to the customers based on their BMI, age, medical history, and smoking habits.

Demo Video:

Medical_Insurance_Cost_Recommendation_Demo.mp4

Group Members:

• @parthdali
• @pranavdalvi
• @shivambhosale
• @harshkumarbhikadiya

Architectural Diagram:

Methodology:

Implementation:

1.Dataset details

• The attributes of dataset are: Age,Sex,BMI,Children,Smoking habit.

2. Algorithm

• Linear Regression algorithm was used.

3.Performance metrics

• R-squared value

Project Screenshots:

Home Page:

Input Page:

Result Page:

Tech Stack Used

Front-End:

• HTML
• CSS
• Bootstrap

Back-End:

• Python
• Flask

Editor Tools:

• VsCode/ PyCharm
• Jupyter Notebook

Dataset:

• Kaggle

Documentation:

Final Report

Final Presentation

Proposal

Conclusion:

• In this project, we used linear regression for evaluating individual health insurance data. The predicted premiums from this model was compared with actual premiums to compare the accuracy of the model.
• Various factors were used and their effect on predicted amount was examined. It was observed that a person’s age and smoking status affects the recommendation most.
• Premium amount recommendation focuses on person’s own health rather than other company’s insurance terms and conditions. The models can be applied to the data collected in coming years to recommend the premium. This can help not only people but also insurance companies to work in tandem for better and more health centric insurance amount.

Future Scope:

• The current machine learning model is limited to accurate predictions of the specific age group hence in future scope we can increase the quality and accuracy of the dataset.
• The user interface can be improved and buying of new policies can be incorporated.
• Inclusion of more parameters like chronic diseases, number of surgeries can be used in the future for better cost recommendation.

References:

[1] Mohamed hanafy, Omar M. A. Mahmoud."Predict Health Insurance Cost by using Machine Learning and DNN Regression Models" International Journal of Innovative Technology and Exploring Engineering (IJITEE)(2021):2278-3075

[2] Kaggle[online] https://www.kaggle.com/datasets/awaiskaggler/insurance-csv (Accessed:Jan 23, 2022)

[3] Researchgate.net.[Online] https://www.researchgate.net/publication/348559741_Predict_Health_Insurance_Cost_by_using_Machine_Learning_and_DNN_Regression_Models. (Accessed: 24-Jan-2022).

[4] moneycrashers.[online] https://www.moneycrashers.com/factors-health-insurance-premium- costs(Accessed:Jan 23, 2022)