Ambeone Student’s Projects Gallery
Based on the Big Data Analytics & Machine Learning Techniques taught in Ambeone’s Programs
This is a Gallery of some glimpses Data Science projects done by recent Ambeone students as part of their program.In case you are interested to know more about a particular project/projects, you may contact us for details .
Insurance Pricing – Medical Expenses Prediction
Submitted by: Sonia
Medical Expenses Prediction using Linear Regression
Overview
Medical Expenses Prediction Model was developed using Data Science Linear Regression Modeling for a leading Insurance company ..
Objective
The goal of this project is to create an estimate of the future average medical care expenses using regression for provided population segments. This will help medical insurance company to decide the future premium charge.
Data Preparation & Processing
- Datasets for Expenses based on Children, Age, Sex, Region, Smoker, BMI was collected
- Target Variable/Dependent Variable to be predicted was found
- InDependent Variable based on Children, Age, BMI was calculated
- InDependent Categorical Variable based on Smoker, Gender, Region was calculated
- Correlation matrix was plotted
- Interactions between the independent variables was analyzed
- Linear Regression Modeling was performed.
- All models were compared to get the best fit.
Data Science Techniques and Models used
- Linear Regression
Key Results
The result showed that Model 2 provides a significantly better fit to the data compared to Model 1 and Model 3, with the very small P-value. This means that adding BMI*Smoker to the model did lead to a significantly improved fit over the other 2 models.
