Prediction: Prescription Drug Insurance Copayments

This project has two primary goals:

1. Predict the patient’s expected cost of a prescription drug
2. Predict the formulary status of the medication on each insurance plan
   • The formulary sorts drugs into tiers such as generic, preferred non-generic, non-preferred non-generic, etc.

I completed this project in both R and Python and the code for both is linked below:

• R - Exploratory Data Analysis

  This notebook walks through an exploratory analysis of insurance claims to develop an understanding of the relationships between drug prescriptions, copayments, and insurance approvals. This exploration will aid in the development of predictive models.

• Python - Exploratory Data Analysis

  This notebook walks through an exploratory analysis of insurance claims to develop an understanding of the relationships between drug prescriptions, copayments, and insurance approvals. This exploration will aid in the development of predictive models.

• R - Data Analysis

  With the data cleaned, and an understanding of the relationships between variables, I now build predictive models to understand patient copayments and insurance claim approvals. These models are primarily built with the tidymodels package.

• Python - Data Analysis

  With the data cleaned, and an understanding of the relationships between variables, I now build predictive models to understand patient copayments and insurance claim approvals. These models are primarily built with the scikit-learn library.