Skip to content

This project involves comprehensive data wrangling and exploratory analysis to uncover key statistical correlations between various factors influencing the revenue of a synthetic medical group. Based on these insights, I developed two distinct and robust machine learning models, decision tree and regression, to predict future revenue.

Notifications You must be signed in to change notification settings

kennmai/Optimizing-Healthcare-Revenue-with-Advanced-Machine-Learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 

Repository files navigation

Optimizing Hospital Revenue with Advanced Machine Learning

ML_Healthcare

Project Overview: This project leverages machine learning to optimize hospital revenue through data-driven insights and predictive modeling. It begins with data wrangling, cleaning, and exploratory analysis to identify statistical relationships between key factors influencing revenue in a synthetic medical group.

Methodology and Approach: The project focuses on Decision Tree and Linear Regression models, primarily using Scikit-learn and other Python ML libraries. Through feature selection, model tuning, and cross-validation, I developed predictive models capable of forecasting revenue with a 10% accuracy margin.

Key steps include:

  • Data Wrangling & Cleaning: Addressed inconsistencies, outliers, and missing values to ensure reliable input for modeling.
  • Exploratory Data Analysis (EDA): Analyzed correlations, distributions, and trends within the data.
  • Model Development: Fine-tuned Decision Tree for categorical insights and Linear Regression for continuous revenue forecasting.
  • Model Validation: Used performance metrics (R-squared, RMSE) to assess and refine model accuracy.

Future Directions:

  • Refine Regression Model: Further feature engineering and hyperparameter tuning to improve prediction accuracy.
  • Explore Advanced Models: Investigate Random Forest and XGBoost for a more robust predictive system.
  • Data Standardization: Recommend standardizing data collection methods across healthcare locations to improve consistency and model reliability.
  • Web Application: Propose a web-based platform for real-time data integration, enhancing model performance.

About

This project involves comprehensive data wrangling and exploratory analysis to uncover key statistical correlations between various factors influencing the revenue of a synthetic medical group. Based on these insights, I developed two distinct and robust machine learning models, decision tree and regression, to predict future revenue.

Topics

Resources

Stars

Watchers

Forks