Kaggle Competition. Time To Event Analysis - HCT Survival Rate Prediction

Kaggle Project Competition run by Equity group to develop a model to improve the prediction of transplant survival rates for patients undergoing allogeneic Hematopoietic Cell Transplantation (HCT) — an important step in ensuring that every patient has a fair chance at a successful outcome. A large data set was provided for analysis.  The data included censored data for when the event has not happened for some individuals during the observation period.

I chose this challenging project to develop Time To Event or Survival Analysis Skills and synthetic data. I elected to use R because, as well as being a fantastic tool for data manipulation and ML tasks, I wanted to develop my exposure to R and Rstudio package and improve knowledge of its many libraries.

An LGBM model was selected as most accurate, R has a function to fine tune the model with best hyperparameters.