SDS BIT Mesra - ML Contest on Liver Disease Prediction(2nd Place Solution)

Link of hackathon is :- https://dphi.tech/challenges/sds-bit-mesra-ml-contest-on-liver-disease-prediction/192/leaderboard/practice/

Team Name :- Still Learning

This repository contain our solution(2nd place) to the Machine Learning Contest organized by BIT Mesra in which we have to create predictive models to predict the stage of liver Cirrhosis using 18 clinical features as Cirrhosis damages the liver from a variety of causes leading to scarring and liver failure.

Motivation Behind The Problem Statement

Hepatitis and chronic alcohol abuse are frequent causes of the disease. Liver damage caused by cirrhosis can't be undone, but further damage can be limited. Treatments focus on the underlying cause. In advanced cases, a liver transplant may be required. Predicting the stage of cirrhosis and beginning the treatment before it's too late can prevent the fatal consequences of the disease.

The full solution is described in the final report :- https://github.com/Jatin-Goyal-552/Bit_Mesra_ML_Hackathon-2nd-place-Soln-/blob/main/Final_Report/StillLearning_final_report.pdf

EDA of dataset can be found at :- https://www.kaggle.com/code/raj401/liver-disease-eda

Code to generate folds of dataset is at :- https://www.kaggle.com/code/raj401/liverdisease-create-folds

Final notebook to train model is at :- https://www.kaggle.com/code/raj401/liver-disease-complete-ensemble-2nd-place/notebook