Wina's Portfolio

Diabetes Classification Web App

Diabetes Web App

This web application allows users to choose different machine learning models to predict diabetes and adjust parameters to achieve the best accuracy. Built using Streamlit, the app includes several popular classifiers such as SVM, Logistic Regression, Random Forest, K-Nearest Neighbors, Decision Tree, XGBoost, and LightGBM.

Gene Expression Analysis in AML and ALL

Gene Expression Project

This project focuses on the analysis of gene expression data to distinguish between Acute Myeloid Leukemia (AML) and Acute Lymphoblastic Leukemia (ALL). Accurate classification and clustering of gene expression profiles can provide significant insights into the molecular mechanisms of these cancers and aid in developing targeted therapies.

Airline Customer Satisfaction Analysis

Airline Satisfaction

This project aims to analyze customer satisfaction in the airline industry by examining various factors that influence passenger experiences. The analysis includes identifying key independent variables that affect customer satisfaction and utilizing machine learning models to predict satisfaction levels. The primary objective is to understand how different service aspects impact customer perceptions and to identify areas for improvement.

Stroke Prediction Model Using R

Stroke Prediction

A leading healthcare organization seeks to predict stroke risk using patient medical history and demographic data. As a data scientist, I built and validated a prediction model using the Random Forest algorithm. This involved data cleaning, processing, analysis, visualization, and deployment for clinical use. The model, achieving 95% accuracy, aims to mitigate stroke incidents and enhance patient outcomes.