Hospital Appointment No-Show Prediction

Project Overview Developed a data analysis and machine learning solution to analyze hospital appointment records and predict whether a patient is likely to attend or miss their appointment. What I Did * Cleaned and prepared the appointment dataset for analysis. * Handled missing values, inconsistent data, and duplicate records. * Performed Exploratory Data Analysis (EDA) to identify patterns related to appointment attendance. * Analyzed factors that may influence patient no-shows. * Created meaningful features to improve the predictive model. * Built a LightGBM classification model to predict appointment no-shows. * Evaluated the model using Accuracy, Precision, Recall, F1-score, Confusion Matrix, and ROC-AUC. * Focused on improving the detection of the No-show class because identifying patients at risk of missing appointments is important for hospital operations. * Designed a Power BI dashboard to present the main findings and make the results easier to understand. Technologies Python · Pandas · NumPy · Matplotlib · Seaborn · Scikit-learn · LightGBM · Power BI Outcome The project provides a complete workflow from raw healthcare appointment data to analysis, predictive modeling, and interactive visualization.