Research Article
Predictive Modeling of Hair Fall using Random Forest Algorithms
@INPROCEEDINGS{10.4108/eai.28-4-2025.2358120, author={M Sirish Kumar and P Lokesh Kumar Reddy and G Dinesh Reddy and Amidela Sai Kumar and P Nagendra}, title={Predictive Modeling of Hair Fall using Random Forest Algorithms}, proceedings={Proceedings of the 4th International Conference on Information Technology, Civil Innovation, Science, and Management, ICITSM 2025, 28-29 April 2025, Tiruchengode, Tamil Nadu, India, Part II}, publisher={EAI}, proceedings_a={ICITSM PART II}, year={2025}, month={10}, keywords={hair loss prediction machine learning random forest dermatology healthcare analytics predictive modeling data preprocessing django web application feature engineering hyperparameter tuning classification models ai in dermatology}, doi={10.4108/eai.28-4-2025.2358120} }- M Sirish Kumar
P Lokesh Kumar Reddy
G Dinesh Reddy
Amidela Sai Kumar
P Nagendra
Year: 2025
Predictive Modeling of Hair Fall using Random Forest Algorithms
ICITSM PART II
EAI
DOI: 10.4108/eai.28-4-2025.2358120
Abstract
Genetics, hormones, lifestyle, and environment cause hair loss in millions. Losing hair can cause worry and low self-esteem. The Random Forest Algorithm is used to develop a machine learning-based hair loss predictive model for accuracy and durability in complicated datasets. Heredity, hormonal imbalances, medical problems, medications, dietary deficiencies, stress, and lifestyle choices may indicate hair loss patterns. Model performance requires label encoding categorical variables, missing values, and feature scaling. GridSearchCV enhanced prediction accuracy with Random Forest hyperparameters. To choose the optimum model, accuracy, precision, recall, and F1-score balanced bias and variance. Comparing Logistic Regression, SVM, KNN, Gradient Boosting, and XGBoost, Random Forest performed best. Users can submit details and get real-time forecasts for this model using a Django web interface. The program's interface is smooth owing to HTML, CSS, and Python. The project shows dermatology can use predictive analytics and machine learning. We want to increase forecast accuracy with data enrichment, model tuning, and deep learning. This study streamlines hair loss risk assessment.
