Silent Signals: A Comparative Analysis of Machine Learning Models in Predicting the Vulnerability of Filipino Women Against Domestic Violence (Published)
Domestic violence against women remains a persistent and underreported issue in the Philippines. This study applies five (5) machine learning models, namely: KNN, Logistic Regression, Random Forest, XGBoost, and LightGBM, to predict the vulnerability of Filipino women to domestic violence using data from the 2022 NDHS. These models were evaluated using comprehensive metrics, including Accuracy, Precision, Recall, F1-Score, Log Loss, MCC, ROC-AUC, PRC-AUC, and Confusion Matrix. Logistic Regression emerged as the most effective model, demonstrating a strong balance between interpretability and predictive performance, particularly in Accuracy, F1-Score, PRC-AUC, and ROC-AUC. The analysis identified key predictive variables that emerged from the best-performing model’s feature importance, namely: household composition, reproductive health knowledge, unmet need for contraception, frequency of internet usage/media exposure, asset ownership, and age of household heads. Based on these findings, several policy recommendations are proposed: expanding VAW desk services and barangay-level response systems; integrating domestic violence screening into family planning and maternal health programs; designing age-specific interventions such as economic support and education; and encouraging the ethical use of machine learning tools by social welfare agencies for early detection. Ethical considerations were also examined, including data privacy, bias mitigation, and responsible AI deployment. This study contributes to the growing field of data-driven policy making by demonstrating the value of machine learning in informing targeted and preventative social interventions.
Keywords: Domestic Violence, machine learning, predictive analysis
IoT-Enhanced Weather Monitoring System: Affordable Hardware Solution for Real-Time Data Collection, Storage, And Predictive Analysis (Published)
An IoT-based weather monitoring system that collects and stores weather data allowing easier access and recording is what this project entails. It is also incorporated with the ability to predict future weather data based on previous recordings. Keeping track of weather conditions is one of the most concentrated areas in our current society. Weather monitoring systems are built to collect these data from a wide range of areas. And there exist satellite systems which do similar work over a wider range of area. The goal of this project is to develop an inexpensive weather monitoring system that can gather these same data over a given area over time. The system is made of hardware built with ESP8266 (NodeMCU) and a website. The hardware device and the server transfer data using the industry-standard HTTP connection protocol. There exist various sensors like temperature sensors, humidity sensors, rain sensors and pressure sensor which are suitable for the full functioning of the system. These sensors collect and transmit data to a server via a Wi-Fi module to be stored and can be accessed on the webpage. These data are then analysed and used in predicting future data.
Keywords: IoT, Real-time data collection, Weather Monitoring, low-cost solution., predictive analysis
Predicting Student University Admission Using Logistic Regression (Published)
The primary purpose is to discuss the prediction of student admission to university based on numerous factors and using logistic regression. Many prospective students apply for Master’s programs. The admission decision depends on criteria within the particular college or degree program. The independent variables in this study will be measured statistically to predict graduate school admission. Exploration and data analysis, if successful, would allow predictive models to allow better prioritization of the applicants screening process to Master’s degree programme which in turn provides the admission to the right candidates.
Keywords: Logistic regression, college admission, data analytics, predictive analysis