List of my Sample Data Applications. 

Click on Project Name to View the Project.


  • Workforce Analytics Engine: An AI-powered employee productivity prediction application that uses machine learning to estimate Productivity Score based on demographic, workplace, engagement, and performance factors. The solution helps HR teams and managers gain actionable insights for workforce optimization, employee development, and data-driven decision-making. 

  • Realt Estate IQ An AI-powered real estate valuation application that predicts property prices using historical housing data from Sindian District, New Taipei City. The solution compares multiple regression models and applies advanced machine learning techniques, with XGBoost selected for its superior balance of accuracy and generalization. It provides data-driven insights to support smarter property pricing, investment analysis, and real estate decision-making. 

  • PayPredict IQ This is a machine learning-powered application designed to predict whether customer invoices will be paid on time or become overdue. By analyzing financial and behavioral indicators such as credit score, debt-to-income ratio, and payment history, the model helps businesses proactively identify payment risks and improve cash flow management. Using advanced classification algorithms, including Random Forest, the application provides actionable insights that support better collection strategies, customer management, and financial decision-making 

  • RSamplingZ: A package geared to make computations of sample size convenient for researchers. It includes sample size formulas such as: Cochran's Formula, Modified Cochran,  Sample size estimation based on the Mean, Sample size estimation using Power and mean, and Sample size estimation using Power and Proportion. It also allows users to randomly or systematically select elements from the Population (via the Master List) that will be included in the Sample Size. 


  • ForcaZ: It is an online application designed for the convenience of administrators in the academe in providing enrollment forecast to be used for purposes of budget preparation as estimates for probable revenues. It utilizes ARIMA models to create projections of student enrollment for the next two academic years. Depending on the uploaded dataset, it can utilize ARIMA models involving both with and without component of Seasonality.