UAC System Capacity & Care Load Analytics Dashboard
Healthcare Data Analytics and Interactive Dashboard Development
Developed an interactive healthcare analytics dashboard during my Machine Learning Internship at Unified Mentor Pvt. Ltd. The project analyzes Unaccompanied Children (UAC) program data from the U.S. Department of Health and Human Services (HHS) to monitor system capacity, care load, intake, transfers, and discharge trends. Implemented data cleaning, feature engineering, exploratory data analysis, and key performance indicators (KPIs) using Python, Pandas, and NumPy. Built an interactive Streamlit dashboard with Plotly visualizations to support data-driven insights into healthcare system capacity and operational trends.
Technology stack
Problem
Healthcare system reporting data contains large volumes of daily intake, transfer, custody, and discharge information. Without structured analytics and visualization, identifying capacity pressure, backlog accumulation, operational trends, and changes in care load becomes difficult. The project aimed to transform raw reporting data into meaningful insights for better system monitoring and capacity planning.
Solution
Developed a Python-based data analytics pipeline involving data cleaning, preprocessing, feature engineering, exploratory data analysis, and KPI calculation. Created an interactive Streamlit dashboard using Plotly to visualize total system load, CBP and HHS care comparisons, net intake pressure, backlog trends, and historical performance. Added date-range filters, time-granularity controls, and interactive chart options for flexible analysis.
Results
Identified a major 167-day sustained system-strain period from August 2023 to January 2024. Analyzed historical care-load trends, volatility, backlog accumulation, and discharge performance across the dataset. Developed five key performance indicators to monitor system conditions and created a deployed interactive dashboard that makes complex healthcare reporting data easier to understand and explore.