TRUPTI
Baltimore, MD +1-667-***-**** ************@*****.*** LinkedIn GitHub Portfolio
PROFESSIONAL SUMMARY
Data Analyst with experience delivering data-driven solutions across healthcare, finance, and research. Skilled in structuring and labeling large datasets, designing scalable ETL pipelines for 100K+ records, and building automated reporting workflows and predictive models. Strong attention to detail, analytical thinking, and quick to learn new digital tools. Seeking an AI Specialist role to apply data organization and quality review skills in remote AI operations. EDUCATION
University of Maryland, Baltimore County May 2025
Master’s, Information Systems
• Coursework: Advanced Databases, Data Mining, Structured System Analysis, Advanced AI, Data Analytics for Cybersecurity Visvesvaraya Technological University Aug 2021
Bachelor’s, Electronics and Communication
• Coursework: Network Analysis, Control Systems, Operating Systems, Digital Signal Processing, Machine Learning PROFESSIONAL EXPERIENCE
UMBC College of Engineering and Information Technology Feb 2024 - Jan 2026 Data Analyst
• Cleaned and structured 100K+ patient records using Pandas and Excel, fixing missing values and inconsistencies to ensure data integrity for downstream research and reporting.
• Designed interactive Power BI (DAX and Power Query dashboards and automated Excel reports (Pivot Tables, Power Query), enabling self-service analytics, tracking project workflows through Jira, and reducing ad-hoc requests by 30%.
• Built a Python (scikit-learn) predictive model to estimate patient health risk, supporting resource planning and decision-making.
• Automated recurring ETL workflows using SSIS and Python scripts, saving several hours of manual data processing each week.
• Implemented workflow management protocols within Jira to monitor ETL processes and ensure quality assurance of data outputs. University of Maryland Baltimore County Sep 2024 - Dec 2025 Research Assistant
• Built a data pipeline to combine clinical text and speech data for early dementia research, creating a structured dataset for analysis.
• Processed and cleaned large audio and text datasets using Python and SQL, improving data quality and reducing missing or inconsistent records by 25%.
• Extracted key NLP and speech features (language patterns, speech behavior markers) to support cognitive score prediction.
• Combined multiple data sources into a unified dataset to enable accurate prediction of patient MOCA cognitive scores, improving model performance by 12%.
• Supported AI operations by labeling and annotating clinical text data for model training to enhance predictive accuracy. Neopathology Corp. May 2024 - Aug 2024
Research and Development Intern
• Conducted a literature review on tissue morphology assessment and identified suitable techniques for medical image analysis.
• Analyzed tissue images using Python (OpenCV) to extract cell features like shape, structure, and organization for research use.
• Engineered automated pipelines to extract image measurements and structure them into organized datasets using Python and SQL.
• Collaborated with clinical teams to validate extracted data using Excel and SQL, improving data completeness by 26%.
• Applied digital literacy to evaluate and test image analysis pipelines and provide feedback on prompt engineering refinements. Government Tool Room and Training Center Feb 2023 - Aug 2023 Data Analyst
• Collected, cleaned, and analyzed industrial machine data using Python and Excel, improving reporting turnaround time by 30%.
• Developed ETL pipelines using Python and SQL (MySQL), applying Azure-aligned cloud data storage concepts to integrate machine logs, SCADA, and CMMS data into a centralized database.
• Built Power BI dashboards and automated Excel reports to track machine utilization, downtime, throughput, and productivity.
• Performed trend and time-series analysis to identify inefficiencies, increasing output by 12% and reducing downtime by 10%.
• Created KPI dashboards for operational monitoring, enabling data-driven decision-making for management.
• Led process improvement initiatives to streamline ETL pipelines, reducing data integration time by 20%. Aradhana Finance Mar 2021 - Jan 2023
Financial Analyst
• Led FP&A activities including budgeting, forecasting, variance analysis, and monthly MIS reporting for decision-making.
• Performed data reconciliation and financial audits using SQL and Excel, identifying discrepancies, control gaps, and ensuring 100% compliance with accounting standards.
• Conducted variance, trend, and root-cause analysis on financial and operational data to identify anomalies and key business insights.
• Built Power BI and Tableau dashboards tracking KPIs (revenue, expenses, collections), improving reporting accuracy by 20%.
• Developed Excel financial models and forecasting scenarios to support budgeting and improved collection efficiency by 15%. TECHNICAL SKILLS
• Programming Languages: Python, SQL (MySQL, Oracle), R
• Data Analysis: Pandas, Statistical Modeling, A/B Testing, EDA, Data Cleaning, Data Validation, Predictive Modeling
• Financial Analysis: FP&A, Budgeting, Forecasting, Variance Analysis, MIS Reporting, Reconciliation, KPI Tracking
• Data Visualization & Reporting: Power BI (DAX, Power Query), Tableau, Microsoft Excel (Pivot Tables, Power Query, VLOOKUP)
• Data Engineering & AI Operations: ETL Pipelines, SSIS, Data Transformation, Data Modeling, AI Operations, Prompt Engineering, Quality Assurance, Workflow Management, Process Improvement
• Cloud & Tools: AWS, Azure, Databricks, Jira, Git, GitHub, Jupyter Notebook, Digital Literacy