Pappu Jha

ABOUT

Pappu Jha is a Research Assistant at the University of Southern Mississippi with more than two years of experience in data science across academic research, public- and private-sector internships, and university-based projects supporting NOAA initiatives. His professional experience includes internships with the Port Authority of New York and New Jersey in New York City and Jones Capital in Hattiesburg, Mississippi, where he has applied data-driven approaches to real-world challenges. Beyond his technical work, Pappu is passionate about public speaking and making complex ideas accessible to broader audiences. As a TEDx Southern Miss 2025 speaker, he enjoys sharing his experiences and research with the wider community. Proficient in Python, PySpark, Machine Learning Algorithms, SQL, Power BI, Cloud Services, n8n, Databricks, Excel, and other data tools, he is passionate about leveraging technology and analytics to solve complex problems and deliver meaningful impact. Connect with Pappu to explore potential collaboration and build a meaningful connection!

  • Data Science
    PySpark, SQL, Pandas, NumPy, API, Dashboards, Machine Learning Algorithms, Statistics
  • Programming
    Python, C++, OOP, Web Development (HTML, CSS, JavaScript, WordPress)
  • Technologies
    Power BI, Databricks, Atlassian (JIRA Service Management, Confluence, Scribe), n8n, MS Office (Excel, SharePoint), Cloud Services, GitHub, MongoDB
  • Spoken Languages
    English (Fluent), Nepali, Maithili (Native), Hindi
  • IT Data Analyst Intern
    Sept 2025 - Present
    Jones Capital - Hattiesburg, MS

    ● Built 30+ data-driven gadgets in Jira Service Management and Excel using JQL filters to track ticket resolution performance of 5 agents and automated data workflows using n8n with Confluence documentation, significantly reducing manual reporting time for IT operations.
  • Undergraduate Research Assistant
    Sept 2024 – Present
    Cyber Innovation Lab - Hattiesburg, MS

    ● Led two machine learning-based cybersecurity research projects, as well as a separate year-long interdisciplinary research project, leading four Computer Science students in collaboration with four Chemistry students on Computing Meets Green Chemistry.
  • Data Analytics and Business Intelligence Intern (Aviation)
    May 2026 - August 2026
    The Port Authority of New York and New Jersey - New York, NY

    ● Supported data-driven decision-making by analyzing operational issues, assisting with predictive modeling, improving data quality, researching process improvements, and maintaining clear data documentation.
  • Data Engineer/Research Assistant
    May 2025 - May 2026
    Institute for Advanced Analytics and Security - Hattiesburg, MS

    ● Built AQUAVIEW, a Python library with 7+ API endpoints (1000+ downloads), processed 17M+ oceanographic data points from 125 years of World Ocean Database, developed LLM-powered classification tools for 10+ data sources, and created an adapter for National Data Buoy Center (NDBC)'s real-time and historical datasets.
  • Web Developer/Producer
    Oct 2024 - May 2025
    Roy Howard Community Journalism Center - Hattiesburg, MS

    ● Developed the website (rhcjcnews.com) of the Roy Howard Community Journalism Center from scratch, designed digital materials such as e-newsletters, and ensured SEO and strong public visibility.
  • The University of Southern Mississippi

    Bachelor of Science (BS) in Computer Science
    Minors: Economic Data Analysis & Information Security
    Hattiesburg, MS, 39406, USA
    Expected Graduation: May 2027
    GPA: 4.0/4.0
    Courses: Machine Learning in Cybersecurity, Econometrics, Statistics, Designing Solutions for Defense

    Awards:
    ● President's List (Fall 2023, Spring 2024, Fall 2024, Spring 2025, Fall 2025, and Spring 2026 semesters)
    ● Honors Keystone Scholarship 2025 (USM Honors College)
    ● International Ambassador of The Year 2025 (USM Center for International Education)
    ● First Position under the 'Computational Approaches' category in 2025 Undergraduate Symposium for Research and Creative Activity (UGS)
    ● 2025 Innovation & Excellence Award (Roy Howard Community Journalism Center)

    Leadership:
    ● Creative Director, The Entrepreneurship Society (August 2025 - Present)
    ● International Student Ambassador, Center for International Education (August 2024 - Present)
    ● Director of Finance, Residence Hall Association (April 2024 - May 2025)

TEDx Southern Miss 2025 Speaker

Areas of Interest

Machine Learning


Develop machine learning models with a focus on real-world applications. Conduct model training, testing, validation, and optimization to achieve accuracy and efficiency.

Data Science


Perform data analysis to turn raw data into meaningful insights. Work with tools like Pandas, NumPy, and Seaborn of Python language to clean and visualize data to identify patterns and present findings in a clear and effective way.

Cybersecurity


Conduct research on cybersecurity threats and vulnerabilities, including but not limited to password classification, phishing, and social engineering attacks. Develop and evaluate machine learning models to detect and prevent these threats.

Projects

World Ocean Database


  • Processed more than 17 million data points of oceans and seas worldwide from the year 1800 to 2024, generated and stored their metadata in MongoDB, indexed on Google Cloud, and integrated with the Elasticsearch so that results are visible in the UI based on the queries of spatial and temporal filters.

  • Skills: Big Data Analysis, Python, MongoDB, Google Cloud, API

Adversarial Machine Learning for Password Strength Estimation


  • Developed five supervised machine learning models to accurately classify adversarial passwords based on their strengths into strong, medium, and weak categories.

  • Tools: Pandas, Seaborn, Random Forest, Logistic Regression, Naive Bayes, Decision Tree, XGBoost

Regulating College Dorms Using C++


  • Built a dormitory management system using concepts from the C++ course, streamlining student check-ins/outs, visitor logs, and violation detection.

  • Tools Used: C++ (Object-Oriented Programming, File Handling, Vectors, and Other Advanced Level Concepts)

Aquaview Python Library


  • Developed Aquaview, a Python-based SDK providing unified access to oceanographic datasets with search, filter, preview, and download capabilities, released June 2025 and downloaded nearly 1,000 times in six months by NOAA and IAAS researchers.

Boston Daddy (Hack Harvard 2025)


  • Developed a full-stack smart city infrastructure platform that integrated energy, traffic, and weather data — achieving predictive analytics and actionable insights for 15+ buildings and 10+ intersections in real-time.

Delagent (MHacks 2025)


  • Built an AI-based scheduling platform using Fetch.AI uAgents framework, FastAPI, and SQLite, resulting in automated 3-agent calendar coordination and negotiation, with 80% reduction in manual scheduling overhead.

Please allow a couple of seconds for the form submission!