JEENAL KHAMAR

Detail-oriented analyst with a bachelor's degree in computer engineering and a completed master's degree in data science. Strong foundation in Python, SQL, and data visualization, with hands-on experience in Natural Language Processing (NLP) projects, and quality assurance (QA). Skilled in conducting in-depth data analysis, building interactive dashboards, and automating workflows to improve efficiency. Adept at translating complex data into actionable insights to drive strategic business decisions. Passionate about applying data science and NLP techniques to solve real-world challenges with precision and impact.

AES-DSA Secure Communication Protocol:As part of a security-focused academic project, I developed and tested a hybrid encryption protocol that combined Advanced Encryption Standard (AES) for data confidentiality with Digital Signature Algorithm (DSA) for authentication and integrity.

• The goal was to enhance the security of e-commerce transactions by ensuring both encrypted data transmission and verified sender identity.
• I designed test cases to simulate real-world attack scenarios and validate the robustness of the encryption pipeline. Through rigorous testing using tools like Selenium and JMeter, I identified and resolved over 150 software defects, which significantly improved system reliability and reduced the potential for data breaches.
• The final protocol offered a scalable and secure model suitable for integration into commercial platforms.

Image Collection Automation:I developed a Python-based NLP tool to automate the process of creating datasets for machine learning workflows, specifically focusing on collecting and organizing labeled image data. By leveraging keyword extraction and intelligent scraping techniques, the tool streamlined the image gathering process based on contextual queries.

• This automation reduced manual effort and significantly improved the efficiency of data preparation in machine learning projects.
• It also enhanced consistency and scalability across multiple testing workflows, accelerating project timelines.

National Park Recommender System:Developed a web-based recommender system using Python and Django to suggest U.S. national parks based on user preferences such as location, park size, and activities. Implemented content-based filtering using TF-IDF vectorization and collaborative filtering to enhance recommendation accuracy by combining user behavior with park attributes.

• Preprocessed large volumes of text data through custom NLP functions for tokenization, lemmatization, and stopword removal, improving model performance. Enabled users to register, log in, and receive personalized park recommendations, contributing to a dynamic and scalable tourism-focused platform.