Temple Finance Department (FSBM)

• Proficiently utilize Python programming language to develop automated scripts for efficient and accurate extraction of financial data from various company websites, ensuring up-to-date and reliable datasets for analysis
• Leveraged Beautiful Soup web scraping to efficiently navigate intricate web structures and extract precise financial data from diverse sources, optimizing data collection and saving 99% time
• Utilize expertise in data manipulation and analysis with Pandas and NumPy libraries to preprocess and clean the data, enabling 98% data accuracy seamless integration into research facilitating insightful financial analysis

• Resolved hardware and software issues promptly, ensuring uninterrupted operations for end-users
• Provided exceptional service, documenting, and resolving items with precision to achieve high satisfaction
• Demonstrated elite troubleshooting skills, swiftly diagnosing, and resolving complex problems across hardware, software, and peripherals
• Streamlined issue management by efficiently handling queues and implementing innovative enhancements
• Meticulously tracked and closed service items, while proactively identifying opportunities for service improvement. Offered insightful recommendations to enhance service quality and reduce recurring incidents.
• Acted as a reliable liaison between clients and the IS Department, facilitating seamless communication.

Temple HCI Lab

• Participate in a research workshop on CoBoard (collaboration platform) Using Online Whiteboard Templates to Design Data for Computationally Supported Workshops
• Customize the Collaborative digital whiteboard's UI design using past studies feedback to improve productivity
• Develop creativity support tools using React.js and uploading and retrieving collected design data using Firebase
• Collaborating with two undergrad students to generate new feature ideas and research questions for CoBoard

BJ's Wholesale Club • Part-time • 6 mos

JCPenney • Part-time

Description: Developed a movie recommendation system using natural language processing (NLP) techniques and machine learning. The system processes movie details, including genres, keywords, cast, and crew, to create a content-based recommendation model
Key Achievements:
• Applied text processing techniques, such as tokenization and stemming, to extract meaningful information from movie overviews, genres, keywords, cast, and crew
• Utilized CountVectorizer and cosine similarity to build a recommendation engine
• Deployed the recommendation system as a Streamlit web application
• Utilized NLTK for stemming to reduce words to their base or root form, improving the efficiency of text analysis
• Implemented the CountVectorizer to convert text data into numerical vectors suitable for machine learning models
• Utilized cosine similarity for measuring the similarity between movies based on their features