Machine Learning Data Science

Shashank Shekhar

New Jersey, NJ, ***** +1-703-***-**** ********@****.**.*** LinkedIn GitHub Portfolio EDUCATION

Katz School of Science & Health - Yeshiva University Jan 2024 - May 2025 Master of Science, Data Analytics & Visualization (GPA: 3.58) New York, NY

• Coursework: Machine Learning, Data Science, Structured Data Management, Computational Math's & Statistics, Storytelling IIIT Bangalore Apr 2023 - Dec 2023

Advance Certificate Programme, Data Science (GPA: 3.4) Bangalore, INDIA

• Coursework: Machine Learning, Data Toolkit

Guru Nanak Institute of Technology May 2018 - May 2022 Bachelors, Computer Science Engineering (GPA: 3.6)

• Coursework: Machine Learning, Data Structure

Kolkata, INDIA

WORK EXPERIENCE

Yeshiva University, Shevet Glaubach Center AI Chatbot Developer Jan 2025 - May 2025 New York, NY

• Programmed a GPT-4o-based academic chatbot using RAG architecture, enhancing context-aware responses and improving student engagement

• Scraped and stored content in ChromaDB vector DB from Azure Blob Storage, ensuring efficient data retrieval and management

• Enabled multilingual voice input, semantic search, and responsive UI, significantly enhancing student access and user experience

• Developed a responsive UI and prompt templates, supporting dynamic and low-hallucination conversations, which improved user interaction

Harman Connected Services Pvt. Ltd. Associate Software Engineer Apr 2022 - Feb 2023 Pune, INDIA

• Collaborated with cross-functional teams to design and deliver C#/.NET-based feature enhancements for ImedOne, improving client satisfaction by 10%.

• Executed predictive analysis on 50,000 mental health records using Python and scikit-learn, SVM model achieved 91% precision.

• Participated in writing and maintaining robust code, ensuring the implementation of object-oriented design patterns.

• Enhanced diagnostic accuracy for high-risk groups, cutting null error rate from 69.34% to 24%. PROJECTS

NYPD Calls for Service Data GitHub Sep 2024 - Dec 2024

• Researched NYPD calls for service data in Tableau, revealing Brooklyn as the highest-crime borough with peak incidents from 12 am to 3am.

• Delivered borough-specific crime insights through Tableau dashboards, enabling data-backed decisions by non-technical stake- holders and resource planners.

E-commerce Purchase Prediction GitHub Oct 2024 - Oct 2024

• Built a KNN model (97.13% accuracy) to identify three customer segments (high-value, moderate, low-engagement) for targeted marketing.

• Unlocked targeted marketing strategies to boost conversions through data-driven segmentation. Dropout Rate Prediction GitHub Aug 2024 - Sep 2024

• Constructed the Random Forest model with 87% AUC, outperforming Decision Tree's 79% AUC, with 69% precision and 68% recall on imbalanced classes.

• Tested two feature sets, with the 23-attribute Random Forest model achieving 87% AUC and 84% accuracy, surpassing Decision Tree performance.

• Analysed 73,000 records to uncover trends like higher dropout rates in larger schools and more Regents diplomas in low-needs districts, providing actionable insights.

Disease Data Modelling and Warehousing Project GitHub Mar 2024 - May 2024

• Architected a scalable data model in PostgreSQL with a dimensional structure and ETL pipelines to optimize disease data storage and streamline data flow.

• Created ER diagrams using DbSchema and built dashboards for visualizing disease trends, enhancing healthcare decision-making.

• Proposed AWS-based architecture, comparing Snowflake vs. PostgreSQL for performance and cost. TECHNICAL SKILLS

• Programming & Development: Python, SQL, C#, HTML, JavaScript, Flask, Git, REST API, OOPS, Agile Development

• Machine Learning & AI: Supervised & Unsupervised Learning, NLP, Neural Networks, Lang Chain, OpenAI GPT- 4o/Whisper, RAG Architecture, ChromaDB

• Data Analysis & Visualization: NumPy, Pandas, EDA, Feature Engineering, Matplotlib, Seaborn, Tableau, Data Storytelling

• Databases, Cloud & Infrastructure: MSSQL, PostgreSQL, Oracle, Azure, AWS, Azure Blob Storage, Canvas API CERTIFICATIONS

• Advance Certificate Programme in Data Science: IIIT Bangalore, Apr 2023 - Dec 2023 Bangalore, INDIA

Contact this candidate