Data Scientist Science

Mrudula Krishna Prasad

Boston, MA• *************.**@*****.*** • 857-***-**** • LinkedIn • Github

SUMMARY

Passionate and results-oriented Data Scientist with a Master's degree in Data Science from Northeastern University, adept at driving business impact through quantitative and scientific analysis, advanced analytics and innovative problem-solving. Skilled in deriving actionable insights from complex data, proficient in Python and adept at leveraging modern development tools,excited to contribute to the creation of bold and disruptive AI-led innovations that address global challenges and drive organizational transformation. EDUCATION

Northeastern University - Boston, MA Sep 2021 – May 2023 Master in Data Science GPA: 3.67

Relevant coursework: Data Management and Processing, Supervised and Unsupervised Machine Learning, Algorithms, Natural Language Processing, Perception AI, Machine learning for Database optimization EXPERIENCE

Corcentric - Data Scientist Remote USA Oct 2023 - ongoing

● Spearheaded the development of ETL processes using Apache Spark and Databricks, collaborating with cross-functional teams to achieve a ~250% decrease in processing time for 2M records, while optimizing API bottlenecks and data storage with JSON for efficient fetching and batch processing.

● Engineered data modeling with Zingg for predictive entity matching, incorporating feature extraction, 2-stage end-to-end model training and model evaluation.

● Built a web application with Langchain, LLMs, and Streamlit (RAG implementation) to decrease query processing time by 20% and implemented prompt engineering for efficient document querying.

● Brainstormed and standardised database structure for invoicing while collaborating with data architects to meet cXML invoicing standards.

RadicalX - Artificial Intelligence Engineer Remote USA July 2023 - Oct 2023

● Researched open-source Language Models (LLMs) and selected GPT-3.5 Turbo for the "Career Coach" project, optimizing project efficiency and accuracy.

● Crafted and honed mock user profiles to tailor career coaching experiences utilizing GPT-3.5 Turbo, thereby amplifying user engagement and maximizing adoption potential for production readiness.

● Led the development of a knowledge testing/ Quizzing model in tech-related subjects, establishing a robust knowledge base for Language Model refinement using Artificial Intelligence-based Prompt engineering. Advisor 360 - Data Scientist Boston MA June 2022 - Aug 2022

● Utilized data analysis to identify market correlations, facilitating strategic decision-making and enhancing trade evaluations.

● Enhanced data visualization processes through a Flask-based Python web app, enabling efficient extraction and visualization of Federal Resource data and analysing advisor app usage trends.

● Enhanced client services by developing an 80% accurate sentiment analysis API, providing deeper insights into financial advisor feedback.

SKILLS

Programming Languages: Python, SQL (MySQL), Postgresql (RDBMS), NoSQL Data Analytics & Machine Learning Libraries:Hive, Spark, Numpy, Pandas, Scikit-learn, TensorFlow, NLTK, Matplotlib, Spark, Linear and Logistic Regression, Decision Tree, Random Forest, SVM, KNN, Clustering, Deep learning, Analysis, predictive modeling, Analytical Thinking Statistical Methods: Regression, Correlation, A/B(hypothesis) Testing, Statistics, Data science tools, Data models Cloud Technologies: AWS, Databricks, AWS S3

Data Analysis & Visualization Tools: PowerBI, Tableau, Jupyter Notebook, Excel, data mining, key performance indicators Version Control & Project Management: Git, Github, JIRA, Agile, Confluence, outlook, MS office Other: A/B Test, Data Engineer, Data Reporting, Data Storytelling, Business Intelligence, communication skills, Docker, interpersonal skills PROJECTS

Job Application Tracking and analysis - Link Jan 2024 - ongoing Developed a data-driven job application tracking system using Tableau, resulting in increased applications and response rates by targeting roles with visa sponsorship; utilized Tableau for analysis, leading to improved application consistency and success rate. Image-Based Fashion Recommendation System - Link Jan 2023 - May 2023 Led a team to develop a high-accuracy fashion recommendation system using image search, achieving over 85% accuracy for product recommendations and over 65% for accessories. Achieved top ranking in a peer review for image embedding and dataset processing. Table Union Classification using BERT - Link Sep 2022 - Dec 2022 Automated table union classification using BERT, reducing manual SQL query writing by at least 50% and implementing scalable NLP solution for large datasets of more than 10k records and improved results using TF-IDF vectorization. Resort Management System - Link Sept 2021 - Dec 2021 Implemented dynamic database management, data analysis and visualization features in Altheda resort management system, enhancing user experience and facilitating informed decision-making for both users and administrators using optimized SQL queries. PAPER PUBLICATIONS

● Crop leaf disease classification using Image processing, Ieee Pune Conference 2021

● Music Recommendation Based on Facial Expression, IJLTEMAS 2021

Contact this candidate