Machine Learning Data Scientist
Resume:
Vijila Yesudhas
SUMMARY
Data Specialist and Data Scientist with 2+ years of experience in data
management, analysis, correction, and advanced machine learning. Proficient in SQL, Python, and PySpark, with expertise in ETL processes, data science techniques, and handling large datasets. Skilled in the Hadoop ecosystem (HDFS), JSON data management, and building machine learning models for predictive analytics. Experienced in modern development environments including VS Code, Google Colab, Jupyter Notebook, and DBeaver for efficient data analysis and debugging workflows.
Hands-on with Trino for distributed SQL querying, Apache Iceberg for managing large analytic tables, and MinIO for scalable object storage solutions. Specialized in healthcare data, particularly medical claims processing and data corrections, ensuring accuracy and compliance with industry standards. Proven ability to manage high volumes of records efficiently, build predictive models, and deliver real-time insights that support data-driven decision- making. Strong background in data visualization using Tableau and Seaborn.
Experienced in Exploratory Data Analysis (EDA), data pre- processing, and implementing decision tree models to analyze key customer attributes influencing loan acquisition. Recently completed hands-on projects involving advanced machine learning models and AI-driven business solutions, showcasing strong applied knowledge in real-world business contexts.
EXPERIENCE
UM/CM Data Specialist
SAN ANTONIO • 02/2023 - 03/2024
● Managed high volumes of data, ensuring quality,
consistency, and accuracy.
● Collaborated with cross-functional teams to support data- related projects.
● Provided technical support and recommendations by processing claims during high-volume system transitions.
● Implemented data validation rules to ensure data reliability.
● Audited claims payment accuracy and resolved discrepancies.
● Assisted in UM/CM approvals, denials, and appeals, preparing correspondence and researching returned mail.
● Created authorization numbers and verified crucial information with medical service coordinators.
● Maintained detailed operational records, delivering insights for managerial review.
CONTACT
**************@*****.***
San Antonio, TX 78254
https://www.linkedin.com/in/viji
la-yesudhas-867974262/
SKILLS
● Programming
Languages &
Libraries: SQL, Python,
PySpark, Pandas,
NumPy
● Databases & Query
Engines: PostgreSQL,
SQL Server, Trino
● Data Formats: JSON,
Excel, CSV
● Data Management &
Analysis: Developing
ETL Pipelines, Data
Corrections, High-
Volume Data Handling,
Apache Iceberg, MinIO
● Office Tools: Microsoft
Excel, Word, SharePoint,
Outlook
● Coding Tools: VS Code,
Google Colab, Jupyter
Notebook, DBeaver
● Data Visualization:
Tableau, Seaborn
EDUCATION
Post Graduate Program in AI
& ML: Business Applications
The University of Texas at
Austin
Mar-2025
● Recognized for meeting tight deadlines and resolving data discrepancies efficiently.
PROJECTS
Personal Loan Campaign Prediction
Program: PGP-AIML-BA-UTA-INTL, UT Austin
● Built a predictive model to identify bank customers likely to purchase personal loans.
● Applied EDA, data pre-processing, and decision tree modeling.
● Provided insights to help the bank optimize its marketing strategies.
Tools Used: Python, Pandas, NumPy, Seaborn, scikit-learn FoodHub Analysis
Program: PGP-AIML-BA-UTA-INTL, UT Austin
• Conducted EDA to analyze restaurant demand and customer preferences.
• Delivered business recommendations to enhance customer experience and operations.
Tools Used: Python, Pandas, NumPy, Seaborn
Credit Card Users Churn Prediction
Program: PGP-AIML-BA-UTA-INTL, UT Austin
• Built classification models to predict customer churn for Thera Bank.
• Applied oversampling/undersampling to handle class imbalance.
• Conducted hyperparameter tuning to improve model performance.
Tools Used: Python, Pandas, NumPy, Seaborn, scikit-learn, XGBoost Plant Seedling Classification (CNN-Based)
Program: PGP-AIML-BA-UTA-INTL, UT Austin
• Developed a Convolutional Neural Network (CNN) to classify plant seedlings into their respective categories.
• Applied deep learning techniques for image classification. Tools Used: Python, TensorFlow, Keras, OpenCV
Stock Market News Sentiment Analysis & Summarization Diploma in Microbiology
Jul-2006
Diploma in Lab Technology
Jul-2004
CERTIFICATIONS
INTRODUCTION TO TABLEAU
Oct-2024
PYTHON FOUNDATIONS
COURSE
Sep-2024
DATA ENGINEERING
ESSENTIALS USING SQL,
PYTHON, AND PYSPARK
May-2024
Program: PGP-AIML-BA-UTA-INTL, UT Austin
• Conducted sentiment analysis on financial news articles.
• Applied NLP techniques to summarize news and predict stock sentiment trends.
Tools Used: Python, NLP, NLTK, Hugging Face Transformers
.
Contact this candidate