Real Estate Data Scientist

Suraj Vujjini

410-***-**** • **********@*****.***

Baltimore, MD • LinkedIn.com/in/SurajVujjini • GitHub.com/SurajVujjini

SUMMARY

Data Scientist with 2+ years’ experience in machine learning, data modeling, and analysis for the healthcare and real estate industries. Knowledgeable about building data pipelines and collaborating with cross functional team members on stakeholder assignments. Quick learner passionate about implementing solutions that eliminate pain points. Seeking a data science role to build prediction models at an enterprise focused on efficiency and innovation.

TECHNICAL SKILLS

Languages: Python, R, JavaScript, UNIX Shell Scripting, MySQL, Oracle SQL Developer, Java (Oracle SE 8 Certification)

Frameworks & Libraries: PyTorch, TensorFlow, scikit-learn, PySpark, Apache Spark, Cassandra, and MongoDB, Ab Initio

Cloud & Data Visualization: AWS, Azure (Azure Developer Associate Certification), Tableau, PowerBI, SAS

EDUCATION

University of Maryland, Baltimore, MD May 2023

Master of Science in Data Science GPA: 3.7

Coursework: Data Management, Platforms for Big Data Processing, Machine Learning, Cybersecurity Law and Policy

Anurag University, India May 2021

Bachelor of Technology in Civil Engineering

Coursework: Data Structures and Algorithms, Probability and Statistics

EXPERIENCE

Data Scientist, Austin, TX Aug 2022 – Jan 2023

Blue Cross Blue Shield Association

Built process to leverage SQL to extract, transform, and load (ETL) medical data totaling 1M+ customers, and structured data for analysis, enabling deeper data analysis and leading to new customer insights from legacy data

Developed and fine-tuned ML models using libraries (SciKit-learn, TensorFlow), improving health forecast capabilities

Collaborated with cross-functional teams to develop production-ready code and created documentation, ensuring scalability/maintainability and decreasing training time by 50%

Helped with deployment of ML models on AWS (Amazon SageMaker), facilitating easy cloud model deployment

Worked with diverse cross-functional teams (domain experts, engineers, business analysts) and utilized Apache Spark to enhance data models through NLP techniques, improving data performance by 3X

Acculytixs, India Jan 2020 – Aug 2021

Data Science Intern

Engineered SQL and Python code for data preprocessing and deployed predictive models using ML techniques to drive data-driven insights, resulting in capabilities to forecast pricing of local real estate market

Collaborated with cross-functional team members to integrate market trends into models and created Tableau dashboards to simplify complex model outputs, improving stakeholder visibility and decision making capabilities

Quantified project potential through advanced analytics, improving investment likelihood by 100%

PROJECTS

Hotel Booking Cancellations Forecast Model: bit.ly/Vujjini Sep 2022 – Present

Built tool to predict hotel booking cancellations using Python (Pandas, Seaborn, Scikit-learn)

Conducted EDA and data cleaning and implemented logistic regression, decision tree, random forest, and gradient boosting algorithms, achieving 87% accuracy when compared to real time cancellations

Baltimore Crime Analysis: github.com/SurajVujjini/Baltimore-Crime-Analysis Sep 2021 – Oct 2021

Analyzed crime dataset with 250k+ rows (Python, SQL, Tableau) and extracted/cleaned data in Jupyter Notebook

Uploaded data to AWS SQL server, established connections with MsSQL, and created dynamic visualizations in Tableau, enabling real-time updates

SKILLS & INTERESTS

Software: Microsoft Office 365 (Word, PowerPoint, Excel, Outlook), Jira, GitHub, Tableau, PowerBI, Qlik, A/B Testing

Work Authorization: Eligible to work in the US without sponsorship

Contact this candidate