DILARA CETINKAYA
Data Scientist
CONTACT
PROFESSIONAL EXPERIENCE
VOLUNTEER
EXPERIENCES
EDUCATION
Data Scientist familiar with the gathering, cleaning, and organizing data for use by technical and non-technical personnel. Advanced understanding of statistical, algebraic, and other analytical techniques. Passionate about working with youth learners. Strong commitment to enhancing and supporting education. Outstanding communication and problem-solving skills.
Dean's List 2020 Fall and 2021 Spring
Relevant Coursework: Calculus I &
Calculus II, Computer Science
Current to May 2024
Associate of Science: Computer Science
Northern Virginia Community
College - Annandale, VA
Completed rigorous data science training covering
python programming, data analysis, data visualization, statistics, regression models, machine learning models, AWS, SQL, and model deployment.
Working as an intern delivering data science ML
Explainibility and Mortgage Modeling projects to clients in the finance industry.
Deci Tech
DATA SCIENTIST INTERN 02/2022 to Current
Fairfax, VA 22033
adwbea@r.postjobfree.com
Youth Mentor Volunteer Core
Educational Services –
Chantilly, VA
https://www.linkedin.com/in/munise-
dilara-nur-cetinkaya/
https://github.com/DelilahCetinkaya
Tutor Volunteer, Sylvan
Learning Center – Sterling, VA
09/2020 to 08/2021
12/2017 to Current
ADDITIONAL
Languages: Fluent in Turkish,
English
Certifications & Training:
Certificate Degree in Data
Science (Data Science Vista)
TECHNICAL SKILLS
Data Science: Predictive Modeling, Data Visualization, ML Explainability, and Insight Generation
Programming: Python, SQL, Bash Shell Scripting,
PostgreSQL, BigTable, MongoDB
Machine Learning & Data Analytics Tools: Keras Tensorflow, Pytorch, Scikit-learn, Pandas, Numpy, SciPy, Statsmodels, Google Colab, Anaconda
ML OPS: CI/CD Tools: AWS, Github Actions, Docker,
Kubernetes, Flask, FastApi, HerOKU.
SELECTED PROJECTS
Tested the conceptual soundness of the ML model
explainability framework developed for Fair Lending reporting for financial institutions with a Mortgage Default model that was built using XGB.
Examined SHAP, ALE, ICE/PDP, Total Gain, Average Gain metrics, and Friedman H-Statistics.
Oct 2022
Downloaded and sampled 15 million rows of mortgage performance data from Freddie Mac using AWS S3, AWS Athena, and SQL.
Developed XGB model to predict mortgage defaults with special considerations to class imbalance. The final model had an F1 Score of 70%.
Aug 2022
Designed and implemented a software system to
investigate the role of social media in instilling anti- American sentiment among US allies through
misinformation and disinformation efforts. The project encompassed data collection, data handling, machine learning, and insight generation.
SENTIMENT ANALYSIS Jul 2022
MORTGAGE DEFAULT MODELING
ML EXPLAINABILITY FRAMEWORK