Want to collaborate?

Right now, you can get in touch with me for a few things:
Beta testing new products
Brainstorming
Open Source Contributions
+ more
Follow

Barkin Cavdaroglu

Junior at college double majoring in computer science and mathematics. Interested in mathematical optimization and machine learning.
Read more
I'm available for
Barkin's Collections

Personal Projects

3 Highlights
2022
Jan 01, 2022
Jan 01, 2022
Excited to join Meta AI as Software Engineer Intern! 🎉
Read more
Software Engineer Intern, Facebook
2021
Jun 24, 2021
Jun 24, 2021
  • Developed several machine learning models and neural networks using Sklearn and TensorFlow to predict whether a credit card transaction is fraudulent or not with 0.86 recall, 0.86 precision and 0.93 balanced accuracy scores.

  • Used hyperopt library for hyperparameter tuning via TPE for LGBoost, XGBoost and CatBoost models which resulted in an improvement of 0.15 in balanced accuracy score.

  • Used methods such as Stratified K-Fold and SMOTE-Random Under Sampling to deal with exceedingly imbalanced data.

The notebook can be viewed here.
Read more
Jun 20, 2021
Jun 20, 2021
  • Designed and developed a full-stack portfolio tracker web application using Reactjs, Redux, MongoDB, Express.

  • Designed RESTful backend server with daily/hourly/weekly crone jobs to keep stock data regularly updated and stored in MongoDB to minimize the number of API calls.

The app can be viewed here.
GitHub Repository can be viewed here.
Read more
Jun 18, 2021
Jun 18, 2021
Tools: MATLAB, Python, GAMS, MapReduce, Hadoop, and Message Passing Interface (MIP)

  • Utilized distributed optimization algorithms with consensus dynamics, specifically proximal point algorithms such as ADMM, in asynchronous scenarios to find near-optimal solutions to convex and non-convex problems using graph topology in the context of peer-to-peer energy market.

  • Reformulated problems with non-convex constraints using convex analysis and found optimal solutions using ADMM with zero duality gap.

  • Conducted rigorous literature review on convex analysis and optimization and meeting with my advisor weekly to present my findings.

More

I worked with a professor on this project since the beginning of March. The end goal is to create a prototype of an energy market that exists on the blockchain. My work mainly dealt with solving various optimization problems related to the energy market in a distributed manner and conducting literature review about distributed optimization.

To get me up to speed, professor has assigned me problem sets from his graduate course that involved solving optimal power flow problems using GAMS and MATLAB. Later on, I learnt about convex optimization by reading Stephen Boyd's and Tyrrell Rockafellar's works, among others, and coded optimization algorithms. 
Read more
Jun 18, 2021
Jun 18, 2021
Ended my journey as Undergraduate Researcher at LIINES!
Read more
Undergraduate Researcher, LIINES
Apr 09, 2021
Apr 09, 2021
Helped organize DDC's second annual Designathon event that brought together students to design solutions to equity problems in education.
Read more
Loading...