Uğur Selim Özen

Data Engineer

Teknasyon•  January 2022 - December 2024

● Writing event-driven developments using Python for ingesting raw data from Producer into BigQuery data warehouse with Apache Kafka. ● Building daily and hourly ETL pipelines using Python and SQL to load data from BigQuery data warehouse to PostgreSQL analytical database for reporting or machine learning projects. ● Orchestrating event developments and ETL data pipelines with Apache Airflow, and designing notification systems with Slack alerts. ● Creating and Developing Dashboards according to business requirements with Apache Superset ● Unsupervised Spam Detection project using Python based on user's mobile phone call detail records data with a country convergence approach ● Unsupervised Time Series Anomaly Detection project using Python for alerting business teams about the most important KPIs

Data Science Bootcamp Student

Hepsiburada•  September 2021 - May 2022

This is a 16 Week data science bootcamp program sponsored by Hepsiburada and I have the following curriculum for my bootcamp education ; Shell - Bash Scripting , NumPy , Pandas , Matplotlib ,Seaborn , Exploratory Data Analysis , Visualization , Oracle SQL , PostgreSQL , Cassandra , MongoDB , pymongo , Linear Regression , Web Scraping with BeautifulSoup and Selenium , Basic Machine Learning Terms (Overfitting , Underfitting , Train/Validation/Test Split) , Tensorflow Models , Feature Engineering , NLP (textblob, NLTK, stacking, squeezing, POS tagging, tf-idf) , RESTful APIs , NoSQL , k-means , Custering algorithm (DBSCAN) , (Dimension reduction , PCA , SVD , LSI ) , A/B testing experience design and interpretation , Distributed databases ( Dask, Spark, Spark MLlib , Spark SQL , Hadoop , HiveQL)

Data Science Internship

Data Glacier•  September 2021 - December 2021

This is 13 Week data science internship program and I have the following curriculum for my internship ; Version Control (Git) / Github , Agile (Scrum/Kanban) , Docker , Flask / Heroku , Pycharm , API , Jupyter , Python , Feature Engineering , Model Interpretation , Model Governance , Stakeholder Communication

Data Analytics & Data Science Bootcamp Student

Enerjisa•  September 2021 - November 2021

I have completed 8-week Data Analytics & Data Science Bootcamp program and I have completed my final project with my teammates and it is related to energy sector and fraud detection classification problem.We have covered following curriculum in the bootcamp ; Numpy , Pandas , Matplotlib , Seaborn , Plotly , Scikit-learn , Basic Statistics , Business Understanding , Data Understanding , Exploratory Data Analysis , Visualization , Feature Engineering , Modelling (Train/Test/Validation , Kfold Cross-Validation) , Time Series Analysis , Evaluating & Deployment (Hyperparameter Tuning)