Ufuk Y.
Data Scientist
One of his key achievements was leading a high-impact project for a major airline, where he developed a demand forecasting and product load optimization system for in-flight sales. The solution addressed complex data and operational constraints, resulting in a 7% increase in monthly profit and a 20% reduction in product waste.
Ufuk delivers data science solutions that combine strong technical foundations with clear business impact.
Main expertise
Python5 years
Data Science5 years
SQL5 yearsExperience4
Senior Data Scientist
- Developed a predictive system for in-flight sales forecasting and inventory optimization, enabling data-driven product loading strategies for airline operations
- Increased monthly profits by 7% and reduced product waste by 20%, contributing to the airline being recognized among Turkey’s 50 most innovative companies
- Conducted customer segmentation using Google Analytics data and K-Means clustering to uncover purchase patterns and demographic insights for targeted marketing
- Built a Generative AI Text-to-SQL system using LangChain and LlamaIndex, enabling natural language querying of databases for non-technical users
- Delivered a Data Science training program for Dashen Bank in Ethiopia, teaching 8 professionals machine learning and statistical analysis through hands-on projects
- Contributed to the SafeRoute-6G research initiative, developing models for fuel consumption, rest stop detection, and traffic accident hotspot analysis
PostgreSQLPythonSQLData Science
TensorFlowData Scientist
- Developed predictive models for early redemption and credit prepayment risk in deposit and loan accounts using survival analysis techniques (Cox proportional hazards, Kaplan–Meier) and machine learning (XGBSE)
- Calculated core deposit ratios to evaluate customer retention and deposit stability, supporting long-term financial planning and risk assessment
- Designed and implemented a shift optimization system driven by sales predictions per store aisle, improving staffing efficiency and operational performance
PythonSQL
Azure ML
Vertex AIJunior Data Scientist
- Led the migration from SAS to SQL for credit risk analytics, ensuring a seamless transition of data pipelines, analytics workflows, and reporting while preserving output fidelity
- Optimized large-scale data processing in SQL and implemented scheduled workflows aligned with IFRS 9 credit risk standards
- Designed a configurable time series forecasting model using PySpark on Microsoft Azure, enabling flexible customer demand predictions across industries
- Delivered a scalable forecasting solution featured in the Azure Marketplace
- Engineered an end-to-end real-time big data pipeline using the Cloudera ecosystem, integrating Python, HDFS, Hive, Impala, Druid, and Superset for seamless ingestion, processing, and visualization of streaming data
PythonSQL
SAS
Hadoop
Apache Superset
PySparkSoftware Engineer
- Collected and labeled image data for model training in an image processing pipeline aimed at real-time license plate detection
- Performed web scraping to gather a comprehensive dataset of license plate images, followed by manual labeling of individual letters and numbers
- Developed a real-time license plate detection system using YOLOv3, leveraging the Darknet-53 CNN architecture with 53 convolutional layers for high-accuracy object detection
- Preprocessed and curated training data to ensure optimal performance and generalizability of the detection model
PythonData Science
OpenCV
Pandas
LinuxEngineering excellence
All Data Scientists who have applied to Proxify are scored from 0 to 300 on engineering excellence, one of the five parameters we evaluate. This score reflects engineering excellence only, based on interviews, take-home assignments, live coding sessions, and/or on-the-job performance reviews. The curve shows how all evaluated Data Scientists are distributed across that range, where our acceptance threshold for this parameter sits, and where Ufuk stands.
Score 179 · Top 15% of engineers
Certificates 2
Issued Jan 2024 - Expires Jan 2025
Credential ID B94692A4FE34A7EC
PythonData ScienceAzure ML
Machine Learning
Issued Feb 2022
Issued Jan 2024 - Expires Jan 2025
Credential ID B94692A4FE34A7EC
PythonData ScienceAzure MLMachine LearningEducation
Stop browsing.
Get matched faster.
Talk to an expert and get tailored matches from our network in just 2 days.
A network of over 6,000+ tech experts
Get matched with perfect-fit talent in 2 days on average
Hire quickly and easily with 94% match success