Data Scientist / ML Engineer

Mustafa Sezer Başar

Data Scientist / Machine Learning Engineer

Ankara, Türkiyemustafasezerbasar@gmail.comgithub.com/mustafa-sezer-basarlinkedin.com/in/mustafa-sezer-başar

Professional Summary

Database analyst at a retail group, leading a three-person technology team. Works on end-to-end ML pipelines, RAG architectures and measurement design, tying a model's output to an actual business decision. Treats measuring how wrong a method is as part of the job: control groups, placebos and hypotheses written before the run.

Highlights

95% reduction in operational errors
2 AI products built end to end
200% ad ROI (profit over spend)

Skills

Data Science & AI: Python (pandas, scikit-learn, NumPy) · RAG architecture, LLM API integration, structured output · Computer Vision (face_recognition, Tesseract OCR) · Power BI, advanced Excel (reporting and data preparation) · Multi-Criteria Decision Making (WASPAS, VIKOR, MACBETH)
Databases: SQL (joins, window functions, indexing) · PostgreSQL (pgvector) · MySQL, SQLite
Web & Full-Stack: JavaScript / TypeScript · React, Next.js · Express.js, REST API · Puppeteer

Projects

Tax Audit System with Rule Extraction from Legislation

The rule engine of a field audit system built for an audit firm: an end-to-end working component that reads legislation with RAG and turns it into audit rules. The corpus is self-sourced: a collector he built pulls statutes and high-court rulings into a database, and the RAG layer works on top of it. Rules are held as JSON with their statute reference and validity period, pass a human review gate, and are then applied deterministically by a Go service. The LLM is not in the hot path — it runs offline — so every audit run stays reproducible and auditable. Taxpayer data never leaves the system: the external language model only ever sees public legislation.

Python (LLM)
Go
Next.js
MySQL

Data Quality Audit & Reporting Tool

Tool that cleans messy tabular data into a multi-sheet Excel report — and, more to the point, measures the cleaner's own error rate. It generates a synthetic file with known defects and scores against ground truth, which makes two outcomes visible that cleaning tools never report: errors missed in silence, and correct cells destroyed. Against an ordinary twenty-line pandas cleaner: 10 silent errors versus 361. The measurement found three defects in the tool itself (61 correct salaries multiplied by twelve, 28 required fields silently blank, 8 malformed emails with no log entry), none of them visible in the output. A pay-gap analysis reads 3.37% on dirty data and 3.86% after cleaning, against a true 3.85%. 134 tests.

Python
pandas
openpyxl

Schedule Risk and Critical Path Analysis

A simulation study measuring how likely a project schedule is to meet its committed date. On a twenty-activity ERP migration schedule the deterministic critical path gives 105.2 days; simulated 40,000 times from the same estimates, that date is met in only 34% of runs. The gap comes from the shape of the network rather than the estimates: every merge point waits for the slowest of several parallel paths. Label-free control networks show the project finishing 12.6 days later purely from adding parallel paths, with no task lengthened. The criticality index was also measured to tie six activities at 1.0 while their influence on the finish differed 4.6-fold. Interventions were compared with common random numbers; the mechanism in the pre-registered hypothesis was refuted and reported as such.

Python (NumPy
SciPy
Monte Carlo)

Experience

June 2026 – PresentAnkara
Paulmark
Database Analyst — Business Development & Strategy
- Leads a three-person technology team, moving a Nebim V3 and Power BI retail stack off Excel-based processes.
- Closed the gap between the teams' own Excel files and the master data; inconsistencies used to surface only once they had grown.
- Compared the company's sales against the TÜİK retail sales index and built a sales forecast model driven by the index's three-month projection.
September 2024 – February 2025Cappadocia
Myrco Spa Center (Barceló Cappadocia)
Co-Founder / Operations Lead
- Ran the spa centre inside the Barceló Cappadocia hotel as a subcontractor; built the 15-person team from scratch.
- Cut team-caused errors 95% in two months with a Spa Management app he built; error = an unauthorised entry counted on camera, or a session off the sold duration by ±5%.

Education

August 2022 – July 2026
Hacettepe University
BA in Business Administration
GPA 3.12/4.00 · English-medium · Graduated
September 2018 – August 2022
Middle East Technical University (METU)
Civil Engineering
English-medium · Transferred to Business Administration at Hacettepe University

Languages

Turkish (Native) · English (Advanced — English-medium undergraduate education)

Leadership & Communities

Founding team member, Hacettepe Management Consulting Club (HMCC)
Debate competitor at METU; special speaker award at the novice tournament