MMehmet Ünlü
HomeAboutProjectsNotesResumeContact
TR

Mehmet Ünlü

I study Electronics and Communication Engineering at ITU and build hands-on projects around forecasting, computer vision, and making data workflows faster.

HomeAboutProjectsNotesResumeContact

Projects

Selected work, written as case studies.

These are not just tiles. Each project explains the context, the implementation choices, the measurements, and the parts that still need work.

Intermittent Demand Forecasting System
FeaturedForecastingLightGBMTweedie

Intermittent Demand Forecasting System

A two-stage machine learning system for intermittent demand forecasting on daily product-level sales data.

Products

20k

History

3 yrs

Zero demand

85%

Metrics

WAPE / RMSSE

Case study
ML Pipeline Runtime Optimization
OptimizationNumPyPandas

ML Pipeline Runtime Optimization

Optimized a large-scale ML feature engineering and inference pipeline by reducing unnecessary computation, memory bloat, and Python-level bottlenecks.

Runtime

40m -> 4m

Rows

3M

Case study
Hybrid Visual Odometry System
Computer VisionRAFTORB

Hybrid Visual Odometry System

A confidence-aware visual odometry system combining deep learning-based optical flow and classic computer vision.

Branches

2

Selector

Confidence

Case studySource
Personal Portfolio Platform
Next.jsTypeScriptExpress

Personal Portfolio Platform

A full-stack portfolio platform with dynamic projects, notes, media uploads, admin tools, and secure self-hosted deployment. Active feature development continues.

Stack

Next.js + API

Content

Dynamic

Case studySource
Whisper-Based Speech & NLP System
WhisperNLPHugging Face

Whisper-Based Speech & NLP System

A self-hosted speech transcription and text processing system using Whisper and NLP models.

Languages

TR / EN

Pipeline

STT + NLP

Case studySource
AI-Powered Storytelling / Flutter App
FlutterFirebaseAI Product

AI-Powered Storytelling / Flutter App

A mobile application concept for children and parents using AI-powered storytelling, video, subtitles, and voice processing.

Roles

Parent / Child

Media

Video + Voice

Case studySource
Plant Doc: On-Device Plant Disease Detection
FlutterDartTensorFlow Lite

Plant Doc: On-Device Plant Disease Detection

A Flutter mobile app that detects plant diseases from leaf photos using an on-device TensorFlow Lite model.

Classes

38

Input

224x224

Case studySource
VCAMP Website & Content Platform
ReactViteTypeScript

VCAMP Website & Content Platform

A team-built web platform for the ITU VCAMP project team, combining a public website, content APIs, project pages, team profiles, blog posts, sponsors, and certificate verification workflows.

Team

4-5

Role

Full-stack

Case study