BMM4111 dönem ödevi: Sensör verileriyle sınıflandırma, regresyon ve kümeleme.

Explainable phishing URL detection: 28 engineered features + gradient boosting + rule floors, typosquatting/homoglyph detection, CLI and FastAPI. F1 0.98, ROC-AUC 0.999.

AI/ML Engineer resume and portfolio website showcasing Generative AI, RAG, CrewAI, and LLM projects, certifications, and skills.

Sentiment analysis of Indonesian e-commerce reviews: comparing a classic ML model (TF-IDF + Logistic Regression) with the Gemini LLM API, including leakage-free evaluation, robustness tests, and cost/latency trade-off analysis.

End-to-End Car Price Prediction using Linear Regression with 83% R2 Score

Proyek analisis data komprehensif dan pemodelan prediktif untuk klaim asuransi kesehatan individu periode Januari 2024 – Juli 2025. Pemodelan Machine Learning untuk memitigasi risiko kenaikan klaim dan menjaga keterjangkauan premi.

Prédiction des retards d'avion à la réservation : LightGBM, encodage par la cible sans fuite, SHAP

A machine learning project that classifies news articles as potentially fake or reliable based on text features and trained NLP models.

Physics-aware person re-identification from Wi-Fi CSI using metric learning, signal-structured augmentation, and controlled ablations.

End-to-end research platform for Parkinson's disease classification from single-channel low-cost EEG (NeuroSky TGAM): binary protocol parser, real-time viewer, GAF + CNN with per-patient evaluation.

Smart Shopping Assistant built with Python, Streamlit, Apriori Algorithm & Association Rules for product recommendations and Market Basket Analysis.

My personal portfolio showcasing data science, machine learning, computer vision, data analytics, and web development projects.

RoadGuard AI is a machine learning project that predicts road accident risk based on weather conditions, road conditions, and traffic levels using a Decision Tree Classifier.

Machine learning-based quantitative research and stock selection backtesting

Unified open-source framework for defending RAG systems against data poisoning, InceptionRAG, and MIA using semantic anomaly detection.

ESP32 Wi-Fi CSI research prototype for nonvisual human presence and movement classification using ESP-IDF, Random Forest, Python and Streamlit.

End-to-end battery degradation intelligence platform combining machine learning, battery aging analysis, and interactive visualisation to diagnose degradation mechanism, quantify their contribution, analyse capacity fade, and present actionable insight through a stream lit dashboard

A local-first AI quant research platform: questions are persistent, conclusions are versioned, and prior findings are recalled into the next call. Python + Next.js, AGPL-3.0-only.

AI-Driven Cyber Threat Prediction and Real-Time SOC Intelligence System using Ensemble ML and MITRE ATT&CK

FastAPI + React/TypeScript app serving four ML models: pneumonia X-ray, brain-tumor MRI, Parkinson's voice and stroke risk

Kinship reasoning without a neural network: a sound, set-valued model that derives its rules from opaque symbols. CLUTRR, all six datasets.

Sensor-missingness forecasting notebook with 16 availability masks, core/specialist routing and data-free smoke checks.

DeepKit-ml A lightweight machine learning library built from scratch in Python, implementing core algorithms and optimization techniques.

《机器学习中的数学》(Mathematics for Machine Learning) 中文版 LaTeX 工程与 408 页编译成品 PDF | 基于 dxxzst/mml-book-chinese 译本整合构建

⚡ AI & Tech Explorer | Python Developer 🤖 Building Telegram Bots & Smart Automations 💻 Exploring Python, APIs & Open Source 🚀 Learn • Build • Innovate • Grow 🌌 Turning Ideas Into Digital Reality 🔮 Dream Big. Code Smart. Stay Limitless.

Watch a language model think: next-word predictions and live attention, visualized as a galaxy — runs 100% in your browser.

Phishing email analyzer: SPF/DKIM/DMARC, spoofing, deceptive links, risky attachments + NLP classifier fused into an explained 0-100 risk score. Recall 100%, ROC-AUC 0.998.

Kaggle: verify article contributors with TF-IDF/SVD embeddings, author profiles and leakage-free XGBoost (score 0.88)

Budgeted counterfactual debugging for ML pipeline regressions, including interacting changes across models, data, preprocessing, configs, and environments.