Ismail Can Oguz

Open to roles in AI for Science / ML for Materials / Research Engineering

#

I’m a computational materials scientist who builds machine-learning + simulation workflows to accelerate discovery and decision-making. I’m currently a researcher at DIFFER — Dutch Institute for Fundamental Energy Research in Eindhoven, NL, where I work on data-driven materials discovery.

Quick links

#

• CV (PDF): Download
• Google Scholar: https://scholar.google.com/citations?hl=tr&user=VFi3h0sAAAAJ
• ORCID: https://orcid.org/0000-0002-8673-7219
• GitHub: https://github.com/isocan
• Kaggle: https://www.kaggle.com/ismailcanoguz

What I do

#

• ML + scientific modeling: build reliable pipelines that combine learned surrogates with physics/DFT to cut iteration time and cost.
• Production-minded data work: clean data, craft features, train/evaluate models, and ship robust artefacts (reports, dashboards, APIs).
• Collaboration first: I enjoy team competitions, open repos, and reproducible research.
• ML + DFT workflows for surface science and electrocatalysis.
• Equivariant GNNs / interatomic potentials (e.g., MACE, NequIP, Equiformer-style).

Selected ML & Data Science projects

#

• Energy & Emissions Forecasting — Predicts building energy use and CO₂ emissions from attributes; includes feature engineering and interpretable regression workflow.
  Repo: https://github.com/isocan/energy-emission-prediction

• Credit Scoring for Limited Histories — End-to-end credit default model with data prep, model comparison, and SHAP-based interpretability.
  Repo: https://github.com/isocan/credit-scoring-model

• Automated Product Classification (NLP + CV) — Classifies e-commerce items by combining text (BERT) and image (VGG16 / classic features) signals.
  Repo: https://github.com/isocan/automated-product-classification

• E-commerce Customer Segmentation (RFM + Clustering) — Segments customers for retention and LTV uplift with actionable marketing insights.
  Repo: https://github.com/isocan/ecommerce-customer-segmentation

• Fruit Classification — Cloud Pipeline — Scalable training/inference with AWS (EMR, S3) and PySpark for distributed preprocessing.
  Repo: https://github.com/isocan/fruit-classification-cloud-deployment

• Food Product Analytics for a Nutrition App — Data analysis + scoring for health, environmental, and packaging impacts.
  Repo: https://github.com/isocan/food-product-analysis-nutrition-app

• World Bank EdTech Opportunity Scan — EDA on global education indicators to identify promising expansion markets.
  Repo: https://github.com/isocan/world-bank-edtech-opportunities

Latest publication

#

Ismail Can Oguz, Nabil Khossossi, Marco Brunacci, Haldun Bucak, Süleyman Er.
Machine Learning–Accelerated Discovery of Earth-Abundant Bimetallic Electrocatalysts for the Hydrogen Evolution Reaction. ACS Catalysis (2025).
DOI: https://doi.org/10.1021/acscatal.5c04967

Competitions

#

• Kaggle · Catechol Benchmark Hackathon (NeurIPS 2025 DnB) — Rank 24 / 227. Leaderboard: https://www.kaggle.com/competitions/catechol-benchmark-hackathon/leaderboard

• Kaggle · NeurIPS Open Polymer Prediction 2025 — Team rank 219 / 2240 (bronze). Competition: https://www.kaggle.com/competitions/neurips-open-polymer-prediction-2025

Tech I use

#

Python, pandas, NumPy, scikit-learn, PyTorch, PySpark, AWS (EMR, S3), Docker, Linux/HPC, plus scientific stacks for atomistic modeling (DFT workflows, equivariant GNNs).