class AbdallahHashad:
role = "Machine Learning Engineer & Data Scientist"
location = "Cairo, Egypt πͺπ¬"
edge = "CFA-level valuation + DCF modelling + professional appraisal work"
def building(self):
return ["end-to-end ML pipelines", "leakage-proof feature engineering",
"tuned gradient boosting models", "quantitative finance tooling"]
def current_focus(self):
return {"learning": ["Hands-On ML (GΓ©ron)", "Linear Algebra (Strang)", "SQL"],
"goal": "models that answer real economic questions, not just minimise loss"}π Portfolio: abdallah-hashad.vercel.app Β β’Β π Kaggle: abdallahhashad0 Β β’Β βοΈ Medium: @abdallahhashad029
| Project | What it does | Stack |
|---|---|---|
| π moscow-real-estate-price-prediction | 0.98 RΒ² CV β CatBoost / XGBoost / LGBM ensembles, SHAP analysis | Python CatBoost SHAP |
| πΎ food-price-inflation-analysis | ML pipeline predicting global food price shocks (1990β2024) | Python LGBM Power BI |
| π‘ airbnb-revenue-prediction | Revenue model on 90k+ EU listings, incl. leakage detection | Python CatBoost |
| π©Ί Diabetes-classification | 6 classifiers with tuned sklearn pipelines | Python scikit-learn |
| π student-performance-prediction | Score regression with sklearn pipelines | Python scikit-learn |