a
attoussi_ouais

atoussi ouais

@attoussi_ouais

Machine Learning Engineer

Argélia
Árabe, Inglês, Francês
Algumas informações são exibidas no idioma inglês.
Sobre mim
Machine Learning Engineer with a Master's degree specializing in time series forecasting and predictive modeling. Recent project: Polypropylene price forecasting using XGBoost — R²=0.80, MAE=178 CNY/ton, 2.3% error rate on unseen test data, deployed as a live Streamlit dashboard with confidence intervals. What I deliver: ✔ Clean, documented Python code ✔ Proper validation — no data leakage ✔ Feature engineering from raw data ✔ Interactive Streamlit dashboards ✔ Full source code included Live demo: polypropylene-price-forecasting.streamlit.app... Saiba mais

Habilidades

a
attoussi_ouais
atoussi ouais
offline • 
Tempo médio de resposta: 1 hora

Conheça meus serviços

Análise de Séries Temporais
I will create sales demand and business forecasting model using ai and python
A partir deUS$ 95 /projetoMais detalhes
Machine learning
I will urgently fix your python machine learning model and improve accuracy
A partir deUS$ 90 /projetoMais detalhes

Portfólio

Experiência profissional

Freelancer.com

Machine Learning Engineer (Freelance)

Freelancer.com • Autônomo

Mar 2024 - Present • 2 yrs 2 mos

Building end-to-end machine learning pipelines for time series forecasting and classification problems. Key project: Polypropylene futures price forecasting model using Walk-Forward XGBoost with 36-month rolling window validation. Results on unseen test data: - R² = 0.80 - MAE = 178 CNY/ton (2.3% average error) - 87.5% coverage inside 95% confidence interval - Deployed as interactive Streamlit dashboard Technical stack: Python, XGBoost, Optuna, Streamlit, Plotly, Pandas, Scikit-learn, yfinance, FRED API Delivered: full source code, predictions CSV, feature importance analysis, confidence intervals, live dashboard deployment.