Yassine Ait Mohamed

Developed a predictive maintenance system utilizing real-time sensor data and deep learning models (LSTMs, Transformers) to forecast equipment failures with high accuracy.

Implemented a robust data preprocessing pipeline for large industrial datasets, ensuring data quality and consistency crucial for optimal model performance.

Collaborated with engineering teams to seamlessly integrate the system into existing infrastructure, significantly improving operational efficiency and minimizing unscheduled downtime.

Presented comprehensive findings and strategic recommendations to stakeholders, demonstrating the system's potential for substantial cost savings and enhanced asset reliability.

Designed and deployed an automated defect detection system using computer vision and deep learning (CNNs, R-CNN) for industrial components.

Collected, annotated, and augmented a large dataset of industrial images, enhancing model robustness and achieving high accuracy in defect identification.

Implemented advanced image preprocessing techniques to optimize data for deep learning models, contributing to improved detection precision.

Significantly reduced manual inspection time and elevated product quality by achieving high accuracy in defect detection, presenting clear ROI to management.

Developed a robust demand forecasting model for industrial products using a blend of machine learning (XGBoost) and statistical methods (ARIMA, Prophet).

Conducted in-depth analysis of historical sales data and applied advanced feature engineering to extract critical trends and patterns, improving forecast accuracy.

Evaluated model performance rigorously, providing actionable insights and data-driven recommendations that optimized inventory management and production planning.

Contributed to measurable cost savings and enhanced operational efficiency by delivering accurate demand predictions to key stakeholders.