Sanâa AÏT-BELLA

I’m a data scientist focused on turning heterogeneous data into reliable, decision-ready insights. I seek opportunities to work on machine learning, data engineering, data quality, and analytics, with an emphasis on actionable outcomes.

At Plantiverse, I cleaned, standardized, and consolidated heterogeneous datasets (sensor data, Google Sheets, agronomic reports). I designed robust data pipelines and automated the computation of 50+ vegetation indices (NDVI, EVI, SAVI), then developed predictive models to assess plant health using Random Forest and Bayesian approaches.

At EcoBubble, I performed data cleaning, preprocessing, and quality checks, and applied Bayesian modeling (brms) plus missing data imputation techniques (mice). I produced clear dashboards and visualizations for non-technical stakeholders while working autonomously through weekly coordination meetings.

Beyond data science, I bring product-minded implementation experience: I built and maintained a WordPress website for NGO Pangee and supported corporate IT environments as an IT intern at Solocal Group. I hold a Master of Engineering in Applied Mathematics and Computer Science (Data Science, Machine Learning, Deep Learning, NLP, Data Quality, Big Data, Data Visualization, Large Language Models), and I value communication, rigor, and team-oriented problem solving.