↩ Work / EXPERIENCE

Data Scientist.Employment

Period
Jul 2018 - May 2019
Company
RINTIO ↗

Built data infrastructure and crop-yield forecasting for Duniya, Rintio's farmer-facing smart-farming MVP for Beninese farmers.

  • Designed and deployed a production data stack using Hadoop, Apache Spark and Elasticsearch, processing hundreds of gigabytes of agricultural data from multiple sources into ML-ready features.
  • Built regression-based crop-yield forecast models, primarily for maize with additional models for beans; achieved R² above 80% in most cases.
  • Developed crop-yield models for a farmer-facing smart-farming web-application MVP combining predictive features with Apache Superset visualizations; the application was still in testing when I left.
  • Delivered an executive data & AI training mission to Société Générale Maroc’s top management, covering banking-specific use cases and hands-on labs.

[•] PROJECTS & USE CASES

4 ENTRIES
01

Big data platform for precision agriculture

Problem / Need
Agricultural data arrived in varied formats and needed a unified storage and compute layer for analysis and product development.
Solution
Designed and deployed a production data stack combining a Hadoop data lake, an Apache Spark cluster, and Elasticsearch. Processed hundreds of gigabytes of agricultural data from multiple sources and built ingestion and transformation pipelines to produce ML-ready features.
Tools

Hadoop·Apache Spark·Elasticsearch·Python

02

Crop yield forecast models

Problem / Need
The farmer-facing smart-farming MVP required crop-yield forecasts based on agricultural data.
Solution
Developed regression-based crop-yield forecast models, primarily for maize with additional models for beans. Achieved R² above 80% in most cases.
Tools

Python·scikit-learn·Apache Spark

03

Farmer-facing smart-farming web-application MVP

Problem / Need
The product needed to present crop-yield predictions alongside agricultural data visualizations for farmers.
Solution
Developed crop-yield models for a farmer-facing web-application MVP that combined predictive features with Apache Superset visualizations. The application was still in testing when I left.
Tools

Apache Superset

04

Data & AI executive training for Société Générale Maroc

Problem / Need
Société Générale Maroc’s top management needed structured exposure to data and AI applications in banking to inform strategic priorities.
Solution
Designed training content and developed lab use cases tailored to banking applications of data and AI, delivered to Société Générale Maroc’s top management in a single training mission.
Tools

Training content design·Lab use case development·Python

← Work