S

scikit-learn

Open industrial IoT platform for predictive maintenance: four sensor nodes, a FastAPI backend, Isolation Forest anomaly detection and a live Next.js dashboard. Reveal before failure.

Machine learning for Ethereum/GBP market data using technical indicators, regression models, neural networks and model evaluation.

Machine learning for image classification using HOG, PCA, traditional classifiers, CNNs, MobileNetV2 transfer learning and Vision Transformers (ViT).

6 machine-learning projects: CNN digit recognition 98.83%, spam detection 96.32%, sales prediction R2 0.91, plus NLP and a recommender | scikit-learn, TensorFlow

• Developed and deployed an interactive media analytics dashboard analyzing 150 English-language political news articles across six major South Korean publications. • Applied TF-IDF vectorization and K-Means clustering to identify recurring themes and examine differences in political news coverage across publications. • Designed a Snowflake cloud analytics layer using relational tables and SQL reporting views to support publication-level comparisons, topic distributions, and NLP cluster analysis. • Integrated Snowflake with Streamlit using RSA key-pair authentication and role-based, read-only access, enabling secure retrieval of cloud-hosted analytics. • Deployed the application through GitLab and Render, delivering an accessible, interactive portfolio project with publication filters, visualizations, and downloadable analytical results.

Credit card fraud detection with Random Forest, KNN, and XGBoost: preprocessing pipelines, SMOTE for class imbalance, and a Flask API for real-time alerts. Reached 85% accuracy and flagged 25% more fraud than a baseline model in testing on 1M+ historical transactions.

Self-hosted forecasting + prediction service. Five zero-shot time-series foundation models (Chronos-2, TimesFM 2.5, Moirai-2, Toto-1, Sundial) across six forecast types, plus nine supervised tabular ML backends (LightGBM, XGBoost, sklearn family) with calibrated / stacking / diversified meta-learners. Unified REST API + MCP server.

Materials on various sections in Computer Science (CS). 🎓

Reproducible Python experiments turning treatment-effect estimates into targeting policies, with cross-fitted policy evaluation, uncertainty analysis, and policy trees on Hillstrom's randomised email experiment.

Analysis of Kilter Board data, along with predictive models for V-grades based on holds and angle.

Analysis of Tension Board 2 data, along with predictive models for V-grades based on holds and angle.

Practical tasks on Deep Learning (DL) and Neural Networks (NN). 🤖

A production-grade machine learning system for classifying celestial objects — stars, galaxies, and quasars — from 500,000 photometric observations sourced from the Sloan Digital Sky Survey (SDSS DR18). The pipeline covers LOF-based outlier detection, SMOTEENN class balancing, and SelectKBest feature selection, with six classifier configurations benchmarked against each other. Random Forest achieved the highest accuracy at ~99.51%, while LightGBM was selected for deployment due to its faster inference, smaller footprint, and clean ONNX export path. The system is fully containerized with Docker, backed by a CI/CD pipeline, and served live via a Gradio interface on Hugging Face Spaces.

A data mining project analyzing hate crime patterns in the United States from 2017 to 2025, using clustering, predictive modeling, and association rule mining.

Fundamental theory and practice in Data Science (DS). 🧮

A set of data machine learning/deep learning projects exploring various datasets — a place to test ideas, models, and modern stacks.

AI-Powered Network Packet Analyzer with ML Anomaly Detection - Scapy/scikit-learn, detects port scans, DNS tunneling, DDoS, C2 beaconing, data exfiltration. For authorized security monitoring only.

https://ayinedjimi-consultants.fr

Intelligent Log Parsing and Anomaly Detection with Machine Learning

https://ayinedjimi-consultants.fr