Home About Career Snapshot Overview Tech Stack & Core Competencies Request Michele's CV Go/No-Go Projects Study Focus Articles Written Team Misfits Contact
CORE COMPETENCIES

Tech stack, methods, and analytical strengths behind Michele’s work

This page pulls together the detailed tools, methods, and competency areas that sit underneath Michele’s Curriculum Vitae, with particular emphasis on predictive maintenance, anomaly detection, time-series analysis, and engineering-grounded machine learning delivery.

Back to Career Snapshot Open Mission Control
// CAPABILITY TILES

Tech Stack & Core Competencies

9 CAPABILITIES

Machine Learning

Classical modelling, classification, and dimensionality reduction.

Predictive modelling foundations spanning ensemble methods, linear models, support vector machines, and unsupervised structure discovery.

XGBoost Random Forest SVM Decision Trees Logistic Regression Linear Regression PCA LDA Clustering
10 CAPABILITIES

Deep Learning

Neural architectures for vision, sequence learning, and transfer.

Applied neural modelling across convolutional, recurrent, temporal forecasting, metric-learning, and transfer-learning workflows.

CNN RNN / LSTM Temporal Fusion Transformers DeepAR N-HiTS Siamese Networks MobileNet ResNet Few-Shot Learning Transfer Learning
6 CAPABILITIES

Time Series & Prognostics

Degradation tracking, forecasting, and asset-health estimation.

Focused on aerospace-style predictive maintenance, operational forecasting, anomaly detection, and Remaining Useful Life estimation.

Time Series Forecasting Remaining Useful Life Anomaly Detection Physics-Aware Feature Engineering Degradation Modelling Predictive Maintenance
10 TOOLS

Tools & Frameworks

Core implementation stack for experimentation and production analysis.

Hands-on workflow across modelling libraries, data tooling, notebook environments, explainability utilities, and numerical computing.

Python PyTorch TensorFlow Scikit-learn PySpark Pandas NumPy Jupyter SHAP Matplotlib
6 METHODS

Statistics & Mathematics

Quantitative methods supporting rigorous model design and evaluation.

Bayesian reasoning, validation strategy, inferential testing, density modelling, and survival-analysis tools used across the research stack.

Bayesian Methods Bayesian Optimisation Cross-Validation Hypothesis Testing Density Estimation Survival Analysis
4 DISCIPLINES

Engineering

Applied engineering context bridging physical systems and analysis.

Domain grounding in structural behaviour, loading response, fatigue progression, and engineering problem-solving beyond pure software.

Civil Engineering Structural Analysis Fatigue & Damage Modelling Impact Loading Analysis
INTERACTIVE MAP

Competencies Mapped to Experience

This dedicated holographic map links Michele's core competencies and technical stack directly to the experiences where they were developed, tested, or operationalised. It is designed as a cleaner, more spatial way to inspect how methods, tools, and engineering strengths connect across FusionCore v0, FusionCore v1, PiNet, the MSc thesis, the Moon Landing platform, and earlier engineering work.

Open the map to rotate the network, hover nodes for quick previews, and click a node to surface a holographic readout showing what that competency or tool is tied to in practice.

Open Competency Experience Map Back to Career Snapshot
Moon Shot Moon Shot