Skills in Statistics, Data Science and Machine Learning

Statistics

• Knowledge of Linear Models and Generalised Linear Models (including logistic regression), both in theory and in applications
• Classical Statistical inference (maximum likelihood estimation, method of moments, minimal variance unbiased estimators) and testing (including goodness of fit)
• Nonparametric statistics
• Bootstrap methods, hidden Markov models
• Knowledge of Bayesian Analysis techniques for inference and testing: Markov Chain Monte Carlo, Approximate Bayesian Computation, Reversible Jump MCMC
• Good knowledge of R for statistical modelling and plotting

Data Analysis

• Experience with large datasets, for classification and regression
• Descriptive statistics, plotting (with dimensionality reduction)
• Data cleaning and formatting
• Experience with unstructured data coming directly from embedded sensors to a microcontroller
• Experience with large graph and network data
• Experience with live data from APIs
• Data analysis with Pandas, xarray (Python) and the tidyverse (R)
• Basic knowledge of SQL

Graph and Network Analysis

• Research project on community detection and graph clustering (theory and implementation)
• Research project on Topological Data Analysis for time-dependent networks
• Random graph models
• Estimation in networks (Stein’s method for Normal and Poisson estimation)
• Network Analysis with NetworkX, graph-tool (Python) and igraph (R and Python)

Time Series Analysis

• experience in analysing inertial sensors data (accelerometer, gyroscope, magnetometer), both in real-time and in post-processing
• use of statistical method for step detection, gait detection, and trajectory reconstruction
• Kalman filtering, Fourier and wavelet analysis
• Machine Learning methods applied to time series (decision trees, SVMs and Recurrent Neural Networks in particular)
• Experience with signal processing functions in Numpy and Scipy (Python)

Machine Learning

• Experience in Dimensionality Reduction (PCA, MDS, Kernel PCA, Isomap, spectral clustering)
• Experience with the most common methods and techniques
• Random forests, SVMs, Neural Networks (including CNNs and RNNs), both theoretical knowledge and practical experience
• Bagging and boosting estimators
• Cross-validation
• Kernel methods, reproducing kernel Hilbert spaces, collaborative filtering, variational Bayes, Gaussian processes
• Machine Learning libraries: Scikit-Learn, PyTorch, TensorFlow, Keras

Simulation

• Inversion, Transformation, Rejection, and Importance sampling
• Gibbs sampling
• Metropolis-Hastings
• Reversible jump MCMC
• Hidden Markov Models and Sequential Monte Carlo Methods