i build Systems & Tools for Analysis, Prediction, Visualization, & Simulation.

i also design, code, and implement/deploy complete Machine Learning-based applications intended to run daemonized inside production web applications (e.g., anti-fraud filter, recommendation engine, monitoring/anomaly detectors); preferably these applications are built as external services and accessed from a main app via RESTful API.

Techniques:

• Machine Learning: in particular, recursive descent parser (CART/C4.5), Multi-layer Perceptron, SVM/SVR, Kernel Machines, kNN/kdtree, Graphical Models (eg, Markov Random Field)

• Dimension Reduction Techniques: spectral decomposition (PCA & kPCA, kLDA), Kohonen Map (self-organizing map)

• Social Network Analysis & Visualization: using graph theoretic techniques for e.g., community detection, id of members essential for network health/growth; identify nascent sub-communities; (particular fluency GraphViz, the premiere tool for graph layout/visualization, NetworkX, the primary network analysis library for python, and d3).

• Analysis & Modeling of Time-Dependent Data

• Optimization: Combinatorial Optimization and Constraint-Satisfaction Programming

• Numerical Methods: e.g., matrix decomposition, Monte Carlo techniques, Gaussian quadrature, finite difference methods

• Data Modeling for "Non-Relational" systems (in particularly Redis and MongoDB) and for relational (ROLAP), multi-dimensional (MOLAP), and hybrid (HOLAP) Data Warehouse systems using conventional relational/SQL servers.

toolchain:

• python
• SciPy + NumPy + Matplotlib
• javascript
• R
• redis
• HDF5 (& pytables, hfpy)
• graphviz
• node.js
• flask/werkzeug (python web framework)
• storm (distributed processing)
• d3.js (svg-based primitives for rendering plots in the browser)
• git (& gitHub)

No recruiters