Matthew Bain

---

Data scientist, machine learning expert, lover of statistics, and part-time musician. I build interpretable, robust, responsible machine learning applications.

I design end-to-end data management, data analytic, and machine learning software, allowing you to harness the power of AI in your own business workflows with fine-grained control, transparency, and scalability. I use Python and R for scripting, scikit-learn and TensorFlow for machine learning, and SQL, Spark, and Google Cloud Platform to do it all at scale.

Info ⓘ

I design dashboards, data apps, and AI pipelines that make your data work for you and make data insights available to all. My preferred platforms are Tableau, Streamlit, Hugging Face, and Google Cloud Platform.

Info ⓘ

Software ⓘ

autocv

R Package

I built an R package automating repetitive elements of the job application process, including managing work history data, building and rendering documents, and performing text analysis to extract and evaluate keywords.

bainmatt.github.io/autocv

datopy

Python Package

I implemented and maintain a Python package for working with unstructured data, providing a simple interface for web scraping, data modeling, and building ETL pipelines.

Tools used: Pandas, PyTest, Pydantic, GitHub Actions

datopy.readthedocs.io/latest

mlvizz

Python Package

I build Python interfaces facilitating efficient, intuitive model selection, hyperparameter tuning, model inspection, and ML pipeline development through modular, object-oriented designs with built-in data validation.

Tools used: Scikit-learn, TensorFlow, ArviZ, PyMC, SciPy

statvizz

Python Package

I build Python extensions unifying Pandas data summarization with Seaborn statistical plotting functionality for a unified, intuitive, fully transparent statistical plotting interface.

Tools used: Pandas, Seaborn, SciPy, Matplotlib

mathvizz

Python Package

I build Python interfaces for exploring the geometry of machine learning mathematics, including linear maps, functions and derivatives, statistical distributions, series approximations, motion along parametric curves and within vector fields.

Tools used: SymPy, SciPy, Seaborn, Matplotlib

Applications ⓘ

Superstore Dashboard

Tableau Dashboard

I designed a comprehensive, interactive business dashboard displaying sales for a superstore in a convenient, unified view, including key KPIs and transactions as a function of both space and time.

Tools used: SQL, Excel

public.tableau.com/app

Geospatial Data Explorer

Streamlit App

I implemented a data application with a dashboard interface and interactive plots displaying geospatial data such as KPIs in space and time, both at the state and county level.

Tools used: Streamlit, Pandas, Plotly, Altair, GeoPandas

zipexplorer.streamlit.app