Machine Learning and Data Science

I am familiar with classification techniques, random forests, clustering, robust regression, SVM, Bayesian linear regression, logistic regression,

LASSO, Bayesian LASSO, Bayesian adaptive LASSO, neural networks, forecasting techniques (ARIMA, VAR), hierarchical Bayesian models, MCMC and non-linear mixed effects models.

For a sample of my work, please browse through my publications, open source data science projects, data munging tools (private),

various bioinformatics tools and other open source software I authored.

I have been involved in various projects involving predicting patterns of crime in different cities, predicting compounds that are likely to be

of therapeutic value with data mined from the gut microbiome and predicting species that could likely be infected in disease outbreaks.

Please browse through my publications to learn more. I have also been involved in multiple open source data science projects.

Here are some select projects:

1) We did some analysis of crime in different cities using freely available data that got some attention (link) and here is some visualization

2) I also did some analysis and visualization of a global scale collaboration network (link). I gave a talk on that and the associated brief paper is here

Here is a brief writeup on some of these recent projects.

3) Project to perform forecasting and SQL like queries for a road accident forecasting and data exploration project (on bitbucket)

Deployed web application to perform data exploration using SQL-like queries and perform machine learning analysis (deployed on shinyapps)