About Me

I am a data scientist working for more than 8 years now. I like solving impactful problems because of the challenges they offer and learning opportunities one can discover along the way. I usually follow a three step framework while solving a problem: Feasability, Prototype and Production.

I’ve been working on projects involving mainly text and tabular data using deep learning or general ML algorithms. Some of the use cases I’ve worked on are:

• Ranking: Rank restaurants based on their click probability
• Search Models: Building models to enhance relevancy in search results
• Recommendation Models: Improving user discovery of products on a platform
• Text Duplication: Building a data product using open source technologies which can efficiently identify duplicate text.

Besides, I like to mentor people and ensure that everyone in the team learns something new besides their day to day job. Earlier, I had been actively involved in my sharing my data science knowledge through blogging, here you can find my articles.

Also, I am the author & maintainer of superml R package. It helps people build ML models in R just like using scikit-learn.

To further know about my latest gigs, checkout my linkedin.