Sudhanshu Mukherjee

Sudhanshu Mukherjee সুধাংশু মুখার্জি

Data Scientist, Boston, MA

Contact: {X @ Y}, X=sud, Y=hustledata.io

Ars longa, vita brevis

Sudhanshu Mukherjee (সুধংশু মুখার্জি) is a Data Scientist pursuing his Master's in Data Science at the University of Massachusetts. He enjoys developing machine learning algorithms to solve complex problems through a multidisciplinary approach to Automated Machine Learning, Deep Learning, and Generative AI.

Currently, as part of his master's research, He is building his most ambitious project: Rapid Insights Data Engine(R.I.D.E), a No-Code Platform designed to simplify and automate the entire data science workflow. Through RIDE, he aims to bridge the gap between technical and non-technical users by integrating my expertise in Machine Learning, Data Science workflows, No-Code Development, and Automated Model Selection.

He pursued his summer internship as a Data Engineering Intern at Camping World | Good Sam in Chicago. His work revolved around increasing data quality using MySQL and validation strategies. He was also involved in migrating databases from legacy servers to Snowflake servers.

Academically, He has served as a Teaching Assistant for a High-Performance Scientific Computing class(DSC 520) in the Fall of 2024 and as a Teaching Assistant for Introduction to C Programming (CIS 190) in Fall of 2023. I have also worked as Data Science Education Lead in Digital Scholarship Hub at my university, where I taught multiple technical topics such Data Visualization using Plotly, Using Langchain to interact with Large Language Model(LLM), ArcGIS for Geospatial Analysis, Introduction to SQL, and Basics of Machine Learning from December 2023 to August 2024.

Projects

RIDE Project

Rapid Insights Data Engine (R.I.D.E)

Sudhanshu Mukherjee

RIDE is a powerful no-code platform that enables users to upload datasets, preprocess data, visualize it, perform feature selection, explore patterns, and apply statistical tests, all in an intuitive interface of your browser. What makes RIDE stand out is its AutoML capabilities, allowing users to test multiple machine learning models across Regression, Classification, and Clustering. The platform automatically evaluates model performance, helping users select the best-performing algorithm with ease.Beta version out soon. Please email to test out the demo.

RIDE Project

Prepup-Linux: Open-Source Python Package

Sudhanshu Mukherjee

An open-source package built on the Polars Library, for data inspection, exploration, visualization, and preprocessing tasks directly on the terminal. Supports multiple file formats (.csv, .excel, .parquet).

Blog Posts

Hustle Data Machine Learning

Multiclass Classification using Neural Networks

Explore the intricacies of building a neural network model capable of handling multiple classes.

Hustle Data Data Science

Deep Learning is all about Gradient Descent Algorithm

Dive into how the gradient descent algorithm powers the learning process in deep neural networks.

Hustle Data Kaggle

From Underdog to Top Contender: How I Surpassed 76% of Teams on Kaggle

Discover the strategies and techniques that helped me climb to the top ranks in a Kaggle competition.

Hustle Data Python

Python Development Best Practices: Virtual Environments and requirements.txt

Learn about the best practices in Python development focusing on virtual environments and managing dependencies.