Giter Site home page Giter Site logo

Hello there! I am Shubham Kumar Shaw👋

A seasoned Data Scientist with over three years of adept proficiency in handling data, demonstrating a profound understanding of exploratory data analysis and adeptly addressing missing values. Proficient in the application of machine learning techniques and coding in Python, showcasing expertise in Linear Regression, Logistic Regression, Time-series Models, and various Classification Techniques. Possesses a working knowledge of Machine Learning algorithms, including Random Forest, SVM, Boosting, and Bagging techniques, as well as proficiency in Clustering algorithms. Additionally, skilled in Data Visualization utilizing Tableau.

At Gigaforce I am working on intelligent End-to-end automation of the Subrogation Process which is Improving loss ratios in Property and casualty insurance built on decades of claims experience integrated and implemented with state-of-the-art Data science techniques.

As a Data Scientist at Curl Analytics, I have worked on creating a robust submodule capable of accurately identifying NER entities for different document types. Enhanced module performance significantly by optimizing existing code, resulting in ~33% reduction in runtime & ~25% increment in accuracy. Improved the existing pre-processing, data wrangling, and augmentation module. Did several NER-based experiments for finding the best fit for the entity recognition part of the Product. Proposed and implemented several new ideas such as using Argilla which is an open-source data curation platform using LLMs and skweak for defining the labeling functions to automatically label the documents, Using TriggerNER which increased the performance over Traditional NER, etc. I have applied my skills in Python, NumPy, Pandas, ML, and LLM to create and test various models and algorithms for this project.

I have a Bachelor of Technology in Computer Science from Orissa Engineering College, where I learned and applied various analytical techniques, such as Linear Regression, Logistic Regression, Time-series Models, Classification Techniques, etc. I also have multiple certifications from Google and MongoDB in Digital Marketing and Data Basics. I am passionate about exploring new possibilities and learning new technologies in the field of Data Science.

I have also co-founded and directed a company called TECHNOBOOT PVT LTD, where I gained experience in digital marketing, graphic designing, web development, and finance. I am skilled in design, Marketing, Public Speaking, Management, UI/UX and Data Science.

---

Experience 📈

  • ⭐ Working at: Gigaforce INC

  • 🔭 Have played around with: Python Numpy Pandas scikit-learn Pytorch NLP Transformer NER LLM

  • 🔧 Using the following tools: Visual Studio Visual Studio Code Git GitHubJupyterLinuxChatGPT

  • 📜 Read my blogs on GitHub

  • ❓ Ask question on Quora

  • 🎨 See my Graphic Design's Portfolio at Behance

  • 🌱 Currently learning: NLP LLM

  • ⭐ Worked at: Technoboot CRMNext Curl Tech Gigaforce


Feel Free To Contact Me 📱

Linkedin Badge

Twitter Badge

Gmail


Shubham's GitHub Statistics

Shubham Kumar shaw's Projects

hands_on_ml icon hands_on_ml

CREATE YOUR OWN MACHINE LEARNING MODEL ON WEBSITE WITHOUT CODING.

pandas_cheatsheet icon pandas_cheatsheet

This repo contains all the tricks and tips i have learned during my learning of Pandas using Python

pycaret icon pycaret

An open-source, low-code machine learning library in Python

twentyone icon twentyone

Slow progress? Twenty One (21) is the auto ML engine which makes it easy to dish out ML models in an automated way.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.