Thanks to visit codestin.com
Credit goes to github.com

Skip to content
View HelloShibani's full-sized avatar
1 follower · 1 following
  • India
  • 02:32 (UTC -12:00)

Achievements

Achievement: Pull SharkAchievement: Quickdraw

Achievements

Achievement: Pull SharkAchievement: Quickdraw

Block or report HelloShibani

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
HelloShibani/README.md

👋 Hey! Nice to see you.

I'm [Shibani Roychoudhury] 😄

👩‍💻 Data Scientist specializing in NLP, Generative AI, and decision-support systems. 🧠 Passionate about building explainable, modular AI pipelines using LangChain, vector databases, and LLMs. 🚀 Former software engineer (15+ yrs) turned AI system designer—focusing on real-world ML applications in insurance, HR, and e-commerce. 📦 Projects include multi-agent RAG assistants, recommender systems with fallback logic, and Dockerized AI pipelines. 🔍 Always exploring the bridge between research and usable AI.

Currently looking for a internship / job 🔎 Email me

🔧 Tools: Python, SQL, LangChain, Hugging Face, ChromaDB, FastAPI
🧠 Focus: NLP, Generative AI, Recommender Systems, Explainable ML
🚀 What I build: Modular AI pipelines, document-grounded assistants, Dockerized ML systems

⚙️ Languages & Tools I Work With

📫 How to reach me:

Pinned Loading

  1. multi-strategy-recommendation-pipeline multi-strategy-recommendation-pipeline Public

    A modular, explainable recommendation pipeline leveraging multiple strategies—collaborative filtering, embeddings, and fallback logic—for robust, personalized product recommendations in real-world …

    Jupyter Notebook 2

  2. Sentiment-Based-Product-Recommendation-Analysis-Revision Sentiment-Based-Product-Recommendation-Analysis-Revision Public

    Revised sentiment-based product recommendation analysis with improved features & model tuning.

    Jupyter Notebook 1

  3. HelpMate_AI HelpMate_AI Public

    Retrieval-Augmented Question Answering system for complex insurance documents using Ollama, LangChain, and ChromaDB. Designed for scalable, intuitive document navigation and decision support.

    Jupyter Notebook

  4. Sentiment-Based-Product-Recommendation-Analysis Sentiment-Based-Product-Recommendation-Analysis Public

    Sentiment-based recommendation system leveraging NLP for personalized product suggestions.

    Jupyter Notebook

  5. Lead_Scoring_Case_Study Lead_Scoring_Case_Study Public

    Lead Scoring Case Study: Analyzing and prioritizing leads using data-driven techniques to enhance sales efficiency

    Jupyter Notebook