Skip to content
View 1985shree's full-sized avatar

Block or report 1985shree

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
1985shree/README.md

Welcome to my github page! 👋

I am a scientist-turned-data scientist with a huge interest in finding innovative solutions to everyday problems. I've been using python and SQL to build my data science projects since 2020. A 6-month data science course at Le Wagon helped me to learn and implement industry best practices and skills. Almost a decade of experience as a scientist and more than 3 year's training in coding and machine learning has prepared me on this journey. I love to do team projects and also contribute to 'AI For good' projects, which have positive impact on society and environment. I am looking forward to build my career in sustainable, social and climate-responsible financial projects and risk managements with my ever expanding data science and statistics toolbox.

Things I've done in the past in addition to my regular work in building machine-lerarning models to tackle money-laundering with our client bank:

  • 🔭 worked on NLP and recommendation system (cosine similarity, knn) with vectorizers, transformers and LLMs as well.

  • 🌱 worked in MLOps (MLflow for ML lifecycle management, GCP and AWS for storage, running models and deployment throug APIs etc.)

  • worked in original reserach projects in molecular physics and published results in leading international journals. My science research background spans over 10 years and I have worked on complex (and cool) projects like femtosecond (i.e. 1/1000000000000000000 th of a second) stimulated Raman spectroscopy, laser induced fluorescence of ultra-cooled molecules at 3-4 K etc.

  • Libraries and tools: Pandas, NumPy, SciPy, Scikit-Learn, TensorFlow, Matplotlib, Seaborn, Plotly, Spacy, LLMs, Pinecone.

  • Methodologies: Statistical methods: Bootstrapping, Hypothesis testing; ML methods: Classification, Linear and multivariate regression, deep learning, tee based models, pipelines, Grid/random search CV.

  • 👯 I’m looking to learn more about financial risk management through ML and statistical/mathematical modelling, quant analytics projects.

  • 🤔 I’m looking for help with understanding in-depth the working and performance metrics, infrastructure building and front-end dev.

  • 💬 Ask me about Spectroscopy, Data processing, Data visualization, ML

  • 📫 How to reach me: Linkedin : https://www.linkedin.com/in/shreetamakarmakar/

  • 😄 Pronouns: she/her


🧰 Toolbox


Popular repositories Loading

  1. 8-week-SQL-challenge 8-week-SQL-challenge Public

    This lists the problems and solutions of Danny Ma's 8 week fun SQL challenge!

    2

  2. Data-science-Zoomcamp-projects Data-science-Zoomcamp-projects Public

    Projects from Alexey's classes

    Jupyter Notebook 1

  3. sommer_picnicplanner sommer_picnicplanner Public

    a simple picnic planner api

    Jupyter Notebook 1

  4. olist olist Public

    olist

    Jupyter Notebook 1

  5. starting-repo starting-repo Public

  6. 1985shree 1985shree Public

    Welcome to my profile!

    Jupyter Notebook