Skip to content
View juliettebm's full-sized avatar

Block or report juliettebm

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 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

Pinned Loading

  1. pharma-commercial-genai pharma-commercial-genai Public

    End-to-end pharma commercial analytics on CMS Open Payments: HCP retention model (SHAP), engagement segmentation, a GenAI text-to-SQL assistant, a Streamlit dashboard, and a responsible-AI model card.

    Jupyter Notebook

  2. steam-reviews-nlp steam-reviews-nlp Public

    End-to-end NLP on 434,891 Steam reviews: EDA, preprocessing, DistilBERT baseline & fine-tuning, BERTopic topic modelling, and LLM aspect-based sentiment (Gemini).

    Jupyter Notebook

  3. insurance-contract-rag insurance-contract-rag Public

    RAG over insurance contract documents: grounded Q&A with an anti-hallucination guardrail and evaluation (retrieval hit-rate + LLM-as-a-judge). LangChain, Sentence-Transformers, FAISS, local LLM.

    Jupyter Notebook

  4. customer-analytics-retail customer-analytics-retail Public

    End-to-end customer analytics on 1M retail transactions: SQL relational modelling, RFM segmentation, Kaplan-Meier and Cox survival analysis, leakage-safe repurchase prediction, and a Power BI dashb…

    Jupyter Notebook

  5. METABRIC-Breast-Cancer-Survival-Analysis-Machine-Learning METABRIC-Breast-Cancer-Survival-Analysis-Machine-Learning Public

    An end-to-end data science and biostatistics pipeline on the METABRIC dataset. Features exploratory data analysis, stratified Kaplan-Meier curves, multivariate Cox models, and 5-year survival predi…

    Jupyter Notebook 1

  6. hospital-readmission-diabetes hospital-readmission-diabetes Public

    Random Forest model predicting 30-day hospital readmission risk in diabetic patients, built on 3 clinically interpretable composite dimensions (UCI Diabetes 130-US Hospitals), with a Streamlit clin…

    Jupyter Notebook