Skip to content
View Olivenatural's full-sized avatar

Block or report Olivenatural

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
Olivenatural/README.md

Hi, I'm Tamauri 👋

Data Analyst (Wellness) / Junior Data Scientist

I turn real-world wellness experience (10+ yrs massage therapy) into data insights that retain customers and lift revenue. I build churn models, analyze booking patterns, and mine reviews for themes leaders can act on.

🔭 Featured Projects

  • Churn Prediction — Beta Bank · AUC-ROC ≈ 0.97 · threshold tuning · PR/ROC curves · action plan for outreach
  • NLP on Wellness Reviews · cleaning → n-grams/embeddings → classifier · top negative drivers (shipping, efficacy, price)
  • Wellness Bookings Analysis · cohort & time-series charts in Matplotlib · weekday utilization and service mix

Links to repositories are in my pinned repos below.

🧰 Toolbox

Python · pandas · Matplotlib · scikit-learn · SQL · Jupyter · Git/GitHub · Churn · NLP · Co-hort Analysis

📚 Currently learning

  • Practical ML for retention (thresholds, cost-aware evaluation)
  • Text embeddings for better review understanding

💬 How I work

  • Clear problem → clean data → simple visuals → measurable outcome.
  • Notebook flow: Explain → Code → Explain results (so anyone can follow).

📫 Connect

Pinned Loading

  1. churn-prediction-betabank churn-prediction-betabank Public

    Predict churn; best model AUC-ROC = 0.97; threshold tuning; PR/ROC; outreach plan.

  2. wellness-bookings-analysis wellness-bookings-analysis Public

    Matplotlib cohorts & utilization: bookings vs re-book rate, service mix, and weekday×hour heatmap. Includes 30-day rebook cohort chart.

    Python

  3. wellness-reviews-nlp wellness-reviews-nlp Public

    Clean → tokenize → TF-IDF n-grams → LR/SVM; classify wellness review themes; macro-F1, confusion matrix, top n-grams.

    Python