Skip to content
View tssarathi's full-sized avatar
💭
Asking “why did they leave?” so churn hurts less.
💭
Asking “why did they leave?” so churn hurts less.
0 followers · 2 following

Sponsoring

@usememos

Achievements

Achievement: Public SponsorAchievement: Pair ExtraordinaireAchievement: YOLOAchievement: Pull SharkAchievement: Quickdraw

Achievements

Achievement: Public SponsorAchievement: Pair ExtraordinaireAchievement: YOLOAchievement: Pull SharkAchievement: Quickdraw

Block or report tssarathi

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
tssarathi/README.md

Hi there 👋

Welcome to my GitHub. I’m Sarathi, a data scientist who questions numbers and turns them into stories. My work spans end-to-end machine learning pipelines, spatial analytics, interactive dashboards, and AI text detection. From predicting hospital readmissions to mapping flood risk and visualising bird sightings around Melbourne, I enjoy applying data science to real-world problems.

These projects reflect my curiosity across different domains and technologies. I also build things just for fun, like an F1 analytics dashboard and a bird-watching app inspired by a Brooklyn Nine-Nine quote—small reminders that data can be both practical and playful.

If you’re curious, feel free to ask me about data science projects, customer analytics, churn modelling, spatial analysis, or building end-to-end pipelines and dashboards. You can reach me on LinkedIn, and I’m always happy to chat or collaborate.

Fun fact

Outside of data, I’m currently training for a Half Ironman, and I’m getting an itch to deploy an agent to monitor my swimming, cycling, and running.

Pinned Loading

  1. airline-customer-analytics airline-customer-analytics Public

    End-to-end customer analytics and churn modelling pipeline built on airline loyalty data. Includes data engineering, feature generation, and machine learning workflows on cloud infrastructure.

    Jupyter Notebook

  2. NaarmWings NaarmWings Public

    Interactive R Shiny + Tableau app for geospatial and temporal analysis of urban bird sightings in Melbourne.

    R

  3. ischemic-stroke-readmission ischemic-stroke-readmission Public

    This project applies machine learning techniques to predict 365-day hospital readmission among ischemic stroke patients using data from the MIMIC-IV database.

    Jupyter Notebook

  4. victoria-school-flood-risk victoria-school-flood-risk Public

    Spatial analysis of flood exposure and socio-economic vulnerability of government schools in North Central Victoria using GIS, spatial statistics, and GWR.

    Jupyter Notebook

  5. ai-text-detection-mtl ai-text-detection-mtl Public

    PyTorch-based multi-task model for detecting AI-generated text across imbalanced domains using TF-IDF features and sentence embeddings.

    Jupyter Notebook

  6. Harish-2502/CCC-Team-72 Harish-2502/CCC-Team-72 Public

    This is maintained by the members of Team 72 for Assignment 2 of the Cluster and Cloud Computing course

    Jupyter Notebook 1