Skip to content
View Varun-Chandra-Shekar's full-sized avatar
🎯
Focusing
🎯
Focusing
  • Melbourne

Block or report Varun-Chandra-Shekar

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

Varun-Chandra-Shekar

Hi 👋, I'm Varun Chandra Shekar

Master of Data Science graduate from RMIT University
Based in Melbourne, Australia
Data Scientist / Data Analyst focused on ML, Analytics, SQL, Power BI, and Cloud

What I Do

  • Build end-to-end data science and analytics solutions
  • Work with SQL, Python, Power BI, machine learning, and cloud tools
  • Develop business-focused dashboards and predictive models
  • Turn messy data into clear decisions and measurable impact

Key Achievements

  • Improved NLP model accuracy from 56% to 86% in a production-focused project
  • Reduced inference latency by 80% through optimization and deployment improvements
  • Identified $35K+ annual revenue leakage through analytics and dashboarding
  • Built end-to-end projects across ML, Power BI, PostgreSQL, Flask, AWS, and Docker

Tech Toolbox

Data & Analytics

  • Python, SQL, PostgreSQL, Pandas, NumPy, Scikit-learn
  • Power BI, Tableau, Excel
  • Data cleaning, feature engineering, EDA, model evaluation

Machine Learning

  • Classification, Regression, NLP, Recommender Systems
  • TensorFlow, Keras, ONNX, Sentence Transformers

Cloud & Deployment

  • AWS, Docker, Flask, DynamoDB, Lambda, S3
  • API integration, model packaging, deployment workflows

Other Tools

  • Git, GitHub, Jupyter, VS Code, Linux

Featured Projects

Jobsite (Python · Scikit-learn · Flask · NLP · Classical ML)

  • Built an NLP pipeline to preprocess and transform unstructured job advertisement text using Bag- of-Words and TF-IDF feature representations to search and classify jobs based on industry domain.
  • Compared multiple vectorization approaches (BOG, weighted TF-IDF, and text feature combinations) using Logistic Regression, achieving 87.9% multi-class classification accuracy.
  • Built and deployed a Flask-based web application enabling job search and automated job classification for employers and job seekers, storing categorized postings through an integrated inference pipeline.

Smart Grid Household Occupancy Prediction (Python (pandas, NumPy, scikit-learn) · PostgreSQL · Matplotlib/Seaborn · Jupyter Notebook)

  • Built a machine learning model to predict daytime household occupancy using Australian energy consumption data.
  • Compared multiple algorithms (Logistic Regression, Random Forest, Neural Networks) using cross-validation and ROC-AUC metrics.
  • Achieved 88% recall, to minimize the cost of false negatives in energy distribution.

Banking Analytics Dashboard (Data Visualisation · Story Telling · ggplot · R Programming )

  • Built a banking analytics dashboard using R (ggplot, dplyr) to visually communicate Australia’s transition from cash to digital payments for non-technical stakeholders.
  • Designed time-series, segmented, and comparative visualisations to highlight generational payment behavior, category-level usage patterns, and the impact of COVID-19.
  • Delivered a data storytelling narrative and published the dashboard on RPubs, linking digital payment adoption to ATM and bank branch closures to support strategic and operational insight

Certifications

Let’s Connect

Popular repositories Loading

  1. Netflix-Data-Analysis Netflix-Data-Analysis Public

    This repository aims to provide analysis of Netflix TV Shows and Movies, how it compares with other Streaming Partners

    Jupyter Notebook

  2. ElectronicStoreDataAnalysis ElectronicStoreDataAnalysis Public

    Jupyter Notebook

  3. Zomato-Data-Analysis Zomato-Data-Analysis Public

  4. Spark-Programming-In-Python Spark-Programming-In-Python Public

    Forked from LearningJournal/Spark-Programming-In-Python

    Apache Spark 3 - Spark Programming in Python for Beginners

    Python

  5. Steps-to-configure-Pyspark Steps-to-configure-Pyspark Public

  6. PySpark PySpark Public

    Forked from hyunjoonbok/PySpark

    PySpark functions and utilities with examples. Assists ETL process of data modeling

    Jupyter Notebook