Skip to content
View ganji-rajesh's full-sized avatar

Highlights

  • Pro

Block or report ganji-rajesh

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
ganji-rajesh/README.md

Hi, I'm Ganji Rajesh πŸ‘‹

πŸ“ Hyderabad, India Β |Β  πŸ’» Data Scientist & Data Analyst Β |Β  LinkedIn

A maths nerd turned Data Analyst β€” I live and breathe data. Turning raw numbers into meaningful insights is what gets me out of bed every morning.

I'm currently deep-diving into AI at the intersection of Biology/Agriculture 🧬, exploring how machine learning can unlock new frontiers in the life sciences. I'm actively open to opportunities at the AI Γ— Biology space.

Beyond work, I love building projects and tools that scratch my own itch β€” if it makes my life even a little better, it's worth building. When I step away from the screen, you'll find me with a camera in hand, capturing emotions and untold stories in still frames πŸ“·.


πŸ› οΈ Skills

🐍 Python Pandas NumPy Matplotlib Seaborn Scikit-Learn SpaCy TensorFlow Pytorch

πŸ—„οΈ SQL SQL Commands Joins CTE Stored Procedures Window functions Views

πŸ“Š Analytics Excel Data Preprocessing Data Analysis Statistical Modelling Predictive Modeling Machine Learning Deep Learning

βš™οΈ Data Engineering Microsoft Fabric Databricks Data Engineering & Transformation Data Warehousing & Querying Data Ingestion PySpark

πŸ“ˆ Visualization Tools Power BI Β |Β Tableau

☁️ Cloud Computing AWS GCP


πŸ—‚οΈ Projects

πŸ“Š Equity Research/Fundamental analysis πŸ”

Github

A growing collection of fundamental analysis of listed Indian companies, powered by LLMs.

  • πŸ“ Covers economic, industry, and company-level analysis
  • πŸ“„ Sources: Annual reports (statutory sections), MoneyControl financials
  • πŸ€– Tools: Gemini models + custom MD&A summarizer
  • πŸ“… Updated monthly

Skills used: fundamental analysis llms pdf parsing llm api keys

🏦 Credit Risk Modelling

GitHub Β |Β  Streamlit

A machine learning project to predict credit risk for loan applicants using historical financial data.

Skills used: Python Pandas Scikit-Learn Machine Learning


⚑ TGNPDCL Domestic Consumption Prediction

GitHub Β |Β  Streamlit

Predicts domestic electricity consumption patterns for TGNPDCL using time-series forecasting and ML models.

Skills used: Python Pandas Machine Learning Time Series


πŸ“„ RHP Tool β€” IPO Document Analyzer

GitHub Β |Β  Streamlit

Extracts and summarizes various sections of RHP/DRHP documents (IPO filings) using Google Gemini AI.

Skills used: Python Google Gemini AI LLM NLP PDF Parsing


πŸ“Š Management Discussion Summary

GitHub Β |Β  Streamlit

Extracts and summarizes Management Discussion & Analysis sections from annual reports using Google Gemini AI.

Skills used: Python Google Gemini AI LLM NLP PDF parsing


πŸ₯ HCA Revenue Guardian

GitHub Β |Β  Streamlit

A Python-based revenue cycle intelligence tool for healthcare organizations to detect anomalies and protect revenue.

Skills used: Python Machine Learning Data Analysis Streamlit


πŸ”¬ Chemical Space Explorer

GitHub Β |Β  Streamlit

Explores chemical compound spaces using cheminformatics techniques for drug discovery applications.

Skills used: Python Cheminformatics RDKit Data Visualization


🎬 YouTube Summary

GitHub

Generates summaries and transcripts from YouTube videos using AI.

Skills used: Python LLM NLP YouTube API


🏦 Customer Churn Prediction in Bank using ANN

GitHub

Predicts whether a bank customer is likely to churn using an Artificial Neural Network trained on customer attributes such as geography, gender, age, balance, tenure, and salary. Skills used: Python Pandas NumPy TensorFlow Keras ANN Data Preprocessing Feature Engineering


Handwritten Digit Recognition using PCA and Classification Models

GitHub

Built a machine learning pipeline to recognize handwritten digits by combining Principal Component Analysis (PCA) for dimensionality reduction with classification models for prediction. The project focuses on reducing high-dimensional image features, improving training efficiency, and comparing model performance for accurate digit classification.

Skills used: Python Pandas NumPy Matplotlib Seaborn Scikit-Learn PCA Classification


🏦 Loan Default Prediction

GitHub

Predicts loan approval outcomes using a 614-record dataset with applicant demographics and financial features. Includes EDA, missing value treatment, and comparison of multiple classification models β€” Logistic Regression, KNN, Decision Tree, and Random Forest β€” achieving ~78% accuracy.

Skills used: Python Pandas NumPy Matplotlib Seaborn Scikit-Learn Classification Models EDA


Visualization projects

GitHub

Visualization projects

Skills used: Power BI


πŸ€– Movie Booking Chatbot

GitHub

A rule-based chatbot built to handle movie booking conversations.

Skills used: Python NLP Chatbot Design


Pinned Loading

  1. portfolio portfolio Public

    Here is my portfolio of projects.

    Jupyter Notebook