Skip to content
View Bhanuprakashachini's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report Bhanuprakashachini

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.

Content in all repositories owned by your account will be closed.
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
Bhanuprakashachini/README.md

📍 Hyderabad, India · Open to Remote


🧭 About

I'm a B.Tech Data Science graduate who genuinely enjoys the messy part of data — cleaning it, pipelining it, and eventually getting a model or dashboard out of it that someone actually uses.

Lately I've been deep in lakehouse pipelines (Spark, Delta Lake, Airflow) and LLM/RAG systems — plus an earlier phase building an LSTM/GRU trading model for NIFTY 50 that I later co-presented as a paper at an international conference in South Korea.

Currently exploring: Data Analyst · Data Engineer · AI/ML Engineer roles — always happy to chat about data, AI, or interesting problems.


🛠️ Stack



Spark Snowflake Airflow dbt LangChain HuggingFace PowerBI Tableau FastAPI Django


🏦 Bank Transactions Lakehouse

Spark · Delta Lake · Airflow · LLaMA 3

Medallion (Bronze-Silver-Gold) lakehouse on AWS S3/MinIO, 5-task Airflow orchestration, and an AI-driven Streamlit dashboard for natural-language BI querying.

🛍️ Metadata Lakehouse (E-Commerce)

Kafka · Spark · dbt · Hugging Face

Real-time event ingestion pipeline with an embedding-based vector search layer for LLM-driven, prompt-based analytics across product and sales data.

🚚 Logistics Data Lakehouse

PySpark · FastAPI · Snowflake

End-to-end pipeline processing 50K–90K+ daily shipment records, with a FastAPI-served delivery-success prediction model feeding Power BI.

🚦 LLM-Orchestrated Traffic Analysis

YOLOv8-v12 · Django Channels · Multi-LLM

Full-stack platform integrating 5 YOLO variants with multi-LLM orchestration (OpenAI, Anthropic, Groq) for live violation detection via WebSocket streaming.

📄 RAG Application (Document Intelligence)

LangChain · FAISS · Streamlit

Multi-format RAG system (PDF/CSV/Excel/Word/JSON) with hybrid semantic + keyword search, 1–3s query response times.

📈 AI Algorithmic Trading System

LSTM · GRU · Telegram Bot

NIFTY-50 trading system, 85–88% signal accuracy, sub-1-second signal generation, and an AI chatbot dashboard with live candlestick charts.

📊 More projects — analytics dashboards
Project Highlights Stack
Online Retail Customer Analytics 797K+ records cleaned; top 10% of customers drove ~63% of £16.36M revenue Python · Power BI · DAX
Quick Commerce Sales Dashboard 3-page dashboard on $347M+ revenue across 500K+ orders Python · NumPy · Power BI
Banking Analytics Dashboard Income segmentation + multi-page loan/deposit dashboards MySQL · SQL · Power BI

🎓 Education & 🏆 Highlights

B.Tech, CSE (Data Science) Sreyas Institute of Engineering & Technology · 2026 · CGPA 7.4–7.5

Diploma, ECE TKR College of Engineering & Technology · 2023

🎤 Co-authored & presented "AI-Powered Algo Trading System" at PCCDA 2026, Sejong University, South Korea

🏁 HackAttack 2K25 — 24-hour national hackathon

Certifications: Cisco (Data Analytics) · IBM (Python for Data Science) · Scaler (ML, DBMS, Java)


📊 GitHub Stats

Repos

Pinned Loading

  1. Quick-E_Commerce-Sales-Analytics Quick-E_Commerce-Sales-Analytics Public

    End-to-end Quick Commerce analytics project using Python and Power BI, featuring data cleaning, EDA, KPI development, and interactive dashboards for sales, delivery, and customer insights.

    Jupyter Notebook

  2. AI-Powered-NIFTY-50-Stock-Prediction-and-Automated-Trading-System AI-Powered-NIFTY-50-Stock-Prediction-and-Automated-Trading-System Public

    Built an end-to-end AI trading system for NIFTY-50 stocks using LSTM/GRU models, automating market-data processing, signal generation, backtesting, and Telegram alerts while delivering 85–88% signa…

    TypeScript

  3. DocIntel- DocIntel- Public

    DocIntel is an intelligent Retrieval-Augmented Generation platform that unifies PDF, DOCX, CSV, Excel, and JSON documents into one searchable knowledge base. Using hybrid semantic search, it delive…

    Python

  4. E-COMMERCE-ANALYTICS E-COMMERCE-ANALYTICS Public

    Built a real-time Kafka+Spark pipeline with dbt Medallion Architecture, Airflow, Power BI, and Hugging Face/vector search to enable LLM-driven analytics across sales, product, and customer data.

    Jupyter Notebook

  5. LLM-Orchestrated-Multi-Model-Traffic-Analysis-System LLM-Orchestrated-Multi-Model-Traffic-Analysis-System Public

    Developed a real-time intelligent traffic monitoring platform integrating YOLOv8, YOLOv11, and YOLOv12 with centroid tracking and temporal smoothing for robust vehicle detection and violation analy…

    Python

  6. Banking-Data-Lakehouse Banking-Data-Lakehouse Public

    Banking data lakehouse (Spark, Delta Lake, Airflow) with an AI-powered Streamlit dashboard for natural-language BI queries.

    Python