Skip to content
View Deepak-Manian's full-sized avatar
💭
I may be slow to respond.
💭
I may be slow to respond.
2 followers · 3 following

Block or report Deepak-Manian

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
Deepak-Manian/README.md 
╔══════════════════════════════════════════════════════════════╗
║  SYSTEM_VERSION_4.0  ░  STATUS: ONLINE  ░  SYNC: COMPLETED  ║
╚══════════════════════════════════════════════════════════════╝

Deepak M

DATA_SCIENTIST.EXE

Engineering high-performance ML pipelines and insightful analytical models. I bridge the gap between raw data chaos and architectural precision.

LinkedIn GitHub Email

01. TECHNICAL DNA

LANGUAGE / IDE

Python SQL HTML CSS VS Code Jupyter

ML / DL FRAMEWORK

scikit-learn TensorFlow Keras HuggingFace OpenCV

DATA & VISUALIZATION

Pandas NumPy Matplotlib Power BI Streamlit

DATABASE / CLOUD

PostgreSQL MongoDB MySQL OracleSQL AWS

DOMAIN KNOWLEDGE

NLP Computer Vision Generative AI RAG Anomaly Detection

02. PROJECT PORTFOLIO

PROJECT_001 — Hyperlocal News Anomaly Detection

NLP pipeline to detect anomalous hyperlocal news patterns and potential source misattribution using transformer embeddings.

#BERT #RoBERTa #NLP #Streamlit #UnsupervisedML

PROJECT_002 — Fish Classification CNN

CNN-based image classifier using transfer learning to identify fish species. Deployed as a Streamlit inference app.

#TensorFlow #Keras #TransferLearning #ComputerVision #Streamlit

PROJECT_003 — YouTube Ad Revenue Predictor

Regression models to forecast YouTube ad revenue from engagement and contextual features. Evaluated Linear, Ridge, Lasso, and Gradient Boosting via R² and RMSE.

#Regression #FeatureEngineering #GradientBoosting #Streamlit

[IN_PROGRESS] — Next Build

Currently enrolled in GUVI Data Science Program (IIT-M Pravartak). Capstone project underway.

#DataScience #Capstone #GUVI #IIT-M

03. EXPERIENCE LOG

╔══════════════════════════════════════════════════════════════╗
║  GTN INFO SOLUTION                                           ║
║  Junior SQL Analyst Intern  ░  05/2024 – 05/2025            ║
╠══════════════════════════════════════════════════════════════╣
║  > SQL queries (joins, subqueries, aggregations) on MySQL    ║
║  > Python (Jupyter) for data extraction & preprocessing      ║
║  > Data validation — duplicates, nulls, inconsistencies      ║
║  > Summary tables & KPI dashboards for operations            ║
╚══════════════════════════════════════════════════════════════╝

04. EDUCATION & CERTIFICATIONS

CREDENTIAL INSTITUTION PERIOD
B.Tech – Information Technology Nandha Engineering College 2018 – 2022
Data Science Program (Capstone) GUVI × IIT-M Pravartak Jun – Oct 2025
Data Analyst Associate EXL & EduBridge Apr – Nov 2023
SQL & UNIX Certification Aimore Technologies Jan – Apr 2024
Data Analysis with Python freeCodeCamp ✓ Certified
Python Basic HackerRank ✓ Certified
Data Analytics Job Simulation Quantium ✓ Certified

05. GITHUB STATS

GitHub Stats

Top Languages

06. INITIALIZE_COMMS

$ ping -c 1 deepak.data_scientist
64 bytes from deepak (127.0.0.1): icmp_seq=1 ttl=64 time=0.841 ms

$ status --check
SYSTEM: OPERATIONAL [AWAITING_INPUT]

# Open for: ML collaborations · data science projects · technical discourse

LinkedIn Email GitHub

"Engineering precision from raw data chaos."

Popular repositories Loading

  1. Amazon-Music-Clustering Amazon-Music-Clustering Public

    Unsupervised ML project that clusters Amazon Music tracks by audio features (tempo, energy, danceability) using K-Means & DBSCAN. Includes EDA, PCA visualization, and an interactive Streamlit app f…

    Jupyter Notebook 1

  2. Mushroom_Classification Mushroom_Classification Public

    This project aims at developing a machine-learning algorithm that will determine if a certain mushroom is edible or poisonous by its specifications like cap shape, cap color, gill color, etc. using…

    Jupyter Notebook

  3. PhonePe-Transaction-Insights PhonePe-Transaction-Insights Public

    Interactive Streamlit dashboard analyzing PhonePe Pulse data with real-time transaction trends, device insights, insurance penetration, and user engagement strategies.

    Jupyter Notebook

  4. The-Ultimate-Master-Directors-Guide The-Ultimate-Master-Directors-Guide Public

    I've created The Ultimate Master Directors Guide - a comprehensive 154+ director reference specifically designed for your cinema studies! This addresses your request perfectly, ensuring you won't m…

  5. Luxury-Housing-Sales-Analysis-Bengaluru Luxury-Housing-Sales-Analysis-Bengaluru Public

    End-to-end real estate analytics pipeline for Bengaluru luxury housing — Python (ETL), SQL (data warehouse), and Power BI (interactive dashboards) delivering market insights, buyer personas, and sa…

    Jupyter Notebook

  6. Content-Monetization-Modeler Content-Monetization-Modeler Public

    Content Monetization Modeler predicts YouTube ad revenue from video performance and contextual features using regression models and a Streamlit app for interactive what‑if analysis

    Jupyter Notebook