Skip to content

3rd-year CS · AI & ML · Open to internships

Naram Charan

◢SPECIALIZING INRecommendation Systems

“I teach machines to predict things.”

View Projects→Download Resume
J.A.R.V.I.S // MARK XLII
SCROLL TO INITIALIZE
01SYSTEM MODULE

Production-grade ML systems — each scanned, validated, and leakage-checked before deployment. Tap any card or FRIDAY for the full brief.

MK-01TIME-SERIES FORECASTINGFEATURED

Walmart Store Weekly Sales Forecasting

95.55% R²

Global multi-series forecasting across ~3,000 Walmart store-department pairs — one model learns them all, driven by a custom recursive walk-forward engine that feeds each week's predictions back in as the next week's lag features.

KEY RESULTS

  • 95.55% validation R² — LightGBM beat XGBoost & Random Forest
  • Recursive walk-forward engine built from scratch, no forecasting libs
  • Caught & fixed temporal leakage masquerading as R² ≈ 0.98
PythonLightGBMXGBoostScikit-LearnPandas
VIEW CODE →
MK-02CLASSIFICATION

E-Commerce Customer Churn Prediction

98.28% acc

Four-model churn system — Logistic Regression, Random Forest, XGBoost and a 4-hidden-layer PyTorch network. The deep net tops the leaderboard; XGBoost ships anyway, because a half-point of accuracy doesn't buy a GPU bill.

KEY RESULTS

  • 98.28% accuracy · 94.74% F1 on the held-out test set
  • PyTorch net hit 98.76% — rejected: marginal gain, heavy compute
  • Optuna over 10-fold Stratified CV, scored on recall
XGBoostPyTorchScikit-LearnOptuna
VIEW CODE →
MK-03RECOMMENDER SYSTEMS

Neural Collaborative Filtering Architecture

<10ms retrieval

Custom recommendation engine training 32-dimensional latent embedding vectors on sparse user-item interaction data with L2 regularization, built from scratch in PyTorch.

KEY RESULTS

  • Sub-10ms FAISS similarity search at inference
  • 32-dim latent embeddings with L2 regularization
  • Meta's FAISS index for real-time retrieval
PyTorchFAISS
VIEW CODE →
MK-04DATA ENGINEERING

Book Data Scraping & Database Pipeline

980+ in <30 min

Automated multi-page scraper using BeautifulSoup + SQLAlchemy ORM, extracting structured data (title, price, rating, availability, description, URL) into a relational schema.

KEY RESULTS

  • 980+ books scraped in under 30 minutes
  • BeautifulSoup + SQLAlchemy ORM pipeline
  • Relational SQLite schema + clean CSV exports
BeautifulSoupSQLAlchemySQLitePandas
VIEW CODE →
MK-05CLASSIFICATION

Titanic Survival Prediction Engine

85.5% acc

End-to-end classification comparing Logistic Regression, Random Forest and XGBoost with KNN imputation and disciplined, leakage-free validation.

KEY RESULTS

  • 85.5% accuracy — 12% above baseline
  • LogReg vs Random Forest vs XGBoost bake-off
  • KNN imputation, leakage-free validation
Scikit-LearnXGBoostOptunaKNNImputer
VIEW CODE →
02SYSTEM MODULE

Core subsystems and their capabilities — the stack that powers every build. (Go ahead — poke the grid, grab a reticle.)

◢ NEURAL

Deep Learning & GenAI

  • PyTorch
  • Neural Collaborative Filtering
  • Vector Embeddings
  • FAISS Similarity Search
  • Prompt Engineering
◢ MODELS

Machine Learning

  • XGBoost
  • LightGBM
  • Random Forest
  • Logistic Regression
  • Scikit-Learn
  • Optuna
◢ SIGNALS

Data Intelligence

  • Pandas
  • NumPy
  • Feature Engineering
  • KNNImputer
  • Imbalance Handling
  • RobustScaler
◢ CORE

Engineering Core

  • Python 3 · Advanced OOP
  • Data Structures
  • SQL · Schema Design
  • SQLAlchemy
  • Git Workflow
  • BeautifulSoup

SCHEMATIC · DWG-03

Neural Recommendation Engine

Collaborative filtering with FAISS retrieval — built from scratch, indexed for real-time inference.

INPUTEMBEDDINGSNEURAL NETFAISS INDEXUSERITEMkNN · L232-DIM VECTORS<10ms RETRIEVAL

FRAMEWORK

PyTorch

EMBEDDING DIM

32

INDEX

FAISS · L2

LATENCY

< 10 ms

03SYSTEM MODULE

It started with a man in a suit of armor and an AI he trusted completely — loyal, steady, present in a way that's rare to find in people, let alone machines. Figuring out how to build that turned a childhood fascination into a career.

I'm a 3rd-year CS student specializing in AI & Machine Learning, focused on end-to-end data pipelines, predictive modeling, and scalable systems — not notebook exercises.

I build recommendation architectures with deep learning and vector-index search, tune tree-based classifiers with hyperparameter optimization, and obsess over data-separation methodology so models hold up in production, not just on a leaderboard.

EDUCATION

B.Tech Computer Science Engineering

Artificial Intelligence & Machine Learning

GD Goenka University, Gurugram · 3rd Year

CGPA AVERAGE
8.98 / 10.0
GRADUATION
Expected May 2028
CERTIFICATIONS

Deep Learning Specialization

DeepLearning.AI

Jul 2026 · VERIFY →

Claude Code: A Highly Agentic Coding Assistant

DeepLearning.AI · Anthropic

Jul 2026 · VERIFY →

Machine Learning Specialization

DeepLearning.AI · Stanford University

May 2026 · VERIFY →

Databases & SQL for Data Science with Python

IBM · Coursera

Nov 2025 · VERIFY →

Python for Everybody Specialization

University of Michigan · Coursera

Mar 2025 · VERIFY →

Prompt Engineering & Generative AI

Google · Vanderbilt University

Mar 2025 · VERIFY →

04SYSTEM MODULE

Channels are open. Reach out for internships, collaborations, or to talk shop about ML.

jarvis@naramcharan:~$ contact

$ whoami

Naramreddy Charan Kumar Reddy — AI & Machine Learning Engineer

$ list --channels

$

DESIGNED & BUILT BY NARAM CHARAN · POWERED BY J.A.R.V.I.S