Skip to content
View kashyaputsav's full-sized avatar

Block or report kashyaputsav

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
kashyaputsav/README.md

LinkedIn Gmail Kaggle LeetCode HackerRank GitHub


Profile Views Followers



🖥️ About Me

> initializing utsav.ai ...

User        : Utsav Kashyap
Role        : Data Scientist | ML Engineer | AI Engineer
Location    : India 🇮🇳

----------------------------------------
Core Modules Loaded:

✔ Machine Learning
✔ NLP Systems
✔ Deep Learning
✔ Computer Vision

----------------------------------------
Mission Status:

🚀 Turning data → intelligence → impact

⚙️ CORE STACK


⚡ Live GitHub Activity Intelligence




🎓 Education




Institution
Lovely Professional University


Degree
B.Tech CSE


Duration
2020 – 2024


Focus
AI • ML • Systems



⚙️ Tech Stack

💻 Languages

Python C++ C

🤖 AI / Machine Learning

TensorFlow PyTorch Keras Scikit-Learn OpenCV MLflow

📊 Data & Visualization

NumPy Pandas Matplotlib Plotly SciPy

🌐 Web & Deployment

Flask FastAPI Django Streamlit HTML5 CSS3

🗄️ Databases

MySQL MongoDB SQLite

☁️ Cloud & DevOps

AWS Render Git GitHub

🏗️ Featured Projects

💳 Real-Time Credit Card Fraud Detection

XGBoost FastAPI SHAP SMOTE Optuna Imbalanced-learn

Production-grade fraud pipeline with real-time inference & explainability

Precision ████████████████████ 93%
Recall    █████████████████    85%
  • 🎯 93% precision / 85% recall on highly imbalanced transaction data
  • 🔬 SMOTE oversampling + precision-recall threshold optimization
  • ⚡ Low-latency FastAPI inference for live transaction scoring
  • 🔍 SHAP values for full model explainability & auditability
  • 🔧 Optuna automated hyperparameter search pipeline
  • 🖥️ Live prediction visualization UI built-in

View Project

🧾 Intelligent Expense Categorization

NLP XGBoost TF-IDF Flask FinTech Human-in-the-loop

QuickBooks-style ML pipeline for automated financial classification

Accuracy  ██████████████       71.3%
F1 Score  ██████████████       0.71
Best F1   ███████████████      0.75
  • 🏦 Classifies ~7,000 financial transactions into 6 categories
  • 🧠 TF-IDF + structured features → multi-class XGBoost pipeline
  • 🚀 Scalable Flask API with per-prediction confidence scores
  • 🔄 Human-in-the-loop feedback loop for continuous improvement
  • 🏭 Designed to real FinTech production standards

View Project

⭐ Restaurant Rating Classification — BiLSTM

Bidirectional LSTM Keras NLP Swiggy/Zomato Deep Learning

Stacked deep NLP architecture classifying 465k+ reviews into 5 star ratings

Reviews    ████████████████████  465,000+
Classes    ████████████████████  5 Star Ratings
Model      Stacked BiLSTM + SpatialDropout + L2
  • 🗃️ Custom NLP preprocessing pipeline at 465k+ review scale
  • 🧠 Stacked Bidirectional LSTM with spatial dropout & L2 reg
  • 🎯 Deep semantic context modelling for nuanced sentiment
  • ⚖️ Dynamic class weighting to handle review distribution skew
  • 🛑 Early Stopping with validation monitoring for generalization

View Project

🚚 Porter Delivery Time Estimation

Random Forest Feature Engineering MAE Logistics ML

ML regression model for real-world last-mile delivery time prediction

Algorithm    Random Forest Regressor
Metric       Mean Absolute Error (MAE)
Domain       Logistics & Supply Chain
  • 🌲 Random Forest regressor on historical delivery data
  • 🔧 Heavy feature engineering: time, distance, order type
  • 📉 Optimized for MAE — directly interpretable time error
  • 🗺️ Processed real logistics route & order pipelines
  • 📦 Improved last-mile delivery planning accuracy

View Project

🏙️ Smart City Route Optimization

C++ Dijkstra's Algorithm Graph Theory DSA Priority Queue

Graph-based pathfinding engine for urban road networks

Structure    Weighted Adjacency List Graph
Algorithm    Dijkstra + Min-Heap Priority Queue
Complexity   O((V + E) log V)
  • 🗺️ Weighted adjacency list for real city road networks
  • Dijkstra's Algorithm with priority queue for optimal speed
  • 🔗 Realistic directional edge weight modelling
  • 🚦 Globally optimal shortest paths between any two nodes
  • 📈 Framework for smart city infrastructure planning

View Project

🎵 Content-Based Music Recommender

Python ML NLP Signal Processing Audio Features

Audio-intelligence engine using content-based filtering

Features    Tempo · Mood · Instrumentation · Key
Method      Content-Based Filtering + User Prefs
Stack       Python · Librosa · Scikit-Learn
  • 🔊 Extracts tempo, mood, instrumentation & key from audio
  • 🧬 Builds rich multi-dimensional music content profiles
  • ⚖️ Hybrid: audio similarity + user preference weighting
  • 📈 Advanced signal processing for robust feature extraction
  • 🎧 Scalable recommendation engine architecture

View Project


🏅 Certifications

🎖️ Certificate 🏢 Platform 📅 Date
🤖 Unsupervised Learning, Recommenders & Reinforcement Learning Coursera Nov 2023
🗣️ Natural Language Processing Coursera Apr 2023
🧮 Data Structures & Algorithms (Self-Paced) GeeksforGeeks Aug 2022
🏗️ Data Structures & Algorithms HitBullsEye Jan 2023
🔄 Building Digital Transformation Strategies UpGrad May 2022

🎯 Skill Proficiency

Loading
Skill Proficiency Animated Bars



Python ML/XGBoost NLP Deep Learning FastAPI/Flask SQL/DB C++/DSA Computer Vision AWS/Cloud

📈 Contribution Activity

🐍 Watch My Contributions Get Eaten

contribution snake animation



> print("Thanks for visiting — let's build something incredible together 🚀")


Wave

Pinned Loading

  1. Real-Time-Credit-Card-Fraud-Detection-System. Real-Time-Credit-Card-Fraud-Detection-System. Public

    Real-time fraud detection using ML

    Jupyter Notebook 1

  2. QuickBooks QuickBooks Public

    A QuickBooks-style Intelligent Expense Categorization system that automatically classifies transactions based on merchant, description, amount, and date. Uses ML models (XGBoost + TF-IDF + Scaler) …

    Jupyter Notebook 1

  3. Delivery-Time-Estimator Delivery-Time-Estimator Public

    Built a Random Forest–based machine learning model to predict Porter delivery times using engineered features and evaluated performance using MAE.

    Jupyter Notebook 1

  4. Restaurant-Rating-Classification-Using-Bi-directional-LSTM-Swiggy-Zomato-Reviews-.- Restaurant-Rating-Classification-Using-Bi-directional-LSTM-Swiggy-Zomato-Reviews-.- Public

    A Deep Learning project designed to classify customer reviews from Swiggy and Zomato into 1 to 5-star ratings. This project leverages Natural Language Processing (NLP) and a 2-layer Bidirectional L…

    Jupyter Notebook

  5. DSA-1-PATH- DSA-1-PATH- Public

    Designed a C++ graph-based route optimization system for smart cities using Dijkstra’s Algorithm. Modeled road networks as weighted graphs with adjacency lists and priority queues to compute effici…

    HTML 1