Available for opportunities

Hi, I'm Biplov Singh

I build

Data Science & Machine Learning developer specializing in end-to-end ML pipelines, NLP systems, and data-driven solutions. Transforming raw data into meaningful insights.

View My Work Download Resume

3+ ML Projects

5+ Technologies

∞ Curiosity

biplov_singh.py

class BiplovSingh:
  def __init__(self):
    self.name    = "Biplov Singh"
    self.domain  = "biplovsingh.dev"
    self.focus   = [
      "Machine Learning",
      "Deep Learning / NLP",
      "Data Engineering",
    ]
    self.stack   = {
      "lang": "Python,C,C++",
      "data": "Pandas,Numpy",
      "viz": "Matplotlib,Seaborn",
      "dl":   "PyTorch",
      "db":   "MySQL / MongoDB",
      "os":   "Linux / Ubuntu",
      "other": "Git,Docker",
    }

  def available(self):
    return True  # open to work!

01. about

About Me

The story behind the code

I'm a Data Science student with a passion for turning complex data into intelligent, real-world solutions.

My journey into Machine Learning started when I became really interested in recognizing patterns. Over time I got really good at building Machine Learning systems from start to finish. Now I am studying for a MSc in Data Science At IIIT Lucknow. I like to think about the process of building a model from getting the data ready and making sure it is clean to actually using the model and checking how well it works.

I am comfortable working with Machine Learning models like Transformers to understand language. I also like designing databases that work well and using the Linux terminal to set up experiments.

I am also getting more interested, in Cybersecurity Testing how secure systems are.

Education Msc in Data Science at IIIT Lucknow(2025 - 2027)

Location Jamshedpur, Jharkhand

Environment Linux / Ubuntu

Website biplovsingh.dev

PyTorch

Linux

Python

terminal

biplov@dev:~/projects $ neofetch

biplov@dev

-------------

OS: Ubuntu 22.04 LTS

Host: Data Science Workstation

Kernel: 5.15.0-generic

Packages: 1420 (dpkg), 12 (snap)

Shell: bash 5.1.16

CPU: Intel i9-12900K (24) @ 5.200GHz

GPU: NVIDIA GeForce RTX 3090

biplov@dev:~/projects $ python train.py

Epoch 1/10 — loss: 0.4231 — acc: 0.8740

Epoch 5/10 — loss: 0.1823 — acc: 0.9310

Epoch 10/10 — loss: 0.0944 — acc: 0.9680

✓ Model saved → ./models/best.pt

biplov@dev:~/projects $ █

02. skills

Tech Stack

Tools and technologies I work with

Core Languages

Python

Expert

SQL (MySQL)

Proficient

Bash / Shell

Proficient

ML & Deep Learning

PyTorch

Proficient

Machine Learning

Proficient

Deep Learning

Proficient

NLP / Transformers

Learning

Data & Visualization

Pandas / NumPy

Proficient

Matplotlib / Seaborn

Proficient

Data Visualization

Proficient

Systems & Security

Linux / Ubuntu

Proficient

Cybersecurity

Learning

Penetration Testing

Learning

Expert Proficient Learning

03. projects

Featured Projects

A selection of my most impactful work

01 Featured

Website Clickstream Trend Analysis

Big Data Pipeline (Hadoop Ecosystem)

A complete big data pipeline demonstrating ETL and analytics using Apache Flume, Pig, and Hive. Processes website clickstream data to identify user behavior trends and patterns—similar to how Amazon, Netflix, and Facebook analyze user interactions.

Ingests clickstream data in real-time using Apache Flume

Cleans raw logs and removes errors with Apache Pig

Analyzes clean data using SQL queries in Apache Hive

Containerized distributed system deployed via Docker

Apache Flume Apache Pig Apache Hive Hadoop Docker

Crop Yield Prediction System

Machine Learning Predictive Model

A machine learning model designed to predict optimal crop choices based on environmental factors. Developed using Python, Pandas, and Scikit-Learn to analyze agricultural data including soil metrics, temperature, and rainfall to enhance data-driven agricultural decision-making.

Developed a predictive model for optimal agricultural choices

Analyzed environmental data (soil metrics, temp, rainfall)

Implemented advanced classification algorithms

Enhanced data-driven decision-making for agriculture

Python Pandas Scikit-Learn Machine Learning Classification

Movie Recommendation System

Content-Based Filtering Engine

A recommendation engine designed to suggest movies based on metadata and user preferences. Built a content-based filtering system leveraging dataset features like genres, cast, and crew to find similar titles and process large datasets efficiently.

Built a content-based filtering recommendation system

Leveraged metadata features like genres, cast, and crew

Processed large datasets using Pandas and NumPy

Applied cosine similarity to accurately calculate and rank results

Python Pandas NumPy Cosine Similarity Content-Based Filtering

More projects on GitHub

View All Projects

04. contact

Get In Touch

Have a project in mind? Let's talk.

I'm currently open to new opportunities, collaborations, and interesting projects. Whether you have a question, a proposal, or just want to say hi — my inbox is always open.

Email biplovsingh785@gmail.com

GitHub github.com/RyukR1

LinkedIn linkedin.com/in/biplovsingh