Skip to content
View Yash49-Xe's full-sized avatar
😄
Focusing
😄
Focusing

Block or report Yash49-Xe

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
Yash49-Xe/README.md

Yash Raj

B.Tech · Mathematics & Scientific Computing

LinkedIn Twitter Email Portfolio


About

I'm a Mathematics & Scientific Computing student focused on data science and backend engineering. My work centers on building data pipelines, designing REST APIs, and applying statistical methods to extract insight from real-world datasets — with a mathematical background that shapes how I think about model design, data quality, and performance trade-offs.

Currently moving from descriptive analysis toward predictive systems — deepening my work in machine learning and building models that forecast and classify rather than just describe.


Technical Skills

Data Science & Analytics

Python Pandas NumPy SciPy Matplotlib Seaborn Jupyter

Backend & APIs

FastAPI Uvicorn SQLite Java

DSA & Tools

C++ LeetCode Git GitHub


Projects

Automated Wealth & Portfolio Optimization API

An asynchronous backend microservice that ingests live market data and computes the mathematically optimal capital allocation across a multi-asset portfolio. An asyncio background worker syncs EOD closing prices and the live 10-year US Treasury rate from the FMP API into a local SQLite database on a 24-hour cycle, fully decoupling data ingestion from request handling. SciPy's SLSQP algorithm minimizes the negative Sharpe Ratio over the Efficient Frontier to produce optimal portfolio weights.


Python FastAPI SciPy SQLite



View Repository →

Dynamic Pricing Optimization Engine

A high-performance microservice that computes the mathematically optimal price for products to maximize profit. Uses SciPy's minimize algorithm to locate the exact peak of a profit parabola, balancing base costs, dynamic demand multipliers, and competitor pricing. PyArrow loads a compressed Parquet database directly into RAM on boot, eliminating disk I/O and enabling Pandas Boolean indexing across 100,000+ products in milliseconds.


Python FastAPI SciPy PyArrow



View Repository →

E-Commerce Customer RFM Segmentation API

An end-to-end data science pipeline and REST API for customer segmentation. Processes 100,000+ real-world e-commerce transactions to compute Recency, Frequency, and Monetary scores and classify customers into actionable business segments in real time.

A key EDA finding — over 95% of customers had made only a single purchase — required custom scoring functions outside standard quantile methods to meaningfully isolate high-value segments from the broader one-time buyer pool.


Python FastAPI Pandas Seaborn



View Repository →

More on the way

Currently building out additional projects in machine learning and applied statistics. New work gets pushed regularly — the full, up-to-date list always lives on my portfolio site.



Visit Portfolio →


Currently Learning

Area Focus
SQL Query optimization and large-scale structured datasets
Scikit-Learn Supervised and unsupervised learning pipelines
ML Fundamentals Regression, classification, and clustering — with emphasis on underlying mathematics
Pipeline Optimization Applying scientific computing principles to data processing efficiency

GitHub Stats

Contribution Graph


Contact



Profile views

Pinned Loading

  1. portfolio-optimization-api portfolio-optimization-api Public

    A high-performance quantitative finance API that dynamically calculates optimal multi-asset portfolio allocations to maximize returns and minimize risk.

    Python 2 1

  2. ecommerce-rfm-api ecommerce-rfm-api Public

    An end-to-end data science pipeline and REST API for customer segmentation using RFM analysis on Brazilian e-commerce data.

    Jupyter Notebook 4

  3. dynamic-pricing-engine dynamic-pricing-engine Public

    A data-driven dynamic pricing API built with FastAPI, Pandas, and SciPy optimization.

    Python 2

  4. Prominent07/QR-Based-file-sharing Prominent07/QR-Based-file-sharing Public

    CSS 7 1