Predict loan defaults, segment customers, and recommend banking products using machine learning and data analysis tools in Python.

🖼️ Extract and process text from images with an OCR AI agent, featuring tools for image preprocessing and unit conversions.

A highly sophisticated, tested, robust and procedural recommender.

💬 Algorithms to Decompose Matrices

Lightweight, single-file vector database for experiments and small projects.

This repository organizes and stores lecture notes and study materials written for university lectures and assignments, covering vectors, linear equations, vector spaces, orthogonality, determinants, eigenvalues, SVD, and linear transformations.

LAPACK development repository

Fast, Accurate and Memory-Efficient Principal Component Analysis For Tera-scale Dataset

Singular Value Decomposition - Stable, Fast, Portable, Easy to use

👑 Multivariate exploratory data analysis in Python — PCA, CA, MCA, MFA, FAMD, GPA

AI-powered movie recommendation engine using SVD + TF-IDF hybrid filtering — runs entirely from the command line.

Reactive marmio notebooks about matrix factorization used in solving SVD, PCA, linear systems.

Behavioral auditing & repair toolkit for LLMs. Measures 8 dimensions via confidence probes.

Multi-algorithm recommendation system: collaborative filtering (ALS, SVD), content-based, hybrid with cold-start handling, A/B evaluation framework

Some utilities for the Jacobi-type SVD algorithms and beyond.

Collaborative filtering product recommendation engine using SVD & cosine similarity on Amazon review data

🧮 Linear Algebra for Data Scientists — Vectors, Matrices, Eigenvalues, SVD, PCA with Python implementations & visual intuitions.

Single-epoch low-rank RFI mitigation for radio astronomy. Reproducible code for SVD, FWSVD, and baseline methods.

This repository creates the codes from the PT_VQC and U-VQSVD algorithms for process tomography. Contains testing, CI, Docker, Data storage with Postgresql and Pandas for full article see New J. Phys. 26 073017

Scraping publicly-accessible Letterboxd data and creating a movie recommendation model with it that can generate recommendations when provided with a Letterboxd username