ml-interview-prep / README.md
gr8monk3ys's picture
Upload folder using huggingface_hub
3e00d6f verified

A newer version of the Gradio SDK is available: 6.11.0

Upgrade
metadata
title: ML Interview Prep
emoji: 🎯
colorFrom: yellow
colorTo: red
sdk: gradio
sdk_version: 5.9.1
python_version: '3.10'
app_file: app.py
pinned: false
license: mit
short_description: Practice ML and Data Science interview questions

ML Interview Prep

An interactive tool for practicing machine learning and data science interview questions. Features 500+ curated questions across 10 categories with detailed expert answers.

Features

500+ Interview Questions

Comprehensive coverage of ML/DS interview topics from top tech companies.

10 Categories

  • Statistics & Probability
  • ML Theory & Algorithms
  • Deep Learning
  • Natural Language Processing
  • Computer Vision
  • System Design
  • SQL & Databases
  • Python Programming
  • Feature Engineering
  • A/B Testing & Experimentation

Three Difficulty Levels

  • Easy - Fundamentals and basic concepts
  • Medium - Applied knowledge and trade-offs
  • Hard - Advanced topics and edge cases

Practice Modes

Quiz Mode

  • Random questions based on your filters
  • Try to answer before revealing the solution
  • Track your progress

Flashcard Mode

  • Quick review of key concepts
  • Flip cards to see answers
  • Great for last-minute prep

Browse Mode

  • Search and filter all questions
  • Study specific topics in depth

Company Tags

Questions tagged by company (Google, Meta, Amazon, etc.) so you can focus on company-specific prep.

How to Use

  1. Select categories you want to practice
  2. Choose difficulty level
  3. Pick a mode (Quiz, Flashcard, or Browse)
  4. Start practicing!

Question Sources

Questions are curated from:

  • Real interview experiences shared online
  • Common ML/DS interview patterns
  • Academic fundamentals
  • Industry best practices

Example Questions

ML Theory (Medium):

"Explain the bias-variance tradeoff and how it affects model selection."

Deep Learning (Hard):

"How would you handle class imbalance in a neural network for fraud detection?"

System Design (Hard):

"Design a real-time recommendation system for a streaming platform."

License

MIT

Author

Built by Lorenzo Scaturchio