Master Data Science, AI & ML

Curated problems and resources to ace your data science interviews and build real-world ML systems

445+
Problems
0
Completed
16
Topics

📄 Need Your Resume Reviewed?

Get AI-powered resume analysis, ATS scoring, and job matching

🚀 Review My Resume

🐍 Python Fundamentals

Master Python basics for data science

0/17
Python Data Types: Lists, Tuples, Sets, Dictionaries Easy
String Manipulation and Formatting (f-strings, format()) Easy
List Comprehensions for Data Filtering Easy
Lambda Functions with Map, Filter, Reduce Easy
File I/O: Reading CSV, JSON, Text Files Easy
Exception Handling and Error Management Easy
Generators and Iterators for Memory Efficiency Medium
Decorators for Function Timing and Logging Medium
Context Managers for Resource Management Medium
Object-Oriented Programming: Classes and Inheritance Medium
Regular Expressions for Text Processing Medium
Multithreading vs Multiprocessing for Data Tasks Medium
Async/Await for Concurrent API Calls Hard
Metaclasses and Advanced OOP Patterns Hard
Memory Profiling and Optimization Techniques Hard

📊 NumPy & Pandas

Data manipulation and analysis

0/20
NumPy Array Creation and Basic Operations Easy
Array Indexing, Slicing, and Boolean Indexing Easy
Array Reshaping and Transposing Easy
Statistical Operations (mean, median, std, var) Easy
Pandas DataFrame Creation and Loading Data Easy
DataFrame Selection: loc, iloc, at, iat Easy
Filtering Data with Boolean Conditions Easy
Handling Missing Data (isnull, fillna, dropna) Easy
Broadcasting and Vectorized Operations Medium
GroupBy Operations and Aggregations Medium
Merge, Join, and Concatenate DataFrames Medium
Pivot Tables and Cross-tabulation Medium
Time Series Data Manipulation Medium
Apply, Map, and Applymap Functions Medium
Window Functions (Rolling, Expanding) Medium
Advanced Vectorization and Performance Optimization Hard
Multi-index and Hierarchical Data Structures Hard
Memory-Efficient Data Processing with Chunking Hard

📈 Statistics & Probability

Statistical foundations for ML

0/26
Measures of Central Tendency (Mean, Median, Mode) Easy
Measures of Dispersion (Variance, Standard Deviation) Easy
Percentiles and Quartiles Calculation Easy
Box Plots and Outlier Detection Easy
Correlation and Covariance Matrices Easy
Skewness and Kurtosis Easy
Probability Distributions (Normal, Binomial, Poisson) Medium
Central Limit Theorem Applications Medium
Hypothesis Testing Fundamentals Medium
t-tests (One-sample, Two-sample, Paired) Medium
Chi-square Tests (Goodness-of-fit, Independence) Medium
ANOVA (One-way and Two-way) Medium
Confidence Intervals Medium
P-values and Statistical Significance Medium
Type I and Type II Errors Medium
Power Analysis and Sample Size Calculation Medium
Bayesian Statistics and Inference Hard
Maximum Likelihood Estimation Hard
Non-parametric Tests (Mann-Whitney, Kruskal-Wallis) Hard
Bootstrap Methods and Resampling Hard
Time Series Statistics (ACF, PACF) Hard
A/B Testing and Experimental Design Hard
Multivariate Statistical Analysis Hard
Monte Carlo Simulations Hard

🤖 Machine Learning

Classical ML algorithms and concepts

0/32
Simple Linear Regression from Scratch Easy
Multiple Linear Regression Easy
Logistic Regression Implementation Easy
K-Nearest Neighbors (KNN) Easy
Naive Bayes Classifier Easy
Train-Test Split and Cross-Validation Easy
Regression Metrics (MSE, RMSE, MAE, R²) Easy
Classification Metrics (Accuracy, Precision, Recall, F1) Easy
Decision Trees (CART Algorithm) Medium
Random Forests Medium
K-Means Clustering Algorithm Medium
Hierarchical Clustering Medium
DBSCAN Clustering Medium
Principal Component Analysis (PCA) Medium
Ridge and Lasso Regression (L1/L2 Regularization) Medium
Elastic Net Regression Medium
Gradient Descent Optimization Medium
ROC Curves and AUC Medium
Confusion Matrix Analysis Medium
K-Fold Cross-Validation Medium
Gradient Boosting (XGBoost, LightGBM, CatBoost) Hard
Support Vector Machines (SVM) Hard
Gaussian Mixture Models (GMM) Hard
Hyperparameter Tuning (Grid Search, Random Search) Hard
Bayesian Optimization Hard
Ensemble Methods (Bagging, Boosting, Stacking) Hard
Imbalanced Data Handling (SMOTE, Class Weights) Hard
Time Series Forecasting (ARIMA, Prophet) Hard
Recommendation Systems (Collaborative Filtering) Hard
Anomaly Detection Techniques Hard

🧠 Deep Learning

Neural networks and deep learning

0/27
Perceptron from Scratch Easy
Activation Functions (ReLU, Sigmoid, Tanh, Softmax) Easy
Forward Propagation in Neural Networks Easy
Backpropagation Algorithm Medium
Neural Network from Scratch (Multi-layer) Medium
Optimization Algorithms (SGD, Adam, RMSprop) Medium
Batch Normalization Medium
Dropout Regularization Medium
Weight Initialization Strategies Medium
Learning Rate Scheduling Medium
Convolutional Neural Networks (CNN Architecture) Hard
Image Classification with CNNs Hard
Transfer Learning with Pre-trained Models (VGG, ResNet) Hard
Fine-tuning Pre-trained Networks Hard
Recurrent Neural Networks (RNN) Hard
LSTM Networks Hard
GRU Networks Hard
Bidirectional RNNs Hard
Sequence-to-Sequence Models Hard
Attention Mechanisms Hard
Transformer Architecture Hard
BERT and Language Models Hard
GPT Architecture Hard
Generative Adversarial Networks (GANs) Hard
Variational Autoencoders (VAE) Hard

💬 Natural Language Processing

Text processing and NLP techniques

0/26
Text Cleaning and Normalization Easy
Tokenization Techniques (Word, Subword, Character) Easy
Stop Words Removal Easy
Stemming and Lemmatization Easy
Bag-of-Words (BoW) Easy
TF-IDF Vectorization Medium
Word2Vec Embeddings Medium
GloVe Word Vectors Medium
FastText Embeddings Medium
Text Classification Medium
Sentiment Analysis Medium
Named Entity Recognition (NER) Medium
Part-of-Speech (POS) Tagging Medium
Topic Modeling (LDA) Medium
Text Summarization Medium
BERT for Text Classification Hard
Fine-tuning Transformers (RoBERTa, ALBERT) Hard
Machine Translation Basics Hard
Question Answering Systems Hard
Text Generation with GPT Hard
Prompt Engineering Hard
Zero-shot and Few-shot Learning Hard
Multilingual NLP Hard
Language Detection Hard

👁️ Computer Vision

Image processing and CV algorithms

0/26
Image Loading and Manipulation (OpenCV, PIL) Easy
Color Spaces (RGB, HSV, Grayscale) Easy
Image Resizing and Cropping Easy
Image Filtering and Smoothing (Blur, Gaussian) Easy
Edge Detection (Canny, Sobel) Easy
Histogram Equalization Easy
Data Augmentation (Rotation, Flipping, Scaling) Medium
Color Jittering and Random Cropping Medium
Advanced Augmentation (Cutout, Mixup, CutMix) Medium
Feature Extraction (HOG, SIFT, SURF) Medium
Image Classification with CNNs Medium
Transfer Learning for Image Recognition Medium
Object Detection (YOLO, SSD) Hard
R-CNN Family (Fast R-CNN, Faster R-CNN) Hard
Instance Segmentation (Mask R-CNN) Hard
Semantic Segmentation (U-Net, DeepLab) Hard
Face Detection and Recognition Hard
Pose Estimation Hard
Image Super-Resolution Hard
Style Transfer Hard
Image Captioning Hard
Visual Question Answering Hard
GANs for Image Generation Hard
Video Analysis and Action Recognition Hard

🗄️ SQL for Data Science

Database queries and data extraction

0/30
Basic SELECT and WHERE Queries Easy
DISTINCT and LIMIT Easy
ORDER BY and Sorting Easy
Aggregate Functions (COUNT, SUM, AVG, MIN, MAX) Easy
GROUP BY and HAVING Easy
String Functions (CONCAT, SUBSTRING, LENGTH) Easy
Date and Time Functions Easy
CASE Statements Easy
INNER JOIN Medium
LEFT JOIN and RIGHT JOIN Medium
FULL OUTER JOIN Medium
SELF JOIN Medium
Multiple Joins Medium
Subqueries in WHERE Clause Medium
Subqueries in FROM Clause Medium
Correlated Subqueries Medium
Common Table Expressions (CTEs) Hard
Recursive CTEs Hard
Window Functions (ROW_NUMBER, RANK, DENSE_RANK) Hard
LAG and LEAD Functions Hard
Running Totals with SUM OVER Hard
Moving Averages with Window Functions Hard
PARTITION BY Usage Hard
Pivoting and Unpivoting Data Hard
UNION and UNION ALL Hard
Views and Materialized Views Hard
Indexes and Query Optimization Hard
Query Execution Plans Hard

⚙️ Feature Engineering

Create powerful features for ML models

0/25
Handling Missing Data (Strategies) Easy
Outlier Detection (IQR, Z-score) Easy
Outlier Treatment Methods Easy
Data Imputation (Mean, Median, Mode, KNN) Easy
Label Encoding Easy
One-Hot Encoding Easy
Encoding Categorical Variables (Ordinal, Binary) Medium
Feature Scaling (StandardScaler, MinMaxScaler) Medium
RobustScaler for Outliers Medium
Log and Power Transformations Medium
Box-Cox Transformation Medium
Polynomial Features Medium
Interaction Features Medium
Date/Time Feature Engineering (Day, Month, Hour) Medium
Cyclical Feature Encoding (sin/cos) Medium
Target Encoding Medium
Frequency Encoding Medium
Feature Selection Techniques (Filter, Wrapper, Embedded) Hard
Recursive Feature Elimination (RFE) Hard
Feature Importance with Tree-based Models Hard
Dimensionality Reduction (PCA, t-SNE, UMAP) Hard
Automated Feature Engineering (Featuretools) Hard
Feature Engineering Pipeline Design Hard

🚀 MLOps & Deployment

Deploy and maintain ML systems

0/25
Model Serialization (Pickle, Joblib) Easy
Model Versioning Basics Easy
Experiment Tracking with MLflow Easy
Model Registry and Metadata Management Medium
Hyperparameter Logging and Tracking Medium
Flask API for Model Serving Medium
FastAPI for ML Models Medium
Docker Containerization for ML Medium
REST API Design for ML Services Medium
Batch Prediction Systems Medium
Real-time Prediction APIs Medium
Model Endpoint Testing Medium
A/B Testing for Models Hard
Model Monitoring and Logging Hard
Data Drift Detection Hard
Model Performance Monitoring Hard
CI/CD for ML Pipelines Hard
Feature Store Implementation Hard
Model Retraining Strategies Hard
Cloud Deployment (AWS SageMaker, Azure ML, GCP) Hard
Kubernetes for ML Hard
Model Scaling and Load Balancing Hard
Cost Optimization for ML Infrastructure Hard

🤖 Generative AI & LLMs

Master Large Language Models and Generative AI

0/35
Introduction to Transformer Architecture Easy
Self-Attention Mechanism Deep Dive Easy
Positional Encoding and Embeddings Easy
Tokenization Strategies (BPE, WordPiece, SentencePiece) Easy
Understanding GPT Architecture (Decoder-only) Easy
BERT Architecture (Encoder-only Models) Easy
T5 and Seq2Seq Models (Encoder-Decoder) Easy
Prompt Engineering Techniques and Best Practices Medium
Few-Shot and Zero-Shot Learning Medium
Chain-of-Thought Prompting Medium
Fine-tuning LLMs with LoRA and QLoRA Medium
Parameter-Efficient Fine-Tuning (PEFT) Medium
Instruction Tuning and RLHF Medium
LLM Evaluation Metrics (BLEU, ROUGE, Perplexity) Medium
Temperature, Top-k, and Top-p Sampling Medium
OpenAI API Integration (GPT-4, GPT-3.5) Medium
Using Anthropic Claude API Medium
Hugging Face Transformers Library Medium
Running Local LLMs (Llama, Mistral, Phi) Medium
Building Custom Text Generation Pipelines Hard
Multimodal Models (CLIP, DALL-E, GPT-4V) Hard
Diffusion Models for Image Generation Hard
Stable Diffusion Architecture and Training Hard
LLM Quantization (4-bit, 8-bit) Hard
Model Distillation for LLMs Hard
Context Window Management and Optimization Hard
Long Context Models (100k+ tokens) Hard
Function Calling with LLMs Hard
Structured Output Generation (JSON mode) Hard
LLM Safety and Alignment Hard
Jailbreak Prevention and Red Teaming Hard
Constitutional AI and Value Alignment Hard
LLM Inference Optimization (vLLM, TensorRT-LLM) Hard
Mixture of Experts (MoE) Architecture Hard
Building Custom LLM Applications with LangChain Hard

🔍 RAG & Vector Databases

Retrieval Augmented Generation systems

0/30
Introduction to RAG Architecture Easy
Vector Embeddings Fundamentals Easy
Semantic Search vs Keyword Search Easy
Sentence Transformers and Embedding Models Easy
OpenAI Embeddings API Easy
Document Chunking Strategies Medium
Text Splitting and Preprocessing for RAG Medium
Vector Database Setup (Pinecone) Medium
Working with ChromaDB Medium
Weaviate Vector Database Medium
FAISS for Similarity Search Medium
Qdrant Vector Database Medium
Milvus Vector Database Medium
Building a Basic RAG Pipeline Medium
Retrieval Strategies (Top-K, MMR) Medium
Hybrid Search (Dense + Sparse Retrieval) Hard
Re-ranking Retrieved Documents Hard
Query Transformation and Expansion Hard
Multi-Query Retrieval Hard
Contextual Compression in RAG Hard
Metadata Filtering in Vector Search Hard
Parent Document Retrieval Hard
Self-Query Retrieval Hard
RAG Evaluation Metrics (RAGAS) Hard
Advanced RAG: Graph RAG Hard
Adaptive RAG (Self-RAG) Hard
Corrective RAG (CRAG) Hard
Multimodal RAG (Images + Text) Hard
RAG with SQL Databases Hard
Production RAG Systems (Scaling & Optimization) Hard

🤖 AI Agents & Agentic AI

Build autonomous AI agents and multi-agent systems

0/30
Introduction to AI Agents Easy
ReAct Pattern (Reasoning + Acting) Easy
Tool Use and Function Calling in Agents Easy
Agent Memory Systems (Short-term & Long-term) Easy
LangChain Agents Framework Medium
LlamaIndex Agents Medium
AutoGPT Architecture and Implementation Medium
BabyAGI Task Management System Medium
Building Custom Tools for Agents Medium
Agent Planning and Decomposition Medium
Conversational Agents with State Management Medium
Web Browsing Agents Medium
Code Execution Agents Medium
Multi-Agent Systems and Communication Hard
Hierarchical Agent Architectures Hard
CrewAI Framework for Multi-Agent Collaboration Hard
AutoGen: Multi-Agent Conversations Hard
Agent Evaluation and Benchmarking Hard
Self-Reflection and Self-Critique Mechanisms Hard
Agent Error Handling and Recovery Hard
Goal-Oriented Action Planning Hard
Tree of Thoughts (ToT) for Complex Reasoning Hard
Graph of Thoughts (GoT) Reasoning Hard
Agent Workflow Orchestration (LangGraph) Hard
Human-in-the-Loop Agent Systems Hard
Agent Safety and Sandboxing Hard
Cost Optimization for Agent Systems Hard
Autonomous Research Agents Hard
Data Analysis Agents Hard
Production Agent Systems (Monitoring & Logging) Hard

Learning Roadmap

1

Python Fundamentals

Master Python basics, OOP, and functional programming

2

Data Manipulation

NumPy, Pandas, and data wrangling techniques

3

Mathematics & Statistics

Linear algebra, calculus, probability, and statistics

4

Machine Learning

Classical ML algorithms and scikit-learn

5

Deep Learning

Neural networks, PyTorch/TensorFlow

6

Specialization

NLP, Computer Vision, or MLOps

7

Generative AI & LLMs

Master Large Language Models, transformers, and prompt engineering

8

RAG Systems

Build Retrieval Augmented Generation with vector databases

9

AI Agents

Create autonomous AI agents and multi-agent systems

Resources

📚 Books

  • Hands-On Machine Learning
  • Deep Learning by Goodfellow
  • Python for Data Analysis

🎥 Courses

  • Andrew Ng's ML Course
  • Fast.ai Deep Learning
  • Stanford CS229

🛠️ Tools

  • Jupyter Notebooks
  • Google Colab
  • Kaggle