Mastering Data Science Interviews – eBook

Description

A new guide to passing data science interviews and landing that sought after job!

In over 800 pages, I provide detailed answers to over 160 common questions in data science and machine learning interviews. We start off with a short succinct answer to each question and then dive into the mathematical intuition behind each concept. A deep dive into each topic is given along with Python coding examples.

This book is suitable for both current Master’s students or those who want to refresh their interview skills. This book will also serve as a baseline knowledge for data science vivas.

Table of Contents:

Introduction

1. The Aim of This Book
2. Prepare for Data Science Interviews

I Modelling and Theory

3. The Bias–Variance trade-off
4. Parametric and Non-Parametric Models
5. Linear Regression
6. Multicollinearity and Model Stability
7. Logistic Regression
8. Decision Trees
9. Bagging and Random Forest
10. Boosting
11. Neural Networks

II Optimisation and Training

12. Loss Functions
13. Gradient Descent
14. Momentum and Adaptive Optimisers
15. Regularisation
16. Training Instabilities
17. Weight Initialisation
18. Hyperparameters
19. Early Stopping

III Evaluation and Metrics

20. Train, Validation, and Test Data
21. Data Leakage
22. Cross Validation
23. Classification Metrics
24. Confusion Matrices
25. ROC Curves
26. Precision–Recall Curves
27. Regression Metrics
28. Model Fitting
29. Model Comparison
30. Information Criteria
31. Statistical Testing
32. Calibration
33. Log Loss

IV Conceptual Foundations

34. The Central Limit Theorem
35. Independence
36. Maximum Likelihood Estimation
37. Bayesian Inference
38. Probability Foundations
39. Feature Engineering
40. Feature Scaling
41. Curse of Dimensionality
42. Principal Component Analysis
43. Clustering
44. Generative vs Discriminative Models
45. Model Interpretability

V Applied ML and Systems

46. Machine Learning Pipelines
47. Real-World Data Challenges
48. Missing Data
49. Outliers
50. Imbalanced Datasets
51. Model Deployment and Monitoring
52. Production ML Systems
53. Online Learning
54. Scaling Machine Learning
55. Distributed Training
56. Experimentation
57. Designing ML Systems