Data Science Study Guide

Probability, statistics, regression, classification, model evaluation, unsupervised learning, time series, and neural networks — the foundations for data science interviews.

Other tracks: Quantitative Finance · Software Engineering

Section 1: Probability Foundations

4 lessons

Random Variables and Distributions
The mathematical language for describing uncertain quantities.
Expectation and Variance
The two most important numbers summarizing a distribution.
Conditional Probability and Bayes' Theorem
Updating beliefs in the face of new evidence.
Central Limit Theorem
Why the normal distribution shows up everywhere.

Section 2: Descriptive Statistics

3 lessons

Measures of Central Tendency
Mean, median, mode — and when each is the right summary.
Measures of Variability
Range, IQR, variance, standard deviation — how spread out is the data?
Correlation and Covariance
Measuring the linear relationship between two variables.

Section 3: Inferential Statistics

3 lessons

Hypothesis Testing
Null hypothesis, p-values, and what they actually mean.
Confidence Intervals
An interval estimate for a parameter — and what 95% really means.
T-test, ANOVA, and Friends
Standard tests for comparing means.

Section 4: Linear Regression

3 lessons

Ordinary Least Squares
Fitting a line by minimizing squared residuals.
Regression Assumptions and Diagnostics
What linear regression assumes, and how to check.
Regularization — Ridge and Lasso
Shrinking coefficients to prevent overfit and handle multicollinearity.

Section 5: Classification

4 lessons

Logistic Regression
Linear model for binary outcomes via the logit link.
Classification Metrics
Precision, recall, AUC — picking the right one for your problem.
Decision Trees
Recursive partitioning of the feature space.
Random Forests and Gradient Boosting
The dominant algorithms for tabular machine learning.

Section 6: Model Evaluation

3 lessons

Train/Test/Validation Splits
Honestly measuring how your model will perform on new data.
Bias-Variance Tradeoff
The fundamental decomposition of model error.
Feature Engineering
Turning raw data into model-useful inputs.

Section 7: Unsupervised Learning

3 lessons

K-Means Clustering
Partitioning data into K spherical clusters.
Principal Component Analysis
Linear dimensionality reduction by finding directions of maximum variance.
Anomaly Detection
Identifying outliers when you don't have labels.

Section 8: Time Series

2 lessons

Stationarity
A property of time series — and what to do when it's missing.
ARIMA and Modern Forecasting
Classical and modern approaches to time-series prediction.

Section 9: Neural Networks

3 lessons

Neural Network Fundamentals
Layers, activations, and gradient descent.
Training Deep Networks
Optimization tricks that make deep learning practical.
Transformers and Attention
The architecture behind modern NLP and beyond.

Section 10: Practical Considerations

2 lessons

A/B Testing
Running controlled online experiments — the right way.
Data Leakage
The most common reason your model 'works' in evaluation but flops in production.

Section 1: Probability Foundations

Random Variables and Distributions

Expectation and Variance

Conditional Probability and Bayes' Theorem

Central Limit Theorem

Section 2: Descriptive Statistics

Measures of Central Tendency

Measures of Variability

Correlation and Covariance

Section 3: Inferential Statistics

Hypothesis Testing

Confidence Intervals

T-test, ANOVA, and Friends

Section 4: Linear Regression

Ordinary Least Squares

Regression Assumptions and Diagnostics

Regularization — Ridge and Lasso

Section 5: Classification

Logistic Regression

Classification Metrics

Decision Trees

Random Forests and Gradient Boosting

Section 6: Model Evaluation

Train/Test/Validation Splits

Bias-Variance Tradeoff

Feature Engineering

Section 7: Unsupervised Learning

K-Means Clustering

Principal Component Analysis

Anomaly Detection

Section 8: Time Series

Stationarity

ARIMA and Modern Forecasting

Section 9: Neural Networks

Neural Network Fundamentals

Training Deep Networks

Transformers and Attention

Section 10: Practical Considerations

A/B Testing

Data Leakage

Section 1: Probability Foundations

Random Variables and Distributions

Expectation and Variance

Conditional Probability and Bayes' Theorem

Central Limit Theorem

Section 2: Descriptive Statistics

Measures of Central Tendency

Measures of Variability

Correlation and Covariance

Section 3: Inferential Statistics

Hypothesis Testing

Confidence Intervals

T-test, ANOVA, and Friends

Section 4: Linear Regression

Ordinary Least Squares

Regression Assumptions and Diagnostics

Regularization — Ridge and Lasso

Section 5: Classification

Logistic Regression

Classification Metrics

Decision Trees

Random Forests and Gradient Boosting

Section 6: Model Evaluation

Train/Test/Validation Splits

Bias-Variance Tradeoff

Feature Engineering

Section 7: Unsupervised Learning

K-Means Clustering

Principal Component Analysis

Anomaly Detection

Section 8: Time Series

Stationarity

ARIMA and Modern Forecasting

Section 9: Neural Networks

Neural Network Fundamentals

Training Deep Networks

Transformers and Attention

Section 10: Practical Considerations

A/B Testing

Data Leakage