Skip to content
Statistics & MLPro

Reason clearly when outcomes are uncertain.

Probability for Data Scientists

Move from events and conditional probability to random variables, distributions, Bayes, limit theorems, estimation, and simulation.

What you will be able to do

Leave with capability, not just vocabulary.

Model events with conditional probability

Work with random variables and common distributions

Update beliefs with Bayes theorem

Use simulation and limit theorems to check intuition

Running example

Streamora, a streaming product whose viewing, churn, experiments, and recommendations make uncertainty concrete.

Prerequisites

Basic algebra. Statistics Foundations is helpful but not required.

Curriculum

Every module earns the next one.

Open any module to review its exact sections. Progress and completion follow you through the course.

8 modules · ~9 hours
01
Module 1

The Language of Uncertainty

BeginnerFree preview

Topics include What P=0.7 Actually Means, Sample Spaces & Events, The Three Axioms, and more.

View 6 sections
  1. 1What Does P = 0.7 Actually Mean?
  2. 2Sample Spaces & Events: Meet Streamora
  3. 3The Three Axioms of Probability
  4. 4Set Operations: Union, Intersection, Complement
  5. 5Counting Principles: Permutations & Combinations
  6. 6When Probability Is (and Isn't) the Right Tool
65 min6 sections
Open module
02
Module 2

Conditional Probability

BeginnerPro

Topics include What Changes When You Know Something, The Multiplication Rule, Tree Diagrams as a Thinking Tool, and more.

View 6 sections
  1. 1What Changes When You "Know Something"
  2. 2The Conditional Probability Formula
  3. 3The Multiplication Rule & Tree Diagrams
  4. 4Independence: Formal Definition & Common Traps
  5. 5The Chain Rule for Multiple Events
  6. 6Streamora Case: Conditional Watch-Through Rates
65 min6 sections
Open module
03
Module 3

Bayes' Theorem

BeginnerPro

Topics include The Belief-Updating Formula, Prior, Likelihood, Posterior, The Disease-Test Paradox, and more.

View 6 sections
  1. 1Bayes' Theorem: The Belief-Updating Formula
  2. 2Prior, Likelihood, Posterior: The Three Pieces
  3. 3The Disease-Test Paradox (The Famous Gotcha)
  4. 4Iterative Updating: One Piece of Evidence at a Time
  5. 5Bayes in the Wild: Spam Filters & Streamora Recommendations
  6. 6The Base-Rate Fallacy: Why Smart People Miss This
65 min6 sections
Open module
04
Module 4

Random Variables

BeginnerPro

Topics include From Events to Numbers, Discrete vs Continuous, PMF, PDF, and CDF, and more.

View 6 sections
  1. 1From Events to Numbers: What Is a Random Variable?
  2. 2Discrete vs Continuous: The Mental Model Shift
  3. 3PMF, PDF, and CDF: Three Views of the Same Thing
  4. 4Expectation: The Center of Mass
  5. 5Variance & Standard Deviation: The Spread
  6. 6Linearity of Expectation: The Most Useful Theorem
60 min6 sections
Open module
05
Module 5

The Distribution Zoo

BeginnerPro

Topics include Choosing the Right Distribution, Bernoulli & Binomial, Yes/No at Scale, Geometric, Time Until First Success, and more.

View 7 sections
  1. 1The Decision Tree: Which Distribution Fits?
  2. 2Bernoulli & Binomial: Did They Click?
  3. 3Geometric: How Long Until First Success?
  4. 4Poisson: Streamora Viewer Arrivals
  5. 5Uniform & Exponential: The Continuous Twins
  6. 6The Normal Distribution: Why It's Everywhere
  7. 7Streamora Case: Picking Distributions for Real Metrics
65 min7 sections
Open module
06
Module 6

Joint Distributions & Dependence

IntermediatePro

Topics include Two Random Variables at Once, Joint, Marginal & Conditional, Independence, Formal Definition, and more.

View 6 sections
  1. 1Two Random Variables at Once: The Joint Picture
  2. 2Marginal & Conditional Distributions
  3. 3Independence: The Formal Definition
  4. 4Covariance & Correlation: How Variables Move Together
  5. 5The Correlation-Causation Trap (and Simpson's Paradox)
  6. 6Conditional Expectation E[Y|X]: The Best Single Prediction
65 min6 sections
Open module
07
Module 7

The Limit Theorems

IntermediatePro

Topics include The Law of Large Numbers, The Central Limit Theorem, Why n=30 Matters (and Why It's Not Magic), and more.

View 5 sections
  1. 1The Law of Large Numbers: Frequencies Converge
  2. 2The Central Limit Theorem: Averages Go Normal
  3. 3Why n=30 Matters (and When It Doesn't)
  4. 4CLT in Action: Averaging Streamora Watch-Time
  5. 5The Bridge to Statistics: Confidence Intervals Preview
65 min5 sections
Open module
08
Module 8

Probability in the Wild

IntermediatePro

Topics include Maximum Likelihood Estimation, The MLE Recipe, The Coin Example, Monte Carlo Simulation, and more.

View 5 sections
  1. 1Maximum Likelihood Estimation: The Idea
  2. 2The MLE Recipe: The Coin-Flipping Example
  3. 3Monte Carlo Simulation: Estimating π & Streamora KPIs
  4. 4Bootstrap: Resampling from Your Own Data
  5. 5Where Probability Lives in ML: LLM Sampling, Model Confidence
65 min5 sections
Open module
Who this course is for

Built for people who need to use the skill.

01

Data scientists strengthening probability intuition

02

Analysts moving toward experimentation or ML

03

Candidates preparing for probability interviews

Start the course

Begin with The Language of Uncertainty.

The first module establishes the language and example used throughout the rest of the course.

Open Module 1
Probability for Data Scientists | Let's Data Science | Let's Data Science