liveBook · Manning

Random walk

A random walk is a stochastic process that forms a sequence of states through successive random transitions from the current state.

How 4 Manning books explain it

Graph Neural Networks in Action

A random walk is a stochastic traversal of a graph that repeatedly moves from a node to one of its connected neighbors according to transition probabilities.

How it is used
Uses walks to sample graph neighborhoods for Node2Vec embeddings that capture node context and similarity.
How deep it goes
Explains encounter probability and DeepWalk versus Node2Vec walk choices without deriving transition probabilities.
Examples
Illustrates walks with a two-hop encounter calculation and embeddings of frequently co-purchased political books.
What you can do after
Apply it via the Node2Vec Python library to generate embeddings for visualization or machine-learning features.

Read how Graph Neural Networks in Action explains random walk →

Grokking Bayes

A random walk is a stochastic process in which successive states change through random increments.

How it is used
Models evolving latent quantities inside Bayesian state-space filters when changes are treated as stochastic increments.
How deep it goes
Defines the Gaussian transition, variance control, filtering behavior, and forecast limitation, but stops short of explicit trend modeling.
Examples
Uses atmospheric CO₂ levels, successive differences, NumPy variance estimation, Kalman updates, and multiyear forecast plots.
What you can do after
Apply it via a Kalman filter to estimate a noisy evolving state and assess how transition variance affects adaptation and forecasts.

Read how Grokking Bayes explains random walk →

Investing for Programmers

A random walk is a stochastic process whose successive movements are determined by random variation rather than a predictable directional pattern.

How it is used
Frames stock-price prediction as uncertain analysis rather than a dependable search for deterministic patterns.
How deep it goes
Explains randomness through market psychology and interconnected markets, but stops short of formal stochastic-process mathematics.
Examples
Uses Mr. Market, tulip mania, global market spillovers, and historical stock performance as concrete illustrations.
What you can do after
Evaluate/understand why historical price patterns may provide limited assistance for predicting chaotic markets.

Read how Investing for Programmers explains random walk →

Graph Algorithms for Data Science

A random walk is a stochastic graph traversal that repeatedly moves from the current node to a neighboring node according to transition probabilities.

How it is used
Generates graph-based training sentences for node2vec and downstream node embedding models.
How deep it goes
Explains walk length, first- and second-order transitions, and weighted probabilities without developing advanced probability or implementation details.
Examples
Uses a traversal from A through C, B, and F to H, plus unweighted and weighted neighbor transitions.
What you can do after
Apply it via node2vec to generate sentence-like walks for training node embeddings.

Read how Graph Algorithms for Data Science explains random walk →

Also covered in

What to know first

Related concepts

Questions about random walk

What is random walk?

A random walk is a stochastic process that forms a sequence of states through successive random transitions from the current state.

Which Manning books explain random walk?

Graph Neural Networks in Action, Grokking Bayes, Investing for Programmers and Graph Algorithms for Data Science.

What should I know before learning random walk?

Manning books that teach random walk usually introduce normal distribution and signal first.

What is the difference between random walk and long-term trend?

A random walk is a stochastic process that forms a sequence of states through successive random transitions from the current state. A long-term trend is a persistent directional pattern in observations across an extended period.

What kinds of random walk are there?

Kinds of random walk include first-order random walk.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.