predict-method: Predicts the Next Click(s) of a User

In clickstream: Analyzes Clickstreams Based on Markov Chains

Predicts the Next Click(s) of a User

Description

Predicts the Next Click(s) of a User

Usage

## S4 method for signature 'MarkovChain'
predict(object, startPattern, dist = 1, ties = "random")

Arguments

object	The MarkovChain used for predicting the next click(s)
startPattern	Starting clicks of a user as Pattern object. A Pattern with an empty sequence is also possible.
dist	(Optional) The number of clicks that should be predicted (default is 1).
ties	(Optional) The strategy for handling ties in predicting the next click. Possible strategies are random (default) and first.

Methods

list("signature(object = \"MarkovChain\")")

This method predicts the next click(s) of a user. The first clicks of a user are given as Pattern object. The next click(s) are predicted based on the transition probabilities in the MarkovChain object. The probability distribution of the next click (n) is estimated as follows:

X^{(n)}=B \cdot \sum_{i=1}^k \lambda_iQ_iX^{(n-i)}

The distribution of states at time n is given as X^n. The transition matrix for lag i is given as Q_i. \lambda_i specifies the lag parameter and B the absorbing probability matrix.

Author(s)

Michael Scholz [e-mail]

See Also

fitMarkovChain

Examples

# fitting a simple Markov chain and predicting the next click
clickstreams <- c("User1,h,c,c,p,c,h,c,p,p,c,p,p,o",
               "User2,i,c,i,c,c,c,d",
               "User3,h,i,c,i,c,p,c,c,p,c,c,i,d",
               "User4,c,c,p,c,d",
               "User5,h,c,c,p,p,c,p,p,p,i,p,o",
               "User6,i,h,c,c,p,p,c,p,c,d")
cls <- as.clickstreams(clickstreams, header = TRUE)
mc <- fitMarkovChain(cls)
startPattern <- new("Pattern", sequence = c("h", "c"))
predict(mc, startPattern)
#
# predict with predefined absorbing probabilities
#
startPattern <- new("Pattern", sequence = c("h", "c"),
        absorbingProbabilities = data.frame(d = 0.2, o = 0.8))
predict(mc, startPattern)

clickstream documentation built on Sept. 27, 2023, 5:06 p.m.