markov_model

data.frame containing paths and conversions.

var_channel

name of the column containing total conversions.

var_conv

name of the column containing total conversion value.

var_value

number of total simulations from transition matrix.

nsim

number of bootstrap samples from the empirical distribution of the maxium number of steps between channels.

n_boot

n_single_boot

if set to 1 return the transition matrix between channels.

out_trans_matrx

Estimate a first-order Markov model from customer journey data.

online attribution

multi channel funnel

channel attribution

markov graph

attribution problem

Advertisers use a variety of online marketing channels to reach consumers and they want to know the degree each channel contributes to their marketing success. It's called the online multi-channel attribution problem. This package contains a probabilistic algorithm for the attribution problem. The model uses a first-order Markov representation to identifying structural correlations in the customer journey data. The package also contains three heuristic algorithms (first-touch, last-touch and linear-touch approach) for the same problem. The algorithms are implemented in C++. For a more extensive version of the package, which includes a k-order Markov model and useful functions to handle customer journey data, and for customizations please contact <davide.altomare@gmail.com>.

markov_model: Markov Model for the online attribution problem

Description

Usage

Arguments

Value

Examples