The time decay attribution model assigns more conversion credit to the interactions which are closest in time to conversion. 

This model is based on the assumption that the users’ interactions that occurred further in the past are less relevant than the interactions that occurred just before conversion.

Let us suppose you want to understand the buying behaviour of your customers during a promotional campaign.

You then would like to assign more conversion credit to the interactions which occurred closest in time to the conversions. 

In that case, you could use the time decay attribution model.

The time decay model takes half-life in exponential decay into account while calculating conversion credit distribution. 

The following is the formula to calculate half-life in exponential decay:

Source: https://en.wikipedia.org/wiki/Half-life

N(t) denotes the quantity that has not decayed after a time ‘t’.

N(o) denotes the initial amount before measuring decay. In our case, this initial amount is 100% conversion credit. 

t denotes the time span an interaction is away from conversion. 

t ½ denotes half-life which is the time it takes for a quantity to reduce to half its original value. 

By default, the time decay attribution model has a half-life value of seven days. 

What that means is that the interaction that occurred seven days prior to conversion, gets half (½) the conversion credit than the interaction that occurred on the day of conversion. 

This half-life value is also called the decay rate. 

Get my best selling books on Attribution Modelling

• Learn to implement attribution modelling in your organisation
• Understand the customer purchase journey across devices
• Determine the most effective marketing channels for investment

 Click book covers to find out more

In Google Analytics you can change this decay rate while creating a custom attribution model that uses time decay as a baseline model.

Consider the following conversion path with a path length of three:

Let us assume that the interaction with position one occurred 14 days ago, interaction with position two occurred 7 days ago and interaction with position three occurred on the day of conversion. 

Now under the time decay attribution model, the conversion credit for each interaction would be calculated as: 

Campaign A gets 85.7% (57.1% + 28.6%) credit for the conversion.

Campaign B gets 14.3% credit for the conversion.

Campaign C gets 0% credit for the conversion (as Campaign C is not on the conversion path)

The actual calculation of the conversion credit distribution in the case of the time decay attribution model is quite complex and cannot be done or demonstrated manually.

So do not worry about that. 

Just remember that in the case of the time decay model, the interactions which occurred closest in time to the conversion get the maximum credit for the conversion. 

And as an interaction gets further away from the conversion, it gets less conversion credit. 

In the time decay attribution model, what decays with time is the conversion credit assigned to each previous touchpoint. 

Other articles on Google Analytics Attribution Models

1. Last Interaction Attribution Model in Google Analytics Explained
2. First Interaction Attribution Model in Google Analytics
3. Linear Attribution Model in Google Analytics
4. Position-Based Attribution Model in Google Analytics – Tutorial
5. Last Non-Direct Click Attribution Model in Google Analytics
6. Last Google Ads Click Attribution Model in Google Analytics
7. Data-Driven Attribution Model in Google Analytics – Tutorial
8. Learn to set up Data-driven attribution model in Google Analytics
9. Default & Custom Google Analytics Attribution Models Explained
10. Which Attribution Model to use in Google Analytics?
11. How to Create Custom Attribution Model in Google Analytics