Attribution is a tool that helps with the visualization of conversion paths for several types of models available in the system. This way you receive a preview of the effectiveness of marketing campaigns you lead, identify the soft spots and optimize your campaigns.
- Insight into the channels/methods/sources that result in the highest conversion.
- Optimized costs on marketing strategies.
- Imported history of events: page visits and transaction charge (minimum required history of 30 days, recommended 90 days).
- Correctly added UTM parameters to the links (medium source).
- Delivered product feed (optional).
In order to configure AI Attribution, go to Analytics > Attribution
- Channels - Choose the channels which you use in order to reach the customers, for example Facebook, Twitter, Webpushes, Email, etc.
- Primary dimension - The customer conversions are divided into Medium, Source or Medium/Source options. This happens thanks to the UTM parameters in the link through which a customer reaches your site. Therefore, in this place you can specify the UTM parameter.
- Secondary dimension - This option allows you to divide the Primary Dimension into smaller groups, resulting in additional insights.
- Metric - Provides you with the possibility to choose whether you want to analyze conversion, revenue or both. This will have an effect on both the chart and table.
- Path length - Choose the period from which the data will be used to evaluate the chosen metric.
- Time range - Determine the time ranges for which the conversion will be counted.
- Chart model - Choose one of the models described below
- Chart type - You can choose the way you want to visualize the statistics. You can display it on the line chart as in the illustration above. The line chart shows the number of conversions per day. You can also display statistics as a transition matrix which depicts the transition between channels and to some extent the probability of conversion.
You can zoom the areas in matrix, just click the chosen column, hold the button and slide the cursor to any column you want. The selected area will be zoomed in.
- Basic model:
- First-touch - This model gives complete credit to the first channel of the path that contributed to the conversion. Because of that, it gives all the credit on the basis of a single touchpoint, and it will overemphasize a single part of the funnel. The first-touch attribution model does not accredit the campaign that brings conversion nor the interaction after the initial touch.
- Last touch - This model gives the whole credit to the last channel before the conversion. However, the model doesn't consider influences leading up to the conversion.
- Last non-direct touch - This model works like last-touch, but additionally eliminates the limitations of Direct Data. Traffic attributed to Direct is typically defined by marketing analytics as a visitor manually enters your URL at anytime. Every marketing analytics product considers any visitor who doesn't have a referral source as Direct. A common behavior that gets classified as Direct is traffic from untagged (or improperly tagged) social posts, social ads, or untagged emails. Rather than having its own filter, Direct becomes the catch-all bucket for traffic that does not qualify for any of the other filters.
- Time decay attribution - A multi-touch model that gives more credit to the touchpoints closest to the conversion. It makes the assumption that the closer to the conversion, the more influence it had on the conversion.
- Linear attribution - Linear is the simplest of the multi-touch attribution models. It distributes credit by evenly dividing and granting it to every single touch in the buyer journey.
- Position based attribution - The model is composed of the best features of the linear attribution and time decay models. Position-based attribution allows you to allocate the percentage of a conversion to different channels, based on when the touch occurred (first, last, or in-between). The Position Based attribution is 40/20/40 where 40% of the credit for the conversion goes to the first touch in the date range, the other 40% of the credit for the conversion goes to the last touch and credit for the remaining 20% of touches are split evenly.
- Sales funnel - Also called purchasing funnel, is a consumer focused marketing model which illustrates the theoretical customer journey towards the purchase of a product or service.
transaction.chargeevents but also
product.addToCartevents. You can fetch attribution results using API
- Markov model - This model is one of the most advanced data-driven attribution models. It involves computing the probabilities of transition between different channels in order to find out the probability of conversion when a customer sees your ad in a given channel. To calculate these probabilities, the system uses customer paths that lead to purchase, taking into account channel history order. However, to truly assess the value of each channel, the system calculates the so called “removal effect”. The system estimates how many conversions can be achieved without particular channels and compares them with the total conversion number. As a result, you receive information about the importance for conversion of the deleted channel.
- Shapley model - This data driven model measures the conversion rate of a given channel and compares it with other channels using the Shapley Value concept from cooperative game theory. To make calculations, it uses customer paths which end with conversion as well as those which were just page visits. We compute conversion rates for all possible customer paths, which consist of at least one channel from a given group.
Below you will find a model comparison table that shows data (in this case conversions) according to the options in these fields: channels, primary dimension, secondary dimension and metrics. You can sort and filter the results for better readability. Click the rows in the Medium column to unfold the results for the elements in the whole group.
If you want to compare models, click the Add comparison button and choose the two models that you want to compare. They will be added to the table. Comparison between two models represents the difference between conversions (or revenue) in two models. The system divides the conversion of the first model by the conversion of the second. In other words, the comparison shows how much the conversion of the first model is higher/lower than the conversions of the second model and it is expressed as a percentage of the second model.