How to Increase Contextual Advertising ROI 2.2x: Eldorado Case Study
We’d like to share a case study from our partners iProspect and Eldorado. To optimize advertising campaigns, the electronics and home appliances retailer Eldorado worked with the iProspect advertising agency. They tested OWOX BI to calculate the probability of conversions and told us about the results.
A question that’s familiar to every business is how to cut spending on contextual advertising while maintaining sales. If you purchase traffic to your website in an advertising system such as Google Ads or Facebook, a huge part of your spending goes to clicks of users who don’t end up putting items in the cart. And even if they do, they don’t always complete the purchase.
The main performance marketing tasks at Eldorado are growing efficiency metrics and reducing contacts with users who are not currently interested in purchasing. We’re constantly looking for new instruments and methods to optimize ad campaigns. Data-driven solutions, in our opinion, are the most promising.
The OWOX BI attribution model uses machine learning technologies to calculate the purchase probability for each website user starting with the first visit. Using these purchase probabilities, companies can determine if it’s worth spending on advertising to a user. Furthermore, the OWOX BI model can calculate the probability of a user’s performing any action.
One of the mandatory tasks of a contextual advertising SEM specialist is segmenting website visitors into various groups depending on actions they perform on the website and the time passed since the last trigger. For example, the number of days since adding an item to the cart without a purchase. Manual analysis of such audiences and adjusting bid calculations takes up a huge part of the work process.
Our goal was to increase the ROI of contextual ad campaigns while saving revenue from completed orders.
To optimize advertising campaigns, we used the OWOX BI machine learning solution that’s trained on:
- historical data on the behavior of website users
- CRM data on redeemed orders
- aggregated and anonymized data from tens of thousands of projects by OWOX clients
What OWOX BI gave us:
- For each website user, the purchase probability is calculated accounting for redeemed orders.
- Probability calculations are updated after each user action or period of inactivity. For example, if a user visits a website and performs a range of actions, they receive X% probability of making a purchase. If they don’t visit the website for four days after that, this probability decreases.
- 10 user segments divided according to purchase probability along a 10-point scale.
To assess the forecast accuracy and the performance of each segment, we analyze how many orders each segment has completed.
At the top of the table is the segment with the highest conversion probability, and at the bottom is the segment with the lowest.
How we implemented OWOX BI to increase ROI
- We started by gathering data about users’ behavior on the website in Google BigQuery with OWOX BI. (It’s also possible to use Google Analytics 360.)
- OWOX analysts trained the attribution model and started regular conversion probability calculations for Eldorado website visitors. Each visitor is assigned a conversion probability. The algorithm accounts for more than 60 parameters, including:
- number of sessions in hits within the conversion window
- actions on the website within a session
- pauses between sessions
- overall number of actions
- session device and operating system
- traffic sources the user had within a conversion window
- number of actions on each page within a session
- timing of a specific session and total time of sessions within a conversion window
Then OWOX BI gathers all this data into one table in Google BigQuery to evaluate the purchase probability for each user.
- Next, we automated the transmission of audience data to our advertising service using an OWOX BI Pipeline.
- Finally, we added audiences to the advertising service.
We conducted the primary A/B test with an equal division of traffic among the examined groups for advertising campaigns we created manually as well as for those we gathered based on a product data feed with the help of an automation service. After the successful experiment, we started the second test on campaigns with dynamic ads.
Gather data according to its efficiency among advertising campaigns, then calculate and adjust bids for audiences:
- Decrease bids for audiences with a low purchase probability (sometimes up to 90%)
- Increase bids for audiences with a high purchase probability
The size of bid adjustments is calculated based on the data gathered about the conversion coefficient of each audience and target ROI. We also considered current ROI of each campaign and audience. For each audience, OWOX BI calculated an appropriate price per click. Based on these calculations, it adjusted the current price to arrive at the target KPI. The adjustments consistently changed based on the results.
For two months, OWOX analysts worked with colleagues from iProspect to conduct two tests. The first lasted a month and a half and included five advertising campaigns with low volumes of traffic. Each of these campaigns was subdivided into two campaigns for A/B testing: one using OWOX BI audiences and one without them.
Campaigns using OWOX audiences showed 1.7 times better results both in terms of ROI and revenue for completed orders. For Eldorado, this was a step in the direction of increased efficiency for advertising investments.
After the first experiment, we checked that this result wasn’t just a one-off. To do that, we ran a three-week test based on campaigns with large volumes of traffic according to the same principle — an equal number of campaigns using OWOX BI audiences and without OWOX BI audiences.
The result of the second test was 2.2 times higher ROI and 2.7 times higher revenue for completed orders in campaigns with OWOX BI audiences.
In both cases, the test group either brought more revenue with the same budget as the control group or brought the same revenue with a lower budget.
Using OWOX BI to predict conversions, we can save time on creating audience segments, all data on website users is processed automatically, and the resulting data is prepared for uploading to an advertising service where it can be used in advertising campaigns to adjust bids and run retargeting.
We consider these test results to be a successful start for further scaling of other performance and brandformance channels.
Experiments with conversion probability calculations proved their efficiency, and the next step is to scale the solution — to use it in all search campaigns, run retargeting by setting different bids depending on conversions in a segment, and apply it in other advertising services such as Facebook, MyTarget, and Google Ads.