Optimization Calculator in Voluum: Which Entity Converts More Likely
Do you have at least one campaign funnel up and running with a data sample of registered visits and conversions? If yes, Voluum gives you an opportunity to take a closer look at your data and incorporate probabilistic calculations based on a Bayesian approach. Why? Because sometimes business decisions are not so obvious and you might want to get some statistical indications to optimize your campaigns at the right time in the right direction.
You might already know these questions and ask yourself: should I pause the offer now? Or maybe would it be better to change weight values in the campaign funnel to optimize the traffic distribution?
Voluum Optimization calculator has been developed to help you to answer those types of questions by presenting probabilities of finding best entities within a given traffic distribution.
Optimization calculations in Voluum take the number of conversions and the number of visits to calculate which entities might bring you the highest estimated number of conversions defined within a 95% chance. In addition, likelihood values in
In the above table, you can find the estimated conversion rate for different entities (browsers) for a single offer in one campaign funnel. The range of the conversion rate for each browser is defined within the 95% credible interval. Those are the estimated values where their widths strongly depend on how much data was gathered before calculating statistical values. To predict the estimated conversion rate the more data, the better. In addition, the Bayesian model allows calculating the likelihood of being best as well as ROI and EPV. From a business perspective, this might give you some insight how to adjust the weight values in the campaign configuration:
The Optimization calculator in Voluum might be a very helpful tool in terms of predicting which entity converts more likely than others, however you should take into account the following points:
Contact us
You might already know these questions and ask yourself: should I pause the offer now? Or maybe would it be better to change weight values in the campaign funnel to optimize the traffic distribution?
Voluum Optimization calculator has been developed to help you to answer those types of questions by presenting probabilities of finding best entities within a given traffic distribution.
Optimization calculations in Voluum take the number of conversions and the number of visits to calculate which entities might bring you the highest estimated number of conversions defined within a 95% chance. In addition, likelihood values in
the Bayesian statistics table indicate how to distribute weights among displayed entities to get the best conversion rate within your campaign funnel. Y
ou can also find such numbers as estimated Return of investment (ROI) or Earnings per visitor (EPV), where both numbers are calculated based on the estimated conversion rate (CVR).In the above table, you can find the estimated conversion rate for different entities (browsers) for a single offer in one campaign funnel. The range of the conversion rate for each browser is defined within the 95% credible interval. Those are the estimated values where their widths strongly depend on how much data was gathered before calculating statistical values. To predict the estimated conversion rate the more data, the better. In addition, the Bayesian model allows calculating the likelihood of being best as well as ROI and EPV. From a business perspective, this might give you some insight how to adjust the weight values in the campaign configuration:
 For example, if you have one offer with a defined rule for the Opera browser, you might provide 27.35 % value as a Weight value (%) for this particular offer.
 If you would like to adjust another browser entity, for example Baidu Spark, the best way would be to duplicate the offer in the campaign configuration and set up the rule for Baidu Spark with the adequate Weight value (6.72 %).
The Optimization calculator in Voluum might be a very helpful tool in terms of predicting which entity converts more likely than others, however you should take into account the following points:
1. In the Voluum platform at least one active campaign should be running where there are samples of data with visits and conversions; the more registered tracking events, the better; you need to keep in mind that this is a statistical approach where more data will generate more adequate estimations.
2. You are familiar with the Voluum reporting for the campaign funnel.
3. The Bayesian statistical estimations can shed some light what can be expected in the future, but the estimations cannot be taken for granted.
4. Voluum reports cannot differentiate a display of data for the same offer added to different paths in one campaign. Thus, some results such as offer conversions cannot be split into single samples of data for only one path.
5. While comparing the likelihoods of ROI and EPV, you need to keep in mind that the estimations are calculated within the average payout for a given time range. If the payout is changing dynamically in the time range, the average value is taken.
6. It is highly recommended to take a look at a timestamp of visits and corresponding conversions registered for your campaign funnel in Voluum. This allows you to find an average time range between recorded tracking events. It is worth comparing estimations for this time range as well as verify how they might change in a longterm period what enables you to visualize how the data varies on a timely basis.

If you wonder how Voluum Optimization calculator can be applied in a reallife scenario, go to the Optimization Calculator in Voluum: Empowering Conversion Rate of Offers guide. 
Frequently Asked Questions:
Have more questions about the Optimization calculator? You might find the answer below:
 Is there any limit of entities that can be compared and analyzed?
Yes, there is. You can select a maximum of 20 entities in the report. For example, if you want to compare in which browsers a display of the ad is the most successful, you can select Browsers option in the report. Voluum collects information about a wide range of browsers and in this case you might analyze up to 20 of them in one Bayesian diagram.
 Why should I select a visit timestamp in Voluum settings while analyzing data?
Reporting by a visit timestamp might be crucial for analyzing data in a shortterm period, particularly when your conversions are registered some time after the visit.
Let’s take a look at the example: One day 10 000 visit were registered. The next day there were only 100 visits, but 1000 conversions were registered from the previous day. In that scenario, if you had reporting by conversion postback enabled and were checking the data selecting the Yesterday option from the time range in a Campaign report, you would see 10 000 visits and no conversions. You might conclude that the offers did not convert at all. If you changed the time range to Today, you would have 100 and 1000 conversions what might indicate that the conversion rate would be 100%.
In the same scenario, with visit timestamp reporting enabled, if you check the data within the Yesterday time range, you will see 10 000 visits and 1000 conversions, so the data you can act upon.
Contact us