Whenever you set up an A/B/n test with multiple variations, it’s important to determine how you want the traffic to be distributed between the variations. The behavior of each traffic allocation option is as follows:
Manual Traffic Allocation
Traffic is distributed between the variations either evenly or according to predefined allocation rates. For example, if you launch a test with four variations, you may decide that all variations should have equal exposure, 25% of traffic each. Alternatively, you can favor certain variations over the other and go for any other combination of allocation rates that amount to 100%, such as 50/20/20/10. Manual allocation is de-facto a standard A/B/n test, and the assumption is that once results are significant, the test administrator will assign solely the best variation to all visitors.
The statistical engine dynamically and automatically allocates traffic to the most appropriate variation, using big data and machine learning algorithms, in order to guarantee optimal performance in real-time. In Dynamic Yield, the algorithm that is primarily at work here is Multi-Armed Bandit (MAB), computing the weight and reallocation of traffic every 30 minutes.