The core optimization of Adspert is based on the market curve theory, meaning modeling the market by all available observations. This especially includes the estimation of market curves to determine volume (clicks) and competitive pressure (effective CPC) depending on the maximum CPC.
In addition, Adspert estimates the conversion rate, and in case of dynamic shopping basket values also the conversion value, by using information inheritance. With the help of ad scheduling bid adjustments, Adspert optimizes seasonal fluctuations (weekday and time effects). Furthermore, Adspert models a possible conversion delay.
Adspert also supports for every platform the bid adjustments. For instance, adspert can adjust bid adjustments for device, demographics, location, ad scheduling, audience.
The core algorithm of Adspert relies on several heuristics of the portfolio theory, i.a. inheritance algorithms.
Dynamic consideration of time period
Adspert uses all the historical data of your account up to several years. In fact, there is no predefined evaluation of certain periods but Adspert decides dynamically on the basis of how relevant is the data. For accounts with a low amount of conversions, Adspert considers a large time range. By contrast, if there are more data and conversions, Adspert uses the most recent data.
Adspert uses native conversion from the platform. If you track your conversions with a 3rd party tool, for instance, Google Analytics, you need to import them as describe here:
Adspert updates your data and your bids every day at 3 am local time.
Bids for new keywords, ad groups and campaigns
Adspert can determine the optimum bid with a low amount of data. For new keywords, ad groups and campaigns or for those already existing but having few data, Adspert inherit information from the rest of your account. For instance, if a keyword has no clicks, it is impossible to determine how well it converts. Thanks to its AI algorithm, Adspert is able to estimate how well this keyword would convert based on the other keyword of your account by comparing it with same match type keywords or keywords with the same word.
How often should I change my goal
When you set a new goal, you should give some time to Adspert to learn. Usually Adspert needs a few days to adjust itself to a new goal. Moreover, you should consider the conversion delay of your account.