The disclosed embodiments provide a system for evaluating a performance of a mobile application. During operation, the system obtains, for a statistical model used in a quasi-experimental design, a first predicted outcome produced from a first set of data that is collected from two substantially identical versions of a mobile application. Next, the system uses the first predicted outcome to assess a bias of the statistical model. The system then improves an accuracy of the statistical model by using the assessed bias to normalize a second predicted outcome of the statistical model.

The presently disclosed subject matter includes a computer-implemented method and system of automatically generating quality scores in a content distribution system; the content distribution system enables the presentation of (digital) content on a display device of computer devices that enable users to engage with the presented content. The quality scores enable to detect and mitigate intent-less (e.g. fraudulent or low quality) user engagements with the user interface in the content distribution system. According to one example, the presently disclosed subject matter enables identification and mitigation of cyber theft in the form of engagement fraud in the content distribution system.

Systems and methods for providing an artificial intelligence (AI) marketing campaign optimization platform or system that automates and optimizes bidding, audience matching, and retargeting of marketing campaigns to meet business goals on digital platforms. The campaign optimization system may autonomously plan and manage advertising campaigns for a plurality of organizations on one or more digital platforms. The campaign optimization system may provide autonomous bidding, autonomous audience matching, and autonomous creative optimization. The autonomous bidding features allow an organization (e.g., company) to target their highest value customers to reach their growth targets or other goals. A bidding automation tool optimizes every dollar spent on advertisements placed on digital platforms to ensure organizations are paying the optimum price for the optimum audience. An audience matching tool autonomously reveals new interest and audience groups, and identifies new keyword groups.

A campaign management system may include a data collection subsystem to collect and store data from different sources that may be related to different marketing channels. The system may also include a map generation subsystem to generate a marketing campaign map that includes a visual representation of performance of the marketing channels. A performance metric adjustment factor may be determined for one or more performance metrics to determine an actual value performance metric for each metric. The actual value performance metrics may be aggregated and compared to benchmarks to generate a visual representation of the entire campaign performance across the marketing channels.

The present disclosure is related to systems and methods for determining an optimal strategy. The method includes classify one or more users into a first user group and a second user group using an optimization model, wherein the first user group and the second user group correspond to two strategies, respectively. The method also includes obtain behavior data from terminals of the one or more users in the first user group and the second user group. The method further includes determine a first value of a parameter regarding the first user group and a second value of the parameter regarding the second user group using the optimization model. The method further includes determine a strategy based on the first value and the second value.

Data transformation offloading in an artificial intelligence infrastructure that includes one or more storage systems and one or more graphical processing unit (GPU) servers, including: storing, within the storage system, a dataset; identifying, in dependence upon one or more machine learning models to be executed on the GPU servers, one or more transformations to apply to the dataset; and generating, by the storage system in dependence upon the one or more transformations, a transformed dataset.

Data transformation caching in an artificial intelligence infrastructure that includes one or more storage systems and one or more graphical processing unit (GPU) servers, including: identifying, in dependence upon one or more machine learning models to be executed on the GPU servers, one or more transformations to apply to a dataset; generating, in dependence upon the one or more transformations, a transformed dataset; storing, within one or more of the storage systems, the transformed dataset; receiving a plurality of requests to transmit the transformed dataset to one or more of the GPU servers; and responsive to each request, transmitting, from the one or more storage systems to the one or more GPU servers without re-performing the one or more transformations on the dataset, the transformed dataset.

Bayesian A/B testing tools and methods for email campaigns are provided. The Bayesian methods and tools disclosed herein determine which version of an email is better than another to enable accurate Bayesian A/B testing on the emails.

Data transformation offloading in an artificial intelligence infrastructure that includes one or more storage systems and one or more graphical processing unit (GPU) servers, including: storing, within the storage system, a dataset; identifying, in dependence upon one or more machine learning models to be executed on the GPU servers, one or more transformations to apply to the dataset; and generating, by the storage system in dependence upon the one or more transformations, a transformed dataset.

Data transformation caching in an artificial intelligence infrastructure that includes one or more storage systems and one or more graphical processing unit (GPU) servers, including: identifying, in dependence upon one or more machine learning models to be executed on the GPU servers, one or more transformations to apply to a dataset; generating, in dependence upon the one or more transformations, a transformed dataset; storing, within one or more of the storage systems, the transformed dataset; receiving a plurality of requests to transmit the transformed dataset to one or more of the GPU servers; and responsive to each request, transmitting, from the one or more storage systems to the one or more GPU servers without re-performing the one or more transformations on the dataset, the transformed dataset.