There are disclosed marketing analytics apparatus and processes. There is a data store of interactions between a plurality of customers and one or more vendors over a plurality of channels. Pathing and attribution of these interactions may be obtained as marketing analytics. Pathing may be obtained in part with a match programming statement which identifies all of the paths in the data store matching criteria specified in the match programming statement. Pathing may be obtained in part with a split programming statement which splits all of the journeys in the data store into paths. After pathing, an attribution pathing statement may be used to attribute conversions to other events.

Presented are embodiments of methods and systems that provide for Internet advertisement pricing and placement to be variably based on the advertisement's performance within a given category of Internet media, while at the same time achieving predictable delivery and pricing for both advertisers and publishers. Techniques are presented where an advertiser's online campaign will be pre-empted only for underperformance on its own merits, and not for its relative performance or price versus other advertisers. Further, techniques are presented for allowing publishers of advertisements to realize increased revenue from their high value media while using tag passbacks to secure a minimum reserve pricing of their choice.

There are disclosed marketing analytics apparatus and processes. There is a data store of interactions between a plurality of customers and one or more vendors over a plurality of channels. Pathing and attribution of these interactions may be obtained as marketing analytics. Pathing may be obtained in part with a match programming statement which identifies all of the paths in the data store matching criteria specified in the match programming statement. Pathing may be obtained in part with a split programming statement which splits all of the journeys in the data store into paths. After pathing, an attribution pathing statement may be used to attribute conversions to other events.

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.

The effectiveness of advertisements with respect to a group of panelists is measured. Based on the results of such analysis, advertisements and/or variants thereof are selected for presentation to consumers. Effectiveness of advertisements is measured, in one embodiment, by detecting exposure to advertisements, and then monitoring panelist behavior following exposure to an advertisement. In one embodiment, the group of panelists is a representative sample of a larger population, so that observations of panelist behavior can be used as a basis for making decisions regarding presentation of advertisements to a larger audience having characteristics similar to those of the panelists.

Once the relative effectiveness for various audiences has been determined, advertisements can be selected for presentation to individual consumers or to groups of consumers, so as to maximize effectiveness. In one embodiment, such analysis and selection is performed substantially in real-time.

A method for identifying causal impact of introducing digital channels and enhancements, the method comprising receiving data corresponding to online interactions with consumers based on online monitoring of an advertiser, identifying digital channels associated with the online interactions with consumers, identifying online metrics for assessment associated with the digital channels, determining a Bayesian time-series model for the data based on the identified online metrics, analyzing causality impact of an intervention for one or more paid digital and organic digital channels using the Bayesian time-series model, identifying optimal pre- and post-intervention assessment time periods based on causality impact of the one or more paid digital and organic digital channels that is statistically significant, and generating a report including a causality assessment of the online metrics for the one or more paid digital and organic digital channels by period based on the causality impact during the optimal pre- and post-intervention time periods.

Image-based features may be significantly correlated with click-through rates of images that depict a product, which may provide a more formal basis for the informal notion that good quality images will result in better click-through rates, as compared to poor quality images. Accordingly, an image assessment machine is configured to analyze image-based features to improve click-through rates for shopping search applications (e.g., a product search engine). Moreover, the image assessment machine may rank search results based on image quality factors and may notify sellers about low quality images. This may have the effect of improving the brand value for an online shopping website and accordingly have a positive long-term impact on the online shopping website.

In some examples, a computing device includes at least one processor and at least one module, operable by the at least one processor to receive, from a client device of a user, a request for one or more advertisements to display at the client device with a set of messages. The set of messages is associated with the user in a social network messaging service. The at least one module may be further operable to determine a probability that the user will select a candidate advertisement using a machine learning model based on point-wise learning and pair-wise learning. The at least one module may be further operable to determine, based on the probability that the user will select the candidate advertisement, a candidate score for the candidate advertisement, determine that the candidate score satisfies a threshold, and send, for display at the client device, the candidate advertisement.

A method includes receiving, from a computing device, a request for content from a content provider and determining one or more experiment variations of the requested content that the computing device is assigned to based, at least in part, on the request. The method further includes generating, by a processing device, code indicating the determined one or more experiment variations and inserting the code into executable code corresponding to the requested content. The executable code is transmitted to the browser.