Oracle International Corporation

Walmart Apollo, LLC

Qing Zou

Jeffrey Taihana Tuatini

Bradley Harold Sergeant

Arun Ananthanarayanan Tharuvai

Yang Peng

Sai Sri Ram Haridass

Raghu Upadhyayula

A system comprising one or more processors and one or more non-transitory computer-readable media storing computing instructions that cause the one or more processors to perform: training a machine learning model using one or more training features, wherein each training feature of the one or more training features is segmented in a respective group of one or more groups by a respective time period; executing, after training the machine learning model, the machine learning model to generate a forecasting system to predict at least a predicted return on an ad spend (ROAS) value; and providing access to the forecasting system to predict one or more input parameters for an electronic advertising campaign to forecast one or more campaign predictions associated with the electronic advertising campaign. Other embodiments are disclosed herein.

Systems and methods for forecasting campaign parameters using machine learning architectures and techniques

Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform acts of: providing access to a forecasting system that includes a machine learning model configured to forecast one or more campaign predictions associated with an electronic advertising campaign; extracting historical campaign data from one or more databases using a distributed processing system; generating training features for training the machine learning model; executing a training procedure that is configured to train the machine learning model, at least in part, using the training features; and executing, after completion of the training procedure, the machine learning model to forecast a predicted ROAS value or a predicted budget value. Other embodiments are disclosed herein.

Systems for prosecuting Internet messaging campaigns. Two or more data sources are determined where at least one of the data sources comprise demographic attributes corresponding to shared IDs such as recipient IDs. A first join operation is performed over matching instances of the shared IDs in the two or more data sources. The first join operation results in a personalization table comprising rows having at least recipient IDs, respective external addresses, and at least one of the demographic attributes. The personalization table is transformed into a key-value data structure that is published to a caching subsystem. The caching subsystem is used to select a first set of recipients determined without performing a second join operation. Personalized messages to at least some of the first and second set of recipients are formed using the message template and the key-value data structures.

Message personalization over multiple internet messaging campaigns

Systems and methods are provided for high-performance data processing. A policy is received that indicates a cutoff time. A request is processed to return the data item from the cache if the cutoff time is satisfied for the data item or return the data item from the database or not at all if the cutoff time is not satisfied for the data item. If the data item retrieved from the database, metadata associated with the data item is stored to indicate when the data item was last marked as in sync with the database.

Growing community of inventors

Sunnyvale, CA, United States of America

Qing Zou