Abstract: Techniques described herein relate to a method for identifying offline accounts for online adoption targeting, including obtaining an account group data set; generating, using the account group data set, an enhanced account group data set comprising the account group data set and a derived data item; obtaining, using a ML model and the enhanced account group data set, a key metric set; performing a clustering analysis using the key metric set and a portion of the enhanced account group data set to obtain account clusters; assigning a weight to a cluster of the account clusters; performing a similarity computation for an offline account of the account group using the key metric set and the portion of the enhanced account group data set to obtain a weighted similarity score; adding the weighted similarity score to a ranked list of weighted similarity scores; and providing the ranked list to an interested entity.

Abstract: A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform: generating linkage scores between nodes at least based on a machine learning model; creating links between the nodes to form connected components based on the linkage scores exceeding a predetermined threshold; generating an actual matching linkage set of the nodes linked in the connected components by using a relaxed blocking criteria; and generating a quality score for the connected components. Other embodiments are disclosed.

Abstract: Systems and methods for using machine learning to determine product offers for individuals are disclosed. According to certain aspects, the systems and methods may determine, using a machine learning model and based on a set of products purchased by a user, a set of digital offers associated with an additional set of products to provide to the user. The user may redeem any of the digital offers, and the systems and methods may use any additional product purchase information to update the machine learning model for use in subsequent analyses.

Abstract: Data clean rooms provided for subscribers to advertising analysis services include data regarding advertising impressions, selections, view or conversion events, and memberships of audience segments, and computing functions or capacities for processing the data in an anonymized fashion. When advertisements are presented to customers, and interactions by customers (e.g., impressions, views, clicks, conversions or others) with goods or services are detected, data regarding the interactions may be aggregated and stored. When queries on behalf of an advertiser are identified, data associated with the queries may be retrieved and stored in a data clean room for processing or analysis. Anonymized responses to the query may be returned to the customer or serve as basis for one or more advertising events.

Abstract: A processor may receive user interaction data of a user for a plurality of electronically-presented offers. The processor may generate a plurality of labels, the generating comprising generating a label for each respective offer according to a comparison of the quality of the user interactions of the respective offer to the frequency of the user interactions of the respective offer. Each label may be a positive label or a negative label. The processor may determine whether the generating produced both positive and negative labels. The processor may select one of a plurality of available ML models, wherein a two-class ML model is chosen in response to determining that the generating produced both positive and negative labels and a one-class ML model is chosen in response to determining that the generating did not produce both positive and negative labels. The selected ML model may be trained and/or may be used to process user profile data and provide recommendations.

Abstract: Systems, devices, and methods are described herein for improving inventory management. As used herein, “inventory” refers to digital space at an inventory providers webpage at which content can be delivered. The disclosed techniques utilize reinforced machine learning and an offline training process to train various models with which a content request corresponding to the inventory can be classified according to historical requests and a selection process identified for the request (e.g., a direct or an indirect selection process). If an indirect selection process is chosen, the content request may be optimized for that process utilizing additional machine learning models trained using reinforced machine learning and the offline training process. The disclosed techniques enable the inventory provider to optimize content selections according to a preferred objective. The training operations are performed offline, in a training system configured to simulate the run time environment.

Abstract: Aspects of the disclosure relate to using synthetic DNA stranding and mutant nucleotide processes to conduct enterprise market volatility predictions. In some embodiments, a computing platform may receive market data from a plurality of lines of business across an enterprise, wherein the market data is received in a raw, uncompressed format. Thereafter, the computing platform may assimilate and preprocess the market data to output vectored market data. The computing platform may perform a synthetic DNA stranding process on the vectored market data to create one or more strands of synthetic DNA market data, and output the one or more strands of synthetic DNA market data to a synthetic DNA client server, wherein the one or more stands of synthetic DNA market data is configured for input in a market volatility prediction model.

Abstract: Systems and methods for managing alternative targeted experimental content are disclosed. A method for managing alternative advertisements may include an offer experience service computer program executed by an electronic device: (1) receiving a query for targeted content to display to a customer on a customer electronic device and an experimental content indicator; (2) based on the experimental content indicator, retrieving an experimental targeted content identifier for the customer from a third-party experimentation platform, wherein the experimental targeted content identifier identifies a variant of targeted content; (3) retrieving experimental targeted content associated with the experimental targeted content identifier from an experimental targeted content database; (4) generating a response to the query for targeted content comprising the experimental targeted content; and (5) returning the response to the customer electronic device.

Abstract: Aspects of the disclosure relate to using synthetic DNA stranding and mutant nucleotide processes to conduct enterprise market volatility predictions. In some embodiments, a computing platform may receive raw market data from a plurality of lines of business of an enterprise organization. Thereafter, the computing platform may preprocess the raw market data to obtain enterprise level market data, execute synthetic DNA stranding of the enterprise level market data to obtain synthetic DNA stranded market data, run the synthetic DNA stranded market data through one or more market volatility models, and compile results from the market volatility models on the synthetic DNA stranded market data. The computing platform may transmit results from the market volatility models on the synthetic DNA stranded market data. The transmitted results may be configured to display a market application interface that includes market volatility forecasting parameters based on results of the market volatility models.

Abstract: Aspects of the disclosure relate to using synthetic DNA stranding and mutant nucleotide processes to conduct enterprise market volatility predictions. In some embodiments, a computing platform may initiate a set of instructions associated with performing an action on a synthetic DNA market data set associated with a plurality of lines of business across an enterprise organization. Thereafter, the computing platform may convert the set of instructions to a mutant nucleotide sequence, and insert the mutant nucleotide sequence into the synthetic DNA market data set. The computing platform may extract, using the mutant nucleotide sequence, target information from the synthetic DNA market data set, and validate the target information to detect one or more anomalies. The computing platform may remove the one or more data anomalies, and subsequently output a validated synthetic DNA market data set to a synthetic DNA client server.

Abstract: A computing device may be configured to provide authorization to a first content source to provide first content to a user device. The computing device may receive a request from the first content source to identify a location of second content to be presented to the user device and respond to the request by providing an address to the first content source. At the provided address, a request for the second content from the user device may be received. When responding to the request, the computing device may retrieve information associated with the user (e.g., user preference information) from the user device. Using this information, the computing device may generate at least one parameter for selecting the second contend and send a response to the user device. The response may include an address for the second content and the at least one parameter for selecting the second content.

Abstract: A real-time survey system can monitor real-time event and interaction data generated as a user interacts with an application. Using the event data in combination with static user attributes, the survey system can identify a subset of microsurveys a user is eligible to receive or participate in. Identifying eligibility can include applying one or more filters based on user attributes as well as detecting a triggering event that signals real-time relevance of the survey to the user's actions. If the user is eligible for multiple surveys, the survey system can select a single survey to send to the user. Surveys can be presented to users directly using the real-time survey system instead of via an alternate delivery method, such as email. After collecting survey data, survey system can automatically analyze survey responses, including by performing machine learning based thematic analysis on freeform text responses.

Abstract: A method and system assists experts associated with an electronic bookkeeping system to increase a rate at which users select to receive the services of the expert. The method and system retain information regarding the selection rates of a plurality of experts, and the profiles of the plurality of experts. The method and system trains an analysis model with a machine learnings process to learn how the attributes in the profiles relate to the selection rates. The method and system then utilizes the analysis model to predict changes to the profile that an expert can make to increase the selection rate of the expert. The method and system outputs recommendation data to the expert recommending one or more changes in the expert's profile that will likely result in an increase in the expert's selection rate.

Abstract: A system and method are disclosed to generate causal inference machine learning models employing statistical background subtraction. Embodiments include a server comprising a processor and memory. Embodiments receive historical sales data for one or more past time periods and corresponding historical data for one or more causal variables. Embodiments deconfound the cause-effect relationship of historical sales data and historical data on the one or more causal variables. Embodiments define one or more sample weights for statistical background subtraction of the historical data and perform statistical background subtraction on the historical data. Embodiments train a first machine learning model to predict an absolute individual causal effect on a considered demand quantity in relation to the one or more causal variables and one or more sample weights.

Abstract: A system and method for creation, distribution and tracking of advertising via electronic networks, enabling creation of advertisements using licensed third-party content and placement of the ads at desired network locations, utilizing an auction of ad spaces based on bids placed by advertisers to have their ads displayed at such locations. When a network user/ad viewer requests an ad by clicking or other action, an auction algorithm executes to select the ad to be displayed from those that bid for display at such ad space location and then the ad is composed and delivered to the ad space location by accessing a relational database storing commands that retrieve, assemble and dispatch the licensed ad content. Usage and display of licensed content on designated ad space is tracked to enable cost-per-use charging for both use of licensed content and ad display at the designated ad space.

Abstract: The present disclosure optimally determines a contact between a user and an advertisement. An advertisement contact determination system according to one aspect of the present disclosure includes a communication unit configured to obtain position information of a device, and a control unit configured to determine that a user of the device has come into contact with an Out Of Home (OOH) advertisement if the OOH advertisement is included in a certain range in a traveling direction of the user based on the position information of the device. The communication unit obtains a log of a certain apparatus, and the control unit determines whether the device exists in vicinity of the certain apparatus in a certain period of time or not and, if the device exists, associates the log of the certain apparatus in the certain period of time with the device.

Abstract: Systems and methods to correlate user behavior patterns within digital environments with psychological attributes of users exhibiting the user behavior patterns are disclosed.

Abstract: This paper presents a practical method for measuring the impact of multiple marketing events on sales, including marketing events that are not traditionally trackable. The technique infers which of several competing media events are likely to have caused a given conversion. The method is tested using hold-out sets, and also a live media experiment for determining whether the method can accurately predict television-generated web conversions.

Abstract: Methods, systems, and media for automated compliance determination of content items are provided.

Abstract: A method for web browser-based distribution of targeted advertising messages is provided. An advertising party registers with a distributor of targeted advertising messages. An advertising campaign for goods targeting user demographic categories chosen by the advertising party is created, with advertising messages being customized for each category and the advertising messages being stored on a web server of the distributor. The advertising party pays the distributor for the advertising campaign. A user registers with the distributor for receiving advertising messages through a web browser and the user providing user demographic data and value account information at registration. The web browser home page of the user is configured with a user-specific URL corresponding to a set of targeted advertising messages according to the user demographic data.