A computer system including a processor in communication with a memory and a database may be provided. The processor may be programmed to: (i) execute a query on the database including a list of user identifiers associated with a plurality of users, (ii) receive license data associated with the user identifiers including a list of licenses and respective license renewal data associated with each user, (iii) determine, from the license data, that one or more licenses of a group of users is in a renewal period, (iv) notify each user of the group of users of the one or more licenses in the renewal period, (v) pre-populate a license renewal application for the one or more licenses in the renewal period the group of users, (vi) transmit the pre-populated application to be approved by the group of users, and (vii) receive the approved pre-populated application from the group of users.

Methods, systems, and apparatuses for user segmentation and analysis are described herein. An analytics subsystem may use a plurality of activity data to generate a plurality of user profiles, corresponding user interest clouds for each user device of a plurality of user devices, and a geographic interest cloud associated with a particular client identifier. In another example embodiment, the analytics subsystem may generate an industry interest cloud associated with the particular client identifier. For example, the industry interest cloud may indicate interests of users associated with a particular industry. In a further example embodiment, the analytics subsystem may determine (e.g., identify) a plurality of clusters of users. For example, each of the plurality of clusters of users may comprise one or more user profiles having common interests, common geographic location, common industry affiliation, a combination thereof, and/or the like.

Implementations generate links between local merchants and community programs. Merchants provide incentives to customers in relation to community programs. Implementations also include online and offline customer transactions with merchants that make use of incentives. Implementation pertain to customers that view a broadcast of content that is interleaved with a merchant's advertisement and analytic reporting. Matches between transactions with a merchant and a customer that view a broadcast of content that is interleaved with the merchant's advertisement may be identified by the system, and a level of certainty that the match is accurate may be determined. These implementations can be operated by an alliance of entities that cooperate in order to facilitate, and benefit from, transactions between customers and merchants, where the customer is incented to conduct the transaction with the merchant by the merchant's agreement to make a donation to an entity of the customer's choice.

A computing device for predicting an expected loss for a set of claim transactions is provided. The computing device predicts, at a first machine learning model, a claim frequency of the set of claim transactions over a given time period and trained using historical frequency data and based on a segment type defining a type of claim, each type of segment having peril types. The computing device also predicts, at a second machine learning model, claim severity of the set of claim transactions during the given time period, the second machine learning model trained using historical severity data and based on the segment type and the corresponding peril types. The computing device then determines the expected loss for the set of claim transactions over the given time period by applying a product of prediction of the first machine learning model and the second machine learning model.

A method for detecting collusive transaction fraud includes: generating a merchant baseline including a transaction data baseline and a time series baseline; extracting time series data of the first merchant system; generating a first score and second score with a deep learning model; generating a first merchant risk score of the first merchant system based on the first and second scores; in response to determining that the first merchant risk score satisfies the threshold, determining a plurality of related entities related to the first merchant system; and classifying the first merchant system and at least one related entity of the plurality of related entities in a first group risk class based on at least one risk score of the at least one related entity.

A media level of each Self-Service Terminal (SST) within a customized group of SSTs are managed in real time based on a current media level and a predicted optimal media level for each SST over a given period of time. During management, depositors are proactively steered away from media heavy SSTs to media deficient SSTs within the group. Any given SST of the group may have deposits temporarily disabled based on real-time instruction. Depositors that are being redirected may be incentivized to encourage the depositors to deposit at the cash deficient SSTs of the group.

The present disclosure provides a computer-implemented method and system for running high performance marketing campaigns for granular-level segments of users in real-time. The computer-implemented method and system corresponds to a user segmentation system. The user segmentation system receives a first set of data associated with a plurality of users. The user segmentation system fetches a second set of data. The user segmentation system obtains a third set of data. The user segmentation system analyzes the first set of data, the second set of data and the third set of data. The user segmentation system enables segmentation of the plurality of users. The user segmentation system assigns one or more segment goals. The user segmentation system creates a plurality of micro-segments. The user segmentation system triggers initialization of one or more marketing campaigns. The user segmentation system predicts performance of each of the one or more marketing campaigns.

Systems and methods for features engineering, in which internal and external signals are received and fused. The fusing is based on meta-data of each of the one or more internal signals and each of the one or more external signals. A set of features is generated based on one or more valid combinations that match a transformation input, the transformation forming part of library of transformations. Finally, a set of one or more features is selected from the plurality of features, based on a predictive strength of each feature. The set of selected features can be used to train and select a machine learning model.

A method of displaying a symbol representative of changes in price during a time period, the method includes receiving, for each intra-time period of a plurality of intra-time periods in the time period, intra-time price data including an intra-time open price, an intra-time high price, an intra-time low price, and an intra-time close price corresponding to the intra-time period, determining, from the received intra-time price data for the plurality of intra-time periods, an open price, which is an intra-time open price of an initial intra-time period of the plurality of intra-time periods, determining, from the intra-time high price of each of the plurality of intra-time periods, a total-higher-high-price counter value, determining, from the intra-time close price of each of the plurality of intra-time periods compared to the open price, a total-above-open-price counter value, and generating and displaying, by a charting engine, the symbol, which illustrates a relationship between the total-higher-high price counter value and the total-above-open-price counter value.

A computerized method of automatically generating a recommendation output includes training a machine learning model with historical feature vector inputs to generate a recommendation output, generating a set of inputs specific to an entity, and transforming the set of inputs into a profile data structure. The profile data structure includes multiple attributes. The transforming includes, for each attribute, assigning a preference according to the set of inputs. The method includes obtaining structured supplemental data associated with the entity. The method includes obtaining a set of option identifiers by filtering the option identifiers according to option criteria specific to the entity. The method includes creating a feature vector input according to the set of option identifiers, the structured supplemental data, and the assigned preferences of the profile data structure. The method includes processing, by the machine learning model, the feature vector input to generate the recommendation output.