Abstract: A processing apparatus is disclosed for representing cognitively biased selection behavior of a consumer as a learnable model with high prediction accuracy taking into account even feature values of a product and the consumer. The processing apparatus generates a selection model obtained by modeling selection behavior of a selection entity that selects at least one choice out of presented input choices. The processing apparatus includes an acquiring unit to acquire training data including a plurality of input feature vectors that indicate features of a plurality of the choices presented to the selection entity and an output feature vector that indicates a feature of an output choice. The processing apparatus further includes an input combining unit to combine the plurality of input vectors to generate an input combined vector, and a learning processing unit to learn a selection model on the basis of the input combined vector and the output vector.

Abstract: A method of enhancing a user interface of a network-based publication system based on seasonality scores associated with items featured in listings posted on the network-based publication system is disclosed. Seasonality data is generated for each of the items. The generating of the seasonality data includes identifying a season corresponding to transaction data pertaining to each of the items and storing the seasonality data in conjunction with the transaction data in a database. The season pertains to a selected user action that is to result in a presentation of a user interface on a device of the user. Seasonality scores are calculated and associated with the items featured in a subset of the listings that are candidates for inclusion in the presentation of the user interface. Relevancy scores are adjusted for each of the candidates and are incorporated into a presentation of the listings in the user interface.

Abstract: Systems and methods are provided for electronic stimulus evaluation through one or more signals. The one or more signals protect underlying raw data relating to behavior, including purchase behavior and location-based behavior. A server platform in network communication with at least one signal buyer computer and at least one signal provider computer facilitates creation of the one or more signals. Anonymized object identifiers are used to identify objects or consumers associated with behavior data and exposure to the electronic stimulus. The server platform provides optimization analytics for the stimulus based on the one or more signals, which include measurement signals, behavior signals, and lift signals.

Abstract: A computer-implemented method includes: obtaining first environmental factor data of a first time period and first historical payment data of a target Internet of Things (IoT) device in the first time period, in which the first time period is before a first time point; obtaining second environmental factor data of a second time period that is after the first time point; and obtaining a prediction, using a neural network model, operating on at least one computing device, of an estimated statistical distribution of one or more users who execute transactions using the target IoT device in the second time period, in which the first environmental factor data, the first historical payment data, and the second environment factor data are inputs to the neural network model.

Abstract: Systems and methods for identifying a selected set of users of a social networking service which, upon issuing a notice regarding a re-post activity of an item of content, will likely result in heightened user interaction with the service. Upon receiving a notice of a re-post action by a first user, the social networking service identifies a first set of users of the service that have posted that item of content. Scores are associated with the users of the first set of users, the scores indicating a likelihood of a user that, if notified of the re-post action of the first user, will result in heightened user interaction with the social networking service. A subset of users of the first set of users are identified according to their associated scores and a notice of the re-post action by the first user is sent to the users of this subset of users.

Abstract: In general, embodiments of the present invention provide systems, methods and computer readable media for a universal relevance service framework for ranking and personalizing items.

Abstract: Described herein are systems and methods for an entity ranking system. In one embodiment, a computing system is configured to interface with one or more domains to identify a set of entities. The computing system can ascertain a first set of data components for each entity, normalize each of the first set of data components for each entity, and detect a failure to ascertain a second set of data components. The computing system can compute a statistical probability for a possible set of values for each data component of the second set based on the ascertained first set of data components. The computing system can rank each entity based on a derived quantile. The computing system can generate a graphical user interface including a visualization of the ranking of each entity, which can be rendered on a display of the at least one user computing devices.

Abstract: Methods and systems for analyzing trends in sale data for a retail enterprise are described. A retail analysis platform includes a data extraction and analysis automation platform, a feature transformation application, a modeling environment, and a dashboard application. Analysis begins with recent sales data. Baseline sales for the retail enterprise are removed from the recent sales data. Then the effects of seasonality and local disruptions are removed by utilizing different weights of driver data for each item category and store location. This top down approach results in more accurate reporting of sales trends and attribution of deviations from demand forecasts to particular drivers. The analysis can be scheduled to automatically initiate on a regular basis.

Abstract: A method includes identifying one or more objects in one or more images of real-world scenes associated with a user, adding the identified one or more objects to a list of real-world objects associated with the user, assigning each object in the list of real-world objects to an object class based on object recognition, and providing a notification to the user that a content item has been associated with an object class assigned to one of the objects on the list of real-world objects associated with the user. A computer readable storage medium stores one or more computer programs, and an apparatus includes a processor-based device.

Abstract: Methods and systems for forecasting demand for a plurality of items are provided. In particular, the demand forecasting system and methods described herein are useful for predicting demand of products in a retail context. Forecast models are built and used to score incoming sales data to predict future demand for items. Forecast models are validated by evaluating actual demand against predicted demand and using that information to inform how future ensemble forecast will be generated. Forecasts may be broken down into smaller components to satisfy a variety of requests for data from client applications.

Abstract: A microservices-management system intercepts a request for a cloud-based microservice sent by a microservices-architecture application. The system selects an optimal cloud-service provider from a group of candidate providers capable of delivering the microservice and then forwards the request to the optimal provider. The optimal provider is selected by drawing cognitive inferences from stored blockchain records that each describe a characteristic of a previous delivery of the requested service. Each record is generated by one of the candidate providers when delivering an instance of the microservice, regardless of whether the provider is in a trusted relationship with the application owner. The providers are barred by blockchain's intrinsic security features from altering or deleting previously stored blockchain records. Upon delivery of the service, the system compares the actual quality or cost of the delivery with predicted values in order to learn how to more effectively select optimal providers.

Abstract: A computing system comprising a database of users, a database of garments, and a database of mappings, wherein a mapping maps one or more users of the database of users to one or more garments of the database of garments and wherein each mapping includes a weight for its corresponding user-garment pair.

Abstract: A method is provided for role-oriented risk analysis in a contract. The method generates, using deep semantic association analysis, a report specifying a set of potential risks relating to explicit and hidden roles of contract parties. The generating step categorizes input statements of the contract into respective obligation/right pairs according to a deep semantic association distribution thereof. Each pair includes a respective obligation and a respective right. The generating step detects deep semantic differences between the respective pairs and a set of reference obligation/right pairs. The generating step identifies the explicit and hidden roles of the involved parties in the respective obligations/rights pairs according to domain-specific use scenarios and multidimensional local and global context clues in the contract. The generating step identifies the set of potential risks by applying a deep semantic role-oriented risk entailment model to the deep semantic differences.

Abstract: Techniques are disclosed herein for selecting a predictive model to perform on a set of hierarchical data. A selection of first time series data representing activity observed in a current period in a first hierarchy is received. Second time series data representing activity observed in a prior period in the first hierarchy is retrieved. Predictive models are performed using the second time series data as input, where each predictive model generates statistical outcomes for the current period. A score is generated in each of the plurality of predictive models based on a comparison of the statistical outcomes with the first time series data. Each of the predictive models is ranked based on the generated scores.

Abstract: A hypergraph is constructed based on historical shopping cart data. A node of the hypergraph corresponds to a shopping basket, and a hyperedge of the hypergraph corresponds to a unique product, the hyperedge connecting all nodes of the hypergraph representing baskets containing the unique product. A hypergraph partition algorithm identifies a cluster of shopping baskets represented in the hypergraph and determined to be similar to a given basket. Based on the cluster of shopping baskets a dual-level return prediction is performed. The dual-level return prediction includes predicting whether the given basket will be returned, and based on predicting that the given basket will be returned, predicting a probability that a product in the given basket will be returned. Based on predicting that the given basket will be returned, an ameliorative action is performed to reduce the probability.

Abstract: A method for predictively updating one or more user parameters associated with a user of a learning system includes predicting, based on the one or more user parameters, a predicted activity of the user, receiving an actual activity of the user, comparing the predicted activity to the actual activity, and updating the one or more user parameters in response to determining that the predicted activity does not match the actual activity. The method may further include scheduling one or more learning interactions based on the one or more updated learning parameters, where the scheduling includes selecting at least one of a timing of the one or more learning interactions or a type of the one or more learning interactions.

Abstract: Methods, apparatus, and processor-readable storage media for dynamically determining procurement user types are provided herein. An example computer-implemented method includes extracting data, from multiple data sources associated with multiple procurement users, pertaining to interactions between the multiple procurement users and one or more procurement destinations; dynamically updating, based on an application of one or more machine learning algorithms to the extracted data, one or more existing procurement user types; dynamically creating, based on the application of the one or more machine learning algorithms to the extracted data, one or more new procurement user types; and outputting, via at least one user portal, the one or more updated procurement user types and the one or more new procurement user types.

Abstract: Embodiments of the present invention provide a system, method and computer program product for forecasting a time series based on actuals and a plan. A method comprises generating a first and a second sequence of segments that rise and fall alternately based on a first and a second sequence of data values over time, respectively. The first and second sequence of data values represent actual data for an ongoing project and estimated data for a planned project, respectively. The method further comprises aligning at least one segment of the second sequence of segments with at least one segment of the first sequence of segments, and adjusting the estimated data by replacing at least one segment of the second sequence of segments with a scaled version of at least one corresponding aligned segment of the first sequence of segments. The scaled version maintains an estimated total for the planned project.

Abstract: A computer implemented method of pre-emptively blocking an electronic communication is provided. The computer implemented method includes inputting an electronic communication history, wherein the electronic communication history includes a plurality of electronic communications and a set of corresponding recipients for each of the plurality of electronic communications. The computer implemented method further includes normalizing the plurality of electronic communications, and extracting a topic from each of the plurality of electronic communications. The computer implemented method further includes clustering the plurality of electronic communications according to the extracted topics, and digesting the plurality of electronic communication to form a positive learning data set and a negative learning data set to train a neural network.

Abstract: A processing device selects a population of persons and measures sales metrics from the population over a time period and measures an advertising weight over the time period. The processing device determines an effect that the advertising weight has on the sales metrics and additionally calculates values for a degree of targetedness for the advertisement to the population of persons. The processing device determines an effect that the degree of targetedness has on the sales metrics and generates a multi-dimensional model that measures the combined effects of the advertising weight and the degree of targetedness on the sales metrics.

Abstract: Input time series data of a particular time length may be received, and pre-processed to obtain processed time series data. The processed time series data may then be decomposed into a plurality of pieces of time series data of the particular time length at different levels, and a detection of whether a piece of time series data at a particular level includes a periodic component candidate in a frequency domain may be performed. In response to detecting that the piece of time series data at the particular level includes the periodic component candidate in the frequency domain, a validation may be performed to determine whether the periodic component candidate in the piece of time series data at the particular level is a true periodic component of the input time series data in a time domain.

Abstract: Intelligent management of authorization requests are described. A server of a payment processing service can receive an authorization request to authorize a payment instrument for a predicted cost of a transaction between a first user and a second user. The server can compare the predicted cost of the transaction with an available balance of the payment instrument and determine that the available balance is less than the predicted cost of the transaction. Based on determining that the available balance is less than the predicted cost of the transaction, the server can determine that the payment instrument is not authorized for the predicted cost of the transaction and can authorize the transaction instead of declining the transaction based at least in part on a prediction of the actual cost of the transaction.

Abstract: Approaches provide for or automatically optimizing sponsored content campaigns for a sponsored content provider for a particular consumption category across different content publisher networks. For example, performance data for sponsored content campaigns can be used to train a model for a consumption category to determine allocation scores that quantify a relationship between target audiences and the consumption category. In response to a content placement request to initiate a sponsored content campaign associated with the consumption category, allocation scores can be determined and used to dynamically determine an allocation of resources to appropriate audiences or segments based at least in part upon the trained optimization model. A campaign template can be generated that includes the target audience(s), sponsored content, and respective budget allocation, and any other information for the campaign.

Abstract: Embodiments are described for a system and method for providing a list of current offers from retailers to a user operating a mobile client device. Aspects of the method comprise analyzing a transaction history of the user to identify a vendor who has transacted with the user; determining a present geographic location of the user based on a location of the mobile client device; determining a location of the vendor proximate the user based on the transaction history and the present geographic location of the user; searching for a current promotion offered by the vendor; and facilitating the serving of the current promotion to the user through the mobile client device.

Abstract: A system for managing fare collection in a public transit network may include a fare collection system and a fare management system. The fare collection may collect fare information from passengers boarding or getting off a vehicle. The fare management system may use the received fare information to determine a fare return series over a period of time, which includes multiple fare returns. The fare management system may use a hierarchical cluster method to cluster multiple fare returns into one or more clusters represented in a dendrogram, apply a “silhouette” method to the dendrogram and obtain an optimal clustering. The system may further output a graphic representation, such as a trend line, for each of the clusters over a time period. Based on the clustering results, the system may also deploy a revised fare class schedule or transit system schedule to the fare collection system.

Abstract: There is provided a method for managing file transmission. A file transmission method includes receiving, by a file transmission system, a request for transmitting a file to a reception side from a transmission side, setting transmission paths for transmitting the file via data centers present between the transmission side and the reception side, determining a splitting reference used for splitting the file into a plurality of fragments for the respective transmission paths, and individually transmitting the file fragments split according to the splitting reference along the transmission paths. Since files are split into a plurality of fragments and the fragments are simultaneously transmitted to several networks in a distributed manner, security may be strengthened and a bandwidth may be temporarily expanded, remarkably enhancing a transfer rate.

Abstract: Aspects of the disclosure relate to transforming event data associated with an entity using a multicomputer platform and directing a client computing device to perform a determined action based on a detected event characteristic of the event data and a detected current event. With some embodiments, an event tracking server detects the current event from sensed data provided by a sensed data server and identifies a correlation measure between the detected event characteristic and the detected current event. The event tracking server may direct one or more client computing devices to perform one or more actions related to an entity based on the correlation measure.

Abstract: Embodiments of the invention are directed to a system, method, and computer program product for resource correlation based on resource usage. The system first determines a quantity of graphical prompts capable of being displayed within the area of a display. The system determines, based on the quantity of graphical prompts, a quantity of resource allocation offers. The system generates a quantity of graphical prompts based on the quantity of resource allocation offers.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for personalizing offers are provided. One of the methods includes: collecting response data comprising one or more offers made to each of a plurality of users of a platform and one or more corresponding responses, wherein the one or more offers are from a group of offer choices; creating a training dataset comprising the collected response data and one or more features associated with each of the plurality of users; training a machine learning model using the training dataset, wherein the trained machine learning model is configured to predict the plurality of users' responses to future offers; obtaining a plurality of projected profits for the platform using the trained machine learning model, wherein each of the plurality of projected profits corresponds to making one of the group of the predetermined offers to one of the plurality of users.

Abstract: A system predicts a value estimate for a user who provides a service that involves moving among geographical regions (e.g., a transportation service). The system determines the value estimate by identifying a sequence of time periods, each time period having an associated set of geographical regions. Possible transitions between geographical regions in different time periods are analyzed, for example, using statistical or machine-learned models, to determine likelihoods that the user will move between the geographical regions from one time period to another, and to determine expected values for a transition. Such models may be trained or developed using historical service data and user profile data stored by the system. Transitions are analyzed over a sequence of time periods to determine accumulated values associated with estimated overall values for each geographical region. The system predicts an overall value estimate for the user based on the accumulated values.

Abstract: A method, apparatus and computer program product are provided for providing auto-replenishment of an inventory of promotions. Auto-replenishment amounts and dates may be determined based on a variety of factors including current inventory, outstanding promotions, redemption ratios and redemption rates. Redemption ratios and redemption rates may be characterized based on provider information, consumer information, and/or promotion information. Auto-replenishment may result in a smoothed redemption curve and optimal impact to the provider.

Abstract: Systems and a method for forecasting data at noninstrumented substations from data collected at instrumented substations is provided. An example method includes determining a cluster id for a noninstrumented substation, creating a model from data for instrumented substations having the cluster id, and forecasting the data for the noninstrumented station from the model.

Abstract: The present disclosure generally relates to a method and a hardware and software system for collecting data from retail point of sale. The hardware connects to a wide variety of barcode scanners and receipt printers. Collected data is transmitted to a cloud-based infrastructure backend system using a wireless internet connection built into the hardware. The collected data can be processed to extract item-level transaction information, and estimate the price and in-stock status of items in particular shops. A search engine can be provided using this data, which allows a customer to discover which nearby shop has an item of interest in stock. A targeted advertising system that complements this search service is also presented. The data can be used by retailers and manufacturers for business analysis and optimization.

Abstract: Embodiments select demand forecast parameters for a demand model for one or more items, receive historical sales data for the items on a per store basis and receive a plurality of seasonality curves for a first item. Embodiments determine a repeatability of each of the seasonality curves using a correlation of each seasonality curve over year to year demand and retain a first seasonality curve based on the repeatability. Embodiments determine a smoothness of the first seasonality curve and determine a sparsity of the first seasonality curve. Based on the determined repeatability, smoothness and sparsity, embodiments determine that the first seasonality curve is reliable and repeat the receiving the plurality of seasonality curves, determining the repeatability, determining the smoothness, and determining the sparsity to determine a plurality of reliable seasonality curves. Embodiments use the demand model and the reliable seasonality curves and determine a demand forecast for the first item.

Abstract: Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: examining change request data defined by the certain analyst user with use of a user interface of a planning application, the change request data defining a change to the dimensional hierarchy used by the planning application, wherein the user interface includes an area that displays a dimensional hierarchy being authored by a certain analyst user; generating a change request data record in dependence on the examining, wherein the change request data record specifies attributes of the change to the dimensional hierarchy; and using data of the change request data record to present prompting data for guiding the certain analyst user in further changing the dimensional hierarchy.

Abstract: Systems and methods for identifying topic coverage for a distribution platform that provides access to online content items. A set of topics that characterize subject matter of the online content items available via a system distribution platform may be obtained and individual ones of the content items may be associated with individual ones of the topics. Internal demand and/or external demand associated with the individual ones of the topics may be determined. Disparities between the internal demand and/or the external demand may be determined for individual ones of the content items. A graphical representation of the disparities determined may be generated.

Abstract: New client acquisition insights and forecasting are provided. A system, method, and computer readable storage device analyze historical data for identifying various client segments based on various combinations of similar attributes; determine cumulative marginal values (CMVs) associated with provisioning clients in each client segment, wherein the CMVs indicate whether provisioning a client within each client segment positively or negatively affects the system; analyze each client segment behavior for learning insights associated with clients in the client segment and effects on the system; and forecast CMVs for a selected client segment based on the learned insights for the selected client segment. In various implementations, a dashboard user interface comprising a data visualization of the forecasted CMVs is generated for display.

Abstract: A processor-based system and method retrieve customer purchase history information from an internal customer purchase history database for a plurality of customer records representing customers that previously purchased products of an enterprise, and retrieve customer profile information for each customer record. The processor executes a predictive machine learning model to determine a set of product purchase scores for each of the customers by applying a logistic regression model utilizing gradient boosting to the customer purchase history information and the customer profile information. The processor classifies the customers into a target customer group and a non-target customer group by applying a classification criterion to the set of product purchase scores, and generates a report of customers in the target customer group including highest product purchase scores and products recommended for cross-sale.

Abstract: A processor-based system and method retrieve customer purchase history information from an internal customer purchase history database for a plurality of customer records representing customers that previously purchased products of an enterprise, and retrieve customer profile information for each customer record. The processor executes a predictive machine learning model to determine a set of product purchase scores for each of the customers by applying a logistic regression model utilizing gradient boosting to the customer purchase history information and the customer profile information. The processor classifies the customers into a target customer group and a non-target customer group by applying a classification criterion to the set of product purchase scores, and generates a report of customers in the target customer group including highest product purchase scores and products recommended for cross-sale.

Abstract: The invention relates to a method for characterizing time series. The method includes obtaining a time series that includes data points for consecutive time intervals, decomposing the time series into a trend component, a seasonal component, and a residual component, and clustering the seasonal component into a number of clusters. Each of the consecutive time intervals is assigned to one of the clusters based on a level of the data points of the seasonality component in the time interval. The method further includes labeling one of the clusters as baseline with the baseline cluster containing more time intervals than any one of the other clusters, determining cluster labels for the other clusters based on the level of the data points of the time intervals assigned to the other clusters; and for each time interval, storing the corresponding cluster label in a vector.

Abstract: The present invention relates to a system and method for generating business decisions. Embodiments of this system and method receive customer transaction data and additional information (cumulatively referred to as ‘modeling data’). This data is utilized to generate a product decision tree which models consumer purchasing decisions as a tree structure. The product decision tree may be utilized by the system to analyze demand for a given leaf (product) in association with other related products. In some embodiments, customers are segmented into groupings of customers who have similar attributes, including similar shopping behaviors. Customer insights are generated for the customer segments. The customer insights and the product decision tree are used to generate business plans, which may then be provided to a store for implementation. These plans may include a product assortment plan, an everyday pricing plan, a promotional plan, and a markdown plan.

Abstract: A method, system, and computer program product for weight adjusted composite model for forecasting in anomalous environments are provided in the illustrative embodiments. A base forecasting model and a second forecasting model are combined to form a composite model, the base forecasting model configured to forecast an event in a time series, the second forecasting model configured to represent an anomalous portion of data in the time series. A mixing algorithm is combined with the composite model to adjust a set of weights associated with the composite model. Upon identifying a future period in which the event is to be forecasted, using the mixing algorithm, a subset of the set of weights is adjusted to from a weight adjusted composite model. The weight adjusted composite model is executed to forecast the event in the future period.

Abstract: The present disclosure relates to a persistent data structure employed as a tree structure with a frequent pattern mining paradigm. The number of nodes in the tree structure scales linearly with respect to the number unique items within the itemsets associated with the nodes. With the disclosed pattern mining paradigm, compressed representations of maximal patterns may be mined with the goal of detecting a frequent maximal pattern covers in a top down approach. Thus, large patterns are detected before their subsets yielding a significant reduction in computation time. The persistent data structure is a dynamic data structure which may be updated to add or delete nodes or transactional information without the need for recreating the entire tree structure. Furthermore, the persistent data structure may be run by a computing system either locally or on a parallelized distributed computing architecture to increase operational performance.

Abstract: A method and processing system for assessing of the health of a network of retail locations in a defined geographic area, by a process including the development of a greenfield benchmark score for a network of ideally sited locations, followed by the development of a brownfield score of current locations, for comparison to the greenfield score. The invention is further applicable to decisions to open a new location, relocate an existing location or close an existing location. In these cases, the effect of opening a new location, or relocating or closing an underperforming location is evaluated by recalculating the brownfield score after the addition of each of several potential new locations, and/or after relocating or closing each of several poorly performing locations.

Abstract: Rendering graphical user interfaces to display current and future data to users, the graphical user interfaces generated in response to search queries comprises a flight search system and an airline system. The flight search system receives current flight data and future flight data for the group of flights from an airline system and stores the data on a database. When the flight search system receives a flight search request comprising desired flight data from a user computing device, the system compares the desired flight search data with the stored data to identify one or more flights of the group of flights that match one or more features of the desired flight data. The system presents the current flight data and the future flight data on a graphical user interface to the user when it is likely that the flight data is going to change.

Abstract: An example method for predicting average inventory with newly added items can include: aggregating sales data of a plurality of items, the items comprising training items and new items; identifying, using a set of predefined rules, a data set of similar items on the training items for each of the new items, the set of predefined rules comprising a first stage similarity module, a second stage similarity module, and a second stage classification module; obtaining target metrics for each of the new items, the target metrics being turn predictions from the data set of the similar items; calculating mean errors of the turn predictions to identify a set of turn predictions with mean errors lower than a dynamic threshold; obtaining an ultimate turn prediction for each new item by averaging the set of turn predictions; and predicting an average inventory for each new item based on the ultimate turn prediction.

Abstract: A server device is provided with: a receiver that receives subject data that are transmitted from one or more folding devices for folding subjects and that include related data on the subjects which are read from the subjects by the folding devices; a storage unit that stores aggregate data obtained by aggregating the subject data; an analyzer that performs an analysis on predetermined data contained in the aggregate data; and a provider that provides a result of the analysis by the analyzer to a predetermined information processing device.

Abstract: A system and method are including a computer and a processor and memory. The computer receives a product class representing a product in a supply chain network including one or more supply chain entities and generates one or more new products for the product class using one or more automatically generated templates including a graphical representation of an exemplary product using a first smart product attribute value, the first smart product attribute value defined by a quantifiable measurement of a product attribute. The computer further causes items to be transported among the one or more supply chain entities to restock the inventory of the one or more items of the product class according to the current state of items in the supply chain network and the one or more new products.

Abstract: This application relates to techniques for recommending content to a user of a content distribution system. A server device can generate recommendations as part of a user interface for the content distribution system. The server device can be configured to: calculate a trend score for each of a plurality of digital assets managed by a content distribution system, calculate a recommendation score for a subset of digital assets that are not installed on a client device of a target user, calculate a breakout score for a subset of digital assets managed by the content distribution system each having a cumulative number of downloads below a threshold value, rank the digital assets according to the trend scores, the recommendation scores, or the breakout scores, and generate a visual representation of one or more digital assets to recommend to the user based on the ranking.

Abstract: Implementations of the present specification disclose a method and a system for recommending a target transaction code setting region. The method includes the following: dividing a target region to obtain multiple sub-regions, where the multiple sub-regions include one or more label sub-regions with known target transaction code setting effects and one or more sample sub-regions with unknown target transaction code setting effects; obtaining an association feature between the multiple sub-regions; obtaining predicted effect values of setting a target transaction code in the one or more sample sub-regions by using a prediction algorithm based on at least estimated effect values of setting a target transaction code in the one or more label sub-regions and the association feature; and determining at least one recommended region for setting a target transaction code from the one or more sample sub-regions based on at least the one or more predicted effect values.