Abstract: Behavior data associated with a user is obtained. The behavior data is generated when the user uses an Internet service and includes a user identification and identification information indicating the Internet service. At least one predefined carbon-saving quantity quantization algorithm is determined based on the identification information related to the Internet service. A carbon-saving quantity associated with the user is calculated based on the obtained behavior data and the determined at least one predefined carbon-saving quantity quantization algorithm. Based on the calculated carbon-saving quantity associated with the user and the user identification, user data is processed. The user data is related to the carbon-saving quantity associated with the user.

Abstract: Example implementations described herein involve a multi-layer hybrid model power generation prediction method and computing system. The example implementations described herein are configured to predict power generation that can be utilized for short-term planning by utilities to optimize operation planning to ensure economic and stable operation of the electricity.

Abstract: A workflow management system for managing the storage, retrieval, and transport of items in a warehouse includes a voice-directed mobile terminal. The system also includes a server computer in communication with the voice-directed mobile terminal. The server computer includes a tasking module for transmitting task data to the voice-directed mobile terminal. The server computer also includes a workflow-analysis module for generating, based at least in part upon an analysis of workflow dialog between the voice-directed mobile terminal and the user, performance data relating to the performance of tasks associated with the storage, retrieval, and/or transport of the items.

Abstract: Embodiments use a hierarchy of machine learning models to predict datacenter behavior at multiple hardware levels of a datacenter without accessing operating system generated hardware utilization information. The accuracy of higher-level models in the hierarchy of models is increased by including, as input to the higher-level models, hardware utilization predictions from lower-level models. The hierarchy of models includes: server utilization models and workload/OS prediction models that produce predictions at a server device-level of a datacenter; and also top-of-rack switch models and backbone switch models that produce predictions at higher levels of the datacenter. These models receive, as input, hardware utilization information from non-OS sources. Based on datacenter-level network utilization predictions from the hierarchy of models, the datacenter automatically configures its hardware to avoid any predicted over-utilization of hardware in the datacenter.

Abstract: An exemplary method of providing content to users of a social networking service includes selecting a first set of users from a plurality of users on a social networking service in a geographic region to receive personalized content. The method further includes setting a first distribution rate for the personalized content during a first period of time based at least in part on a first user-traffic pattern. The method also includes providing the personalized content to client devices of the first set of users in accordance with the first distribution rate during the first period of time. The method further includes tracking posting of the personalized content to the social networking service by the first set of users, and reducing the first distribution rate if a ratio between a number of times the personalized content is posted and a number of times the personalized content is provided satisfies a threshold.

Abstract: During operation, the system obtains a training dataset during a training mode, wherein the training dataset includes counts of actions performed by users while operating applications in the computer system. Next, the system uses the training dataset to produce corresponding per-action datasets. The system then cleanses the training dataset based on counts of actions in the per-action datasets to produce a cleansed training dataset, and uses the cleansed training dataset to produce corresponding per-user datasets. Next, the system trains per-user models based on the per-user datasets to detect anomalous actions of users. The system then obtains a surveillance dataset during a surveillance mode, wherein the surveillance dataset includes counts of actions performed by users while operating applications in the computer system. Next, the system uses the trained per-user models to detect anomalous actions in the surveillance dataset. Finally, when an anomalous action is detected, the system triggers an alert.

Abstract: Disclosed embodiments provide a computer-implemented technique for creating a log chain from multiple software component logs. The log chain can include log information from multiple software components that interact with each other. In embodiments, a locality-sensitive hashing technique is used to create a signature of a log chain. Machine-learning systems are trained with log chains generated from test execution, and/or log chains from incidents with deployed software. In embodiments, logs are pre-processed by tokenizing and trimming. Logs from various components that interact with each other may be combined into a temporally sequential log chain. The signature of the log chain may be used to identify additional information about the error from a machine-learning process that was trained on previously generated log chains. In this way, the time required to identify a problem can be significantly reduced, resulting in increased reliability and availability of complex computer systems.

Abstract: A method, system, and computer program product for managing resources by obtaining a high spatial resolution estimate of behavior adoption are described. The method includes obtaining a low-resolution estimate with a fixed geographic scale, selecting a sample of customers based on the low-resolution estimate, implementing a statistical model to obtain relative probability of adoption of the behavior by each of the sample of customers, and generating a weighted random realization from the sample of customers, the weighted random realization being weighted based on the relative probability of adoption.

Abstract: A system and method are disclosed for solving a supply chain planning problem modeled as a linear programming (LP) problem. Embodiments include receiving an LP problem representing a supply chain planning problem for a supply chain network comprising material buffers and resource buffers, partitioning the supply chain network at a complicating node into at least two supply chains sharing the complicating node, formulating a decomposed subproblem for each of the supply chains, calculating an effective dual based, at least in part, on a mathematical difference of at least two dual values calculated by solving the functional-based decomposed subproblems, and generating a globally-optimal LP solution to the LP problem using subgradient descent with the effective dual.

Abstract: An exemplary system, method, and computer-accessible medium for providing a financial account recommendation to person(s) can include receiving a transaction history for the person(s) associated with a first financial account, determining first rewards information based on the transaction history, accessing database(s) containing rewards rates for a plurality of second financial accounts, determining second rewards information for a particular second financial account of the plurality of second financial accounts based on the transaction history, and providing the financial account recommendation to the person(s) to one of (i) keep the first financial account or (ii) switch to the second financial account based on a comparison of the first rewards information to the second rewards information.

Abstract: A system for matching at least one utility consumer to at least one utility provider is provided. The system may include a communication device, a processing device and a storage device. The communication device may be configured for receiving utility consumption information from a utility consumption information source, receiving environmental information from an environmental information source, receiving premises information from a premises information source, receiving utility provider information from utility provider information source and transmitting a utility recommendation to an electronic device. Further, the processing device may be configured for analyzing each of the utility consumption information, the environmental information and the premises information and the utility provider information, and generating the utility recommendation based on the analyzing.

Abstract: A procurement system and process using blockchain is disclosed. The procurement system may facilitate procurement reconciliation between procurement initiators, clients, suppliers, and/or transaction processors, using blockchain. Each party may comprise a blockchain node configured to interact with a procurement blockchain. The procurement process may be controlled by a billing smart contract and a client smart contract configured to enforce data workflows and establish trust between the parties.

Abstract: A method and system for task execution in dynamic heterogeneous robotic environment is disclosed. The method includes extracting data associated with a plurality of data categories and further deriving a plurality of factors from the extracted data. The method further includes determining a plurality of correlations among the plurality of factors based on the deep learning network. The method further includes deriving a plurality of sentiment parameters for a set of factors from the plurality of factors based on the plurality of correlations. The method may further includes simulating execution of the at least one current task by employing a plurality of robots. The method may further includes iteratively re-adjusting at least one of the plurality of sentiment parameters based on reinforcement learning performed on a result of the simulating. The method may further includes executing the at least one current task by employing the plurality of robots.

Abstract: A system and method for mining social media signals and cues i) created by a user (for example, a customer) and/or ii) to which the user is exposed (the “data”), and for processing that data as it relates to a service (including a fee or subscription-based service), in order to predict the user's predisposition or likelihood to either leave the subscription or the service or reduce his/her engagement with the subscription or the service.

Abstract: A vending machine system is disclosed and claimed. In particular, the disclosed vending machine system allows multiple vendors to sell food items through a vending machine. The vending machine provides multiple locked bins, each of which can authenticate to a single vendor. Also, the vending machine implements price adjustment rules, such as raising the price of a particular item during, before, and after a high traffic event. In addition, customer dietary restrictions can be tracked, and purchases of food items that would violate those dietary restrictions can be prevented.

Abstract: Multilevel production processes are integrated utilizing as input a relatively lower production level. Activities at the lower production level producing an end product and physical parameters that influence these activities are identified, the identified physical parameters are measured with sensors, and a quota fulfillment probability index for an activity is determined using the measured physical parameters. The quota fulfillment probability index is supplied to a production entity operating at a consecutive, relatively higher production level than the activities at the relatively lower production level.

Abstract: A system and method for automated delivery driver routing and order preparation timing. The system is a cloud-based network containing an optimization server, portals for restaurants, customers, and drivers to enter their information, and an optimization engine which determines optimal pickup and delivery times for delivery drivers based on a multitude of variables associated with the business enterprises and delivery driver availability. The system may be accessed through web browsers or purpose-built computer and mobile phone applications.

Abstract: A financial institution computing system includes an account database configured to store a plurality of transaction statistics with respect to a financial account of a customer, a social media database configured to store a plurality of social media activities of the customer, and a customer metric management circuit. At least one of the plurality of transaction statistics is indicative of a first transaction between the customer and a merchant. The customer metric management circuit is configured to determine a probability model of the customer based on the plurality of transaction statistics and the plurality of social media activities of the customer. The probability model indicates a probability that the customer will conduct a second transaction with the merchant in the future. The customer metric management circuit is further configured to provide the probability model of the customer to a device associated with the merchant.

Abstract: A social media streaming system, includes a server and at least one client device. The server includes a server-trading module. The client device includes a display component and an input component. The input component is configured to receive a trading request, and send the trading request to the server. When the server receiving the trading request, subsequently, the server-trading module generates a trading log based on the trading request. The client device is enabled to delete the trading request after the trading log is generated.

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 dynamic supply chain planning system for analysis of historical lead time data that uses machine learning algorithms to forecast future lead times based on historical lead time data, weather data and financial data related to locations and dates within the supply chain.

Abstract: This disclosure involves verifying that a power network model corresponds to an electric power network providing electrical power in a geographical area. For instance, a validation device computes a validation score for a power network model based on a connectivity score, an asset score, and a power-flow score. The connectivity score indicates connectivity errors in the power network model as compared to the power network. The asset score indicates power-delivery errors in the power network model with respect to power-consuming assets serviced by the power network. The power-flow score indicates power-flow calculation errors in the power network model with respect to voltage ranges for the power network. The validation score is repeatedly computed for iteratively updated versions of the power network model until a threshold validation score is obtained. The validated power network model is provided to a control system for identifying and correcting errors in the power network.

Abstract: A system includes a financial data storage that stores internal account data, external account data, and transaction data, a communications interface configured to receive external account data from an external data source and transaction data from a merchant, and a database manager that cooperates with the communications interface to store the external account data and the transaction data. The system also includes an account balance prediction processor configured to identify recurring expense transaction(s) and recurring income transaction(s) and update them based on user input, determine predicted expense transaction(s) and a predictive income using a predictive model, and calculate a predicted account balance. The system also includes a transaction monitor configured to compare one or more actual expense transactions with one or more predicted expense transactions, and an alert transmitter configure to generate and transmit one or more alerts based on the comparison.

Abstract: A computer generates an optimized decision distribution vector for a plurality of related, demand-correlated products. The computer receives data indexed by product, with each entry including several entry attributes. The computer receives decision context data for the products. The computer determines a set of primary attributes and trains a first machine learning model based upon those attributes. The computer receives a decision optimization request that includes an associated set of attributes corresponding to the primary attributes. The computer scores the associated set of attributes, using the first machine learning model, to generate a baseline purchase propensity. The computer trains a second machine learning model, based upon the baseline purchase propensity and the decision context data, to generate own-product and cross-product elasticity data.

Abstract: Examples of article designing are described herein. In an example, image data, margin data, and sales data corresponding to a plurality of articles may be obtained. The obtained data may be analyzed to identify a first article image of a first article and a second article image of a second article. The first article image is integrated with the second article image, based on an article attribute to generate a transformed article image. The article attribute may be an attribute having a maximum likelihood of making the article popular. The transformed article image may be filtered based on predefined filtering rules to obtain a curated article design image. The curated article design image is assessed to generate a design score indicative of a popularity and/or a sellability of an article, and a design of the article may be selected for a post design selection process, based on the design score.

Abstract: A system may include a rental unit allocation portal and a prediction unit. The portal receives tenant application information and allocating a rental unit based on the tenant application information and a length of stay prediction score associated with the tenant. The prediction unit may determine the length of stay prediction score by using one or more models and voting among the prediction scores of the one or more models. The one or more models may include a logic regression model, a survival analysis model, a tree-based model and/or a gradient boosting model. In addition, the system may include a conformal predictor configured to predict the confidence interval. The length of stay prediction score can also be provided to a risk allocation unit configured to quantify risk by aggregating it for a portfolio of underlying properties with tenants, or a portfolio of loans secured by tenanted properties.

Abstract: Examples of network bandwidth management are provided. A system may access, time series distribution data including a distribution of data points corresponding to an average count of network packets. Further, the system may determine, from the time series distribution data, trend data component, seasonal data component, cyclical data component, and irregular data component. Furthermore, the system may compute, baseline distribution traffic data based on the trend data component, the cyclical data component, and the seasonal data component. Furthermore, the system may identify auto regression data component and moving average data component based on the irregular data component. The system may further, determine an estimated network traffic for a future time interval based on the baseline distribution traffic data, a lagged covariate factor, and covariate metrics. Furthermore, the system may provide the estimated bandwidth based on the estimated network traffic to configure the server.

Abstract: Similarity of items can be estimated by using a method including generating a prediction model that predicts an indicator of a target based on one or more attributes for items, by estimating a weight set, among weight sets, for each of the items, and estimating a similarity among the items for the target based on the weight sets of the prediction model.

Abstract: A health care provider (HCP) engagement engine is disclosed. The HCP engagement engine facilitates effective communication between pharmaceutical sales representatives (pharma reps) and HCPs by tracking actions performed by pharma reps to sell products to HCPs, analyzing the actions, and eliminating confounding effects due to inbound and outbound activities. Inbound activities include behaviors performed by pharma reps to the HCPs, while outbound activities are taken by HCPs in response to the inbound activities. Reducing confounding allows the pharma reps to have better information about which behaviors best drive HCP engagement.

Abstract: Quantitative evaluations of friction within a customer experience may be provided to reduce abandonment and improve conversion of transactions. One or more transactions may be identified. One or more personas corresponding to the one or more transactions may be identified. One or more customer friction factor (CFF) scores corresponding to the one or more transactions may be determined. A given CFF score may be a quantification of an aspect of a given transaction that has a negative impact on a customer experience associated with the given transaction. The one or more CFF scores may be compared with one or more valid comparisons relating to the same industry and the same transaction type. One or more friction points may be identified based on the comparison of the one or more CFF scores. Addressing a friction point may reduce abandonment and improves conversion associated with transactions.

Abstract: Systems for monitoring and analyzing behavior in various applications and uses thereof. Generally, the systems (and uses thereof) are for monitoring and analyzing consumer purchasing behavior in real-time to drive sales via engaging digital customer experiences. In embodiments, the disclosed system can include a retail store system that features and includes MAC address tracking, user eye tracking, object identification of goods on shelves, open API, advertising broker rules engine. In addition, the system can include a customer engagement with interactive output displays including displays with demographic intelligence, displays with demographics and MAC—panels throughout store at product, displays with demographics and MAC—single panel or few panels scattered throughout store, automated customer assistance at shelf, customer purchase at shelf.

Abstract: A request for transport services that identifies a rider, an origin, and a destination is received from a client device. Eligibility of the request to be serviced by a vertical take-off and landing (VTOL) aircraft is determined based on the origin and the destination. The client device is sent an itinerary for servicing the transport request including a leg serviced by the VTOL aircraft. Confirmation is received that the rider has boarded the VTOL aircraft and determination made as to whether the VTOL aircraft should wait for additional riders. Instruction are sent to the VTOL aircraft to take-off if one or more conditions are met.

Abstract: A method and apparatus for predicting customer behavior is disclosed. The method comprises organizing a transcribed, diarized text of a conversation in a call, into a predefined number of sets, determining features corresponding to a sentiment score, a percentage and/or count of positive words, and a percentage and/or count of negative words for each of the a predefined number of sets, determining word count features corresponding to the word count for each of the a predefined number of sets, determining features corresponding to a call talk time, a call hold time and a call hold percentage based on the transcribed text. Based on all the determined features, the method determines whether the customer is satisfied or not, the customer activity based on an activity profile of the customer, and whether the customer used escalation terms based on the transcribed text.

Abstract: A Foundational Framework (“the Framework”) may refer to an apparatus that connects a multiplicity of potentially very complex components, each of which produce different types of information related to financial forecast, while maintaining a distributed and federated model to allow high autonomy to each component. The innovative Framework provides a unified operation of lifecycle of every component and allows the production of unlimited types of forecasts of different dimensions and for different purposes using a common tool that is responsible of coordinating and running the sequence of components for the user's needs.

Abstract: Based upon the transition information for all the retail stores, a determination is made of an average cluster retention score. The average cluster retention score is a measure of how many retail stores have moved from original to different existing sales clusters in the current sales period. When the average cluster retention score is below a predetermined threshold, a complete re-organization of the existing sales clusters is performed. When the average cluster retention score is above the predetermined threshold, a determination is made as to whether each retail store should be re-classified.

Abstract: The embodiments of the present disclosure provide an order processing method, apparatus, device, system and storage medium, where the method includes: acquiring an original order to be processed; searching for unsorted target orders, where the target orders are obtained by combining a plurality of original orders; decomposing at least part of the searched target orders into original orders; combining the original orders obtained by decomposition and the original order to be processed to regenerate one or more target orders. The order processing method, apparatus, device, system and storage medium provided by the embodiments of the present disclosure can realize dynamic roll-back combining, so that the newly arrived original order is combined with the currently unsorted target orders, and the out-of-warehouse efficiency is effectively improved.

Abstract: A method, system, and computer program product for relating test data to business requirements are provided in the illustrative embodiments. a test operation of a code is configured in a test data processing environment, a section in the code corresponding to a portion of a business requirements document. A set of baseline results is received. The test operation is executed, identifying the section of the code and associating the section of the code with a test result produced from the test operation. A determination is made whether the test result matches a first baseline result from the set of baseline results within a tolerance. When the test result does not match the first baseline result from the set of baseline results within the tolerance, the portion of the business requirements document is annotated.

Abstract: Methods and systems for generating a messaging campaign are described. A first phase of the campaign is conducted using a first set of parameters for delivering a first message to a first group of intended recipients via a first distribution channel. Based on analysis of online activity associated with one or more members of the first group, a second set of parameters is determined for a second phase of the messaging campaign. The second set of parameters define a change to the first set of parameters.

Abstract: The present specification discloses a multi-classifier-based recommendation method and device, and an electronic device.

Abstract: In order to facilitate machine learning for prediction using distinct dataset types, systems and methods include collecting content information from archived websites databases. Collecting historical event information from online sources, where the historical event information is associated with a plurality of historical events. Generating event-dependent products training datasets based on the content information and the historical event information, where the event-dependent content training datasets defines for content historical events that are associated with attributes of the content, attribute change of the content, or both. Training an attribute prediction machine learning model based on the event-dependent content training datasets. Applying the trained attribute prediction machine learning model to additional event information to predict, for content, a future attribute estimate, a future attribute change estimate, or both.

Abstract: Risk scores are generated by systems that use features or inputs from the current transactions, some summary statistics like velocity and some statistics calculated in batch mode which traverse hierarchical classification levels of entities, including classified attribute levels of known transactions, to identify neighborhoods of related entities and related transactions. Corresponding records of transaction information are extracted from or are otherwise generated from neighborhoods of the related transactions associated with the defined neighborhoods of entities/transactions.

Abstract: A system and method for optimizing advertisements for display to users comprising receiving a request for an advertisement wherein the request comprises information about a user to whom the advertisement is to be displayed; determining at least one community of which the user is a member; determining a conditional probability that the user will interact with the advertisement; responsive to the conditional probability exceeding a threshold, determining community data to present with the advertisement and providing for display to the user the advertisement and the community data; responsive to the providing of the advertisement, receiving an indication of activity at a client system related to the advertisement or community data; and storing the indication in a storage medium.

Abstract: This disclosure describes a market segment analysis (MSA) system that facilitates a cluster analysis of market segment data and performance metrics to identify data patterns between individual market segments within a designated market region. Particularly, the MSA system may quantify current performance of existing vendor product or service offerings within a market segment relative to historical performance of the vendor product or service offering within the market segment. Further, the MSA system may quantify current performance of a vendor product or service offering relative to current peer performance of the same or substantially similar vendor product or service offerings within additional market segments. The MSA system may recommend one or more additional market segments for an offering of the vendor product or service. Alternatively, or additionally, the MSA system may recommend one or more vendor product or service offering(s) for a target market segment of a designated market region.

Abstract: A device may receive, from account entity devices, sets of transaction data for transactions between merchants and customers, and may use a first machine learning model to assign the customers to clusters based on measures of similarity among the sets of transaction data. The device may determine travel-related data items in a set of transaction data, of the sets of transaction data, associated with a set of customers assigned to a particular cluster, and may use a second machine learning model to identify a travel experience that has a threshold likelihood of being of interest to the set of customers. The device may receive offers relating to the travel experience, and may provide, to customer devices associated with customers of the set of customers, travel offer packages that include at least one of the offers relating to the travel experience.

Abstract: A method and apparatus for analysing utility consumption at a utility supply location is described. The method comprises the steps of: receiving utility consumption data corresponding to utility consumption at the utility supply location over a time period to be analysed; generating a recurring consumption model indicative of repeating consumption patterns in the utility consumption data; identifying divergences between the utility consumption data and the recurring consumption model; computing a diagnostic measure indicative of irregular consumption based on the identified divergences; and outputting the diagnostic measure. The diagnostic measure may be used to identify flexibility or irregularities in consumption and/or to control supply of the utility. The utility may be e.g. electricity, gas or water.

Abstract: Systems and methods are disclosed that provide for extracting information from a text string. In certain embodiments, a system is disclosed to receive a textual string representative of a distributed computing operation. The system is configured to isolate an identifier included in the textual string based on information in the textual string and/or other information associated with the distributed computing operation. The system is also configured to provide the identifier to a computer device over a network.

Abstract: A system and computer implemented method for amplifying the online visibility and credibility of a user of an application platform is provided. The system includes an application platform for carrying out the method; a desired work related to a defined topic; a drafted work from a creator that is graded based on predetermined attributes; an automated reader configured to read, identify, and tag keywords; target websites having attributes associated with the defined topic or keywords; one or more accepted users for sponsoring the drafted work on a selected target website; a matching user to sponsor the drafted work; an enhanced work enhanced for the keywords and the matching user; a transmission of the enhanced work to a selected target website; a published work on target website; and a symbiotic sharing the work on one or more social media platforms selected by the matching user.

Abstract: Systems, methods, and storage media for pre-approving onboarding to a payment platform, executing on a processing device are disclosed. Exemplary implementations may: access a node network; determine a first business entity associated with a first node of the plurality of nodes is not a member of a payment platform; determine a total strength of connections of the first node to one or more nodes of the plurality of nodes exceeds a predetermined threshold value; and flag the first node of the plurality of nodes for an offer of onboarding to the payment platform consequent to determining the total strength of connections of the first node to the one or more nodes of the plurality of nodes exceeds the predetermined threshold value.

Abstract: A system and method for creating a model for predicting and reducing subscriber churn in a computer network. The method including: for a predetermined time period: retrieving traffic flow data per subscriber for a plurality of subscribers in the computer network; determining at least one metric per subscriber from the traffic flow data; determining at least one systemic feature associated with the plurality of subscribers; and storing the at least one amalgamated metric and feature; on reaching the predetermined time period create the model by: analyzing at least one metric and at least one feature for the predetermined time period; predicting, per subscriber, whether the subscriber is going to churn within a churn period in the future based on the analysis; validating the prediction by determining whether the subscriber actually churned during the churn period; and creating the model based on the validated predictions.

Abstract: A method of determining and optimizing the location of a new insurance agency is disclosed to increase market penetration of underrepresented markets. The method comprises the use of a scoring algorithm to rank various geographic regions or related zip codes. The scoring algorithm may be implemented by a location modeling system based on variables selected by a user.