Methods, systems, and techniques for producing and using enhanced machine learning models and computer-implemented tools to investigate cybersecurity related data and threat intelligence data are provided. Example embodiments provide an Enhanced Predictive Security System, for building, deploying, and managing applications for evaluating threat intelligence data that can predict malicious domains associated with bad actors before the domains are known to be malicious. In one example, the EPSS comprises one or more components that work together to provide an architecture and a framework for building and deploying cybersecurity threat analysis application, including machine learning algorithms, feature class engines, tuning systems, ensemble classifier engines, and validation and testing engines. These components cooperate and act upon domain data and feature class vectors to create sampled test, training, and validation data and to build model subsets and applications using a trained model library, which stores definitions of each model subset for easy re-instantiation.

Methods, systems, and computer programs are presented for estimating a propensity to buy a product or service. One method includes accessing events generated at a website. Each event comprises a data structure describing an operation performed by a user when accessing the website. Further, the method performs operations, for each user from a group of users associated with an audience, comprising: providing event information for a time window, information of the user, and information for a product as input to a propensity machine-learning (ML) model, the model being trained with training data comprising values for features that include event features, user information features, and audience labels; and generating, by the propensity ML model, a score for the user indicating a probability that the user will purchase the product. Further, the method generates a forecast of purchases of the product for the users in the audience based on the scores.

A method for automatically generating, in real-time, for display on a display, a simplified network layout from an initial network layout including one or more lines each connecting a plurality of nodes. Graph information is provided indicating vertices representing geographic positions of the nodes and edges representing connections between the nodes. The nodes are repositioned to optimize an objective function based on readability of the simplified network layout. Nodes and edges are discretized using interpolation to align a plurality of the nodes and connect the aligned nodes using simplified k-linear segments, where k-linear segments are parallel to one of k equidistant orientations whose angles are multiples of 180/k degrees, with k larger or equal to two. The simplified network layout is provided for a display.

Systems, methods, and apparatuses for implementing a geo-demographic zoning optimization engine are disclosed. According to an exemplary embodiment, there is a system executing at a web platform, in which the system includes: a memory to store instructions; a set of one or more processors; a non-transitory machine-readable storage medium that provides instructions that, when executed by the set of one or more processors, the instructions stored in the memory are configurable to cause the system to perform operations for designing sectioned mappings for a geo-demographic region, the operations including: executing instructions via the processor to implement a receive interface at the web platform; exposing the receive interface to users of the web platform; receiving, at the receive interface, geographic information system (GIS) data defining a plurality of district boundary spatial layers for a plurality of land parcels representing districts located at least partially within the geo-demographic region; creating a plurality of zones by overlapping the plurality of district boundary spatial layers; combining separate subsets of the plurality of zones into temporary exclusive regions; optimizing a number of precincts for each of the temporary exclusive regions by combining two or more of the temporary exclusive regions into a number of precincts; in which the optimizing comprises executing an algorithm based on hierarchical objectives configured to minimize splitting precincts that contain more than one district of any type, subject to user-selected input parameters operating as constraints; and generating a design plan map with optimized number, shape, size, and boundaries defining every precinct of the design plan map outputted from the web platform to a user interface. Other related embodiments are disclosed.

An apparatus, for a mobile object, that determines a bid-offer condition on an electricity transaction market: acquires information on sell-buy prices for an electricity amount presented by electricity demanders on direct transaction markets, where a contract is executed for electricity that the mobile object directly supplies to or procures from an electricity demander; determines, based on the sell-buy prices, an optimal condition that maximizes a profit from an electricity transaction for the mobile object; and determines, as the bid-offer condition, to place an offer or a bid on an electricity transaction market at a sell or buy price for a to-be-discharged or to-be-charged electricity amount that are determined for each time period in the optimal condition. The sell-buy prices for the electricity amount presented by the electricity demanders on the direct transaction markets are acquired through prediction, or notification from the individual electricity demanders.

The present disclosure provides a method comprising receiving a ride request from a user having a user profile, the ride request including a requested drop-off location within a service area and the user profile specifying at least one drop-off location preference parameter; querying a database to obtain data regarding a condition of the requested drop-off location, wherein the data is collected by a plurality of vehicles traversing the service area and equipped with at least one sensor and at least one imaging device; determining whether the obtained data satisfies the at least one drop-off location preference parameter; and determining at least one alternative drop-off location within a first distance from the requested drop-off location if the obtained data does not satisfy the at least one drop-off location preference parameter.

Provided is a process, including: obtaining geolocations histories of computing devices; assigning different subsets of the location histories to different computing devices in a compute cluster; querying a geographic information system (GIS) with geolocations in the geolocations histories to obtain identifiers of chain retail establishments; determining visit graphs for the individuals; and determining, for a given retail chain and a given individual, a score indicative of an affinity of the given individual to the given retail chain based on the visit graphs for more than 100 individuals including the given individual.

A service provider may receive merchant analytics information from a plurality of merchant devices. In some examples, the service provider may generate a model based at least in part on the merchant analytics information, the model including a core set of features for predicting a merchant metric associated with a merchant. The service provider may detect a lift in an observed value of the merchant metric based at least in part on a residual value of the merchant metric at a location of the lift, and add an additional feature to the model to cause a predicted value of the merchant metric to correspond to the observed value of the merchant metric at the location of the lift. The service provider may further send information associated with the feature to a merchant device associated with the merchant. As an example, the information may include a prediction for the merchant metric and/or a recommendation for improving the business of the merchant.

The present invention relates to a method for diagnosing and predicting the science technology power of countries, companies, research institutes, and desired technologies through a diagnosis model created by applying one or more patent and paper variables to a machine learning algorithm. The present invention comprises a step for: collecting patent or paper data for a predetermined technology, classifying the collected patent data into each country, company, and research institute, calculating one or more patent or paper variables, generating a diagnosis model by applying the variable to a machine learning algorithm, and calculating one or more diagnosis values using the diagnosis model.

A method includes receiving data characterizing a configuration of an asset configured within an oil and gas production environment. The data can include attribute-value pairs identifying attributes of the configuration of the asset and values of the attributes. The attribute-value pairs can correspond to a hierarchical structure of the asset and sub-components of the asset. The method can include determining a representation of the asset. The representation can be provided in a provided in a language-independent format suitable for use with data interchange application programming interfaces. The method can include determining an asset model of the asset. The asset model can include a digital representation characterize the hierarchical structure of the asset and sub-components of the asset. The asset model can include computer-readable, executable content associated with the attribute-value pairs. The method can include providing asset model. Related systems, techniques, and non-transitory computer readable mediums are also described.