Various embodiments are generally directed to techniques utilizing computers to process service billing data, generate one or more groups of customers based on one or more attributes of the data, and train a recurrent neural network (RNN) to predict future bill amounts for customers. Embodiments further include techniques to predict the future bill amounts of the customers and providing an indication of the bill amounts to the customers.

The present disclosure is directed to a novel system for using a distributed register to generate, manage, and store data for interest-pooled time deposit resource accounts. The invention leverages a pooled resource account approach, allowing for multiple disparate resource accounts to benefit from an enhanced interest return by pooling resource accounts. The system components of the invention contemplate the use of distributed register technology to provide a verified ledger of information related to one or more resource accounts, as well as store system data, user data, and metadata related to the movement and management of resources. By using a distributed register approach to store and verify data related to time-dependent resource account services, the invention provides an automated system and methods for enhancing the flow of sensitive verified information, reducing the need for manual review and increasing the speed at which various resource account services can be validated and executed.

An automobile maintenance application may link automobile owners with service providers and provide service reminders based on manufacturers' recommended scheduled maintenance. The automobile maintenance application may maintain maintenance records for automobiles. The automobile maintenance application may provide a system for service providers to send targeted advertisements to automobile owners in need of a service. The maintenance application may allow automobile owners to compare the prices and services of local service providers and benefit from the value associated with competition between service providers that is realized during a live or proxy auction.

Implementations of the disclosed subject matter may provide a method of retrieving a data record including historic utility bill statements of a customer, determining a historic energy usage rate of the customer based on the retrieved data record, and determining whether the customer is eligible to subscribe to a community solar energy generating system based on geographic location of the community solar energy generating system, the determined historic energy usage rate of the customer, and the customer's geographic location. The method may determine an allocation of energy produced by the community solar energy generating system when the eligible customer is enrolled in a subscription to the community solar energy generating system. The method may generate a customer data record for the user based on credits for the allocation of energy of the community solar energy generating system and receiving energy from another energy generating system.

An online concierge system allows users to order items from a warehouse having multiple physical locations, allowing a user to order items at any given warehouse location. To select a warehouse location for a warehouse selected by a user, the online concierge system identifies a set of items that the user has a threshold likelihood of purchasing from prior orders by the user. For each of a set of warehouse locations, the online concierge system applies a machine-learned item availability model to each item of the identified set. From the availabilities of items of the set at each warehouse location of the set, the online concierge system selects a warehouse location. The online concierge system identifies an inventory of items from the selected warehouse location to the user for inclusion in an order.

Technologies are described for determining route proposals for shipment of cargo using unique location identifiers (ULIs). For example, a pickup ULI and a delivery ULI can be received. The pickup ULI and the delivery ULI are in the ULI data structure format defined herein. A first geographic area representing a pickup leg can be determined for shipment of the cargo from the pickup ULI to a first transportation network location and a second geographic area representing a delivery leg can be determined for shipment of the cargo from a second transportation network location to the delivery ULI. The main leg of the shipment occurs between the first transportation network location and the second transportation network location and travels through one or more defined transportation networks. Route proposals can be generated for shipment of the cargo through the pickup leg, main leg, and/or delivery leg.

Technologies are described for determining possible routes using pre-processing operations. The pre-processing operations determine possible routes from an origin location to a destination location by dynamically generating representations of the transportation networks at runtime. For example, the pre-processing operations can dynamically determine a geographic area, and/or multiple sub-areas, that covers the origin location and the destination location. Possible routes from the origin location to the destination location can then be determined using only those locations within the geographic area and/or sub-areas. The locations that make up the possible routes can be provided for route optimization that utilizes transportation schedules and/or additional transportation requirements.

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.

The present disclosure provides method and system to facilitate definition, tuning and visualization of a geo-fence at a computer system. The method comprises: receiving input parameters for a geo-fence, the input parameters including one or more parameters specifying a geographical region; sampling historical mobile signals based on one or more of the input parameters; dividing the geographical region into a plurality of areas; determining a weight for each respective area of the plurality of areas based at least on density of sampled mobile signals associated with geographical locations in the respective area; selecting a subset of the plurality of areas based on respective weights of the plurality of areas; and forming the geo-fence using the subset of the plurality of areas, the geo-fence including one or more contiguously closed regions each formed by a cluster of adjacent areas among the subset of the plurality of areas.

A system and method are disclosed herein. The system includes one or more processors and a memory having programming instructions stored thereon, which, when executed by the one or more processors, performs operations. The operations include retrieving historical account activity. The operations further include constructing a training data set that includes the historical inflow data, the historical outflow data, and known forecast information from the historical account activity. The operations further include generating a combined prediction model configured to forecast future inflow activity and future outflow activity. The operations further include receiving current inflow activity, current outflow activity, and current balance information for a user. The operations further include generating a predicted account balance by forecasting, by the prediction model, a future inflow and a future outflow and constructing the predicted account balance based on the future inflow, the future outflow, and the current balance information.