Abstract: Systems and methods to facilitate a customization and proliferation of models are described. The system receives, via a first interface, table information and communicates the table information to a first model. The first model includes logic to process the values to generate a column of predicted values. The system receives a column of predicted values from the first model. The system appends the column of predicted values to the table information to generate appended table information. The system communicates, via a second interface, the appended table information to a second state including a second plurality of models. The sequence of states is associated with a plurality of interfaces including the first interface and the second interface. The interfaces facilitate a customization and proliferation of models.

Abstract: Systems and methods to utilize a machine learning model registry are described. The system deploys a first version of a machine learning model and a first version of an access module to server machines. Each of the server machines utilizes the model and the access module to provide a prediction service. The system retrains the machine learning model to generate a second version. The system performs an acceptance test of the second version of the machine learning model to identify it as deployable. The system promotes the second version of the machine learning model by identifying the first version of the access module as being interoperable with the second version of the machine learning model and by automatically deploying the first version of the access module and the second version of the machine learning model to the plurality of server machines to provide the prediction service.

Abstract: Systems and methods to facilitate a customization and proliferation of models are described. The system receives, via a first interface, table information and communicates the table information to a first model. The first model includes logic to process the values to generate a column of predicted values. The system receives a column of predicted values from the first model. The system appends the column of predicted values to the table information to generate appended table information. The system communicates, via a second interface, the appended table information to a second state including a second plurality of models. The sequence of states is associated with a plurality of interfaces including the first interface and the second interface. The interfaces facilitate a customization and proliferation of models.

Abstract: Systems and methods are disclosed for automatically determining property value, the systems and methods perform operations comprising: receiving, by a server, subject real-estate property listing information associated with a subject real-estate property; identifying a plurality of comparable real-estate property listings based on attributes of the subject real-estate property listing information; processing the subject real-estate property listing information together with the plurality of comparable real-estate property listings using a trained machine learning technique to predict a value for the subject real-estate property, the trained machine learning technique being trained to jointly establish a relationship between weights assigned to a set of training comparable real-estate property listings and value adjustments of the set of training comparable real-estate property listings and a value of a real-estate property of interest; and performing an action with respect to the subject real-estate property

Abstract: Systems and methods to facilitate a customization and proliferation of models are described. The system receives, via a first interface, table information and communicates the table information to a first model. The first model includes logic to process the values to generate a column of predicted values. The system receives a column of predicted values from the first model. The system appends the column of predicted values to the table information to generate appended table information. The system communicates, via a second interface, the appended table information to a second state including a second plurality of models. The sequence of states is associated with a plurality of interfaces including the first interface and the second interface. The interfaces facilitate a customization and proliferation of models.

Abstract: Systems and methods are disclosed for receiving, from a client device, a request to generate a value for a subject real-estate property, searching a database to identify a plurality of real-estate properties that have previously been sold, and automatically generating, based on a sale price of each of the plurality of real-estate properties, the value for the subject real-estate property. The systems and methods further provide for computing a collective physical state of the plurality of real-estate properties, determining whether the collective physical state corresponds to a threshold, and generating a prompt, based on the determination of whether the collective physical state corresponds to the threshold, for display on an operator device to review the automatically generated value before the value is presented to the client device.

Abstract: Systems and methods to utilize a machine learning model registry are described. The system deploys a first version of a machine learning model and a first version of an access module to server machines. Each of the server machines utilizes the model and the access module to provide a prediction service. The system retrains the machine learning model to generate a second version. The system performs an acceptance test of the second version of the machine learning model to identify it as deployable. The system promotes the second version of the machine learning model by identifying the first version of the access module as being interoperable with the second version of the machine learning model and by automatically deploying the first version of the access module and the second version of the machine learning model to the plurality of server machines to provide the prediction service.

Abstract: Systems and methods are disclosed for automatically determining property value, the systems and methods perform operations comprising: receiving, by a server, subject real-estate property listing information associated with a subject real-estate property; identifying a plurality of comparable real-estate property listings based on attributes of the subject real-estate property listing information; processing the subject real-estate property listing information together with the plurality of comparable real-estate property listings using a trained machine learning technique to predict a value for the subject real-estate property, the trained machine learning technique being trained to jointly establish a relationship between weights assigned to a set of training comparable real-estate property listings and value adjustments of the set of training comparable real-estate property listings and a value of a real-estate property of interest; and performing an action with respect to the subject real-estate property

Abstract: In an example embodiment, a solution is provided that produces wide tables containing features for machine learned models. These wide tables are made available for model training for multiple models and/or groups. These wide tables may be served on a serving database for fast access for application program interface (API) serving and lightweight access during interactive development. The solution decreases the time needed to add a new feature from several days to a couple of hours by enabling experimentation.

Abstract: Systems and methods are disclosed for automatically projecting a number of days to pending for a real-estate property by receiving, by a server, real-estate property listing information of real-estate property activities associated with a plurality of real-estate properties and determining, for each of the plurality of real-estate properties, a days to pending amount indicating time between when a respective one of the plurality of real-estate properties was listed and when the respective real-estate property was sold. The systems and methods further train a machine learning technique to establish a relationship between the different types of real-estate property activities and the determined days to pending amounts. The trained machine learning technique is applied to new real-estate property activities associated with a new real-estate property to predict a length of time between a first time the new real-estate property was listed and a second time when the new real-estate property will be sold.

Abstract: Systems and methods are disclosed for receiving, from a client device, a first input that provides a current address associated with a user; receiving, from the client device, a second user input that identifies a target location; and searching a real-estate database to identify a real-estate property associated with the current address. The systems and methods further provide for estimating equity associated with the real-estate property, updating parameters of a loan model based on the target location and the estimated equity, and providing an output of the model for presentation to the user based on the updated parameters.

Abstract: Systems and methods to manage a fleet of home electronic systems are described. The system receives, over a network, event information at a home fleet management system. The event information is received from home electronic systems and includes sensor information. The system aggregates the sensor information according to geographic areas to generate first aggregated sensor information. The system generates first user interface information based on the first aggregated sensor information. The system receives first selection information including a metric identifier and a geographic identifier. The system generates second user interface information based on the first selection information. The system receives second selection information identifying a group of home electronic systems and an action. The system communicates action information to selected home electronic systems based on the action to cause the action to be performed at the selected home electronic systems.