The present disclosure describes transaction-enabling systems and methods. A system can include a facility including a core task including a customer relevant output and a controller. The controller may include a facility description circuit to interpret a plurality of historical facility parameter values and corresponding facility outcome values and a facility prediction circuit to operate an adaptive learning system, wherein the adaptive learning system is configured to train a facility production predictor in response to the historical facility parameter values and the corresponding outcome values. The facility description circuit also interprets a plurality of present state facility parameter values, wherein the trained facility production predictor determines a customer contact indicator in response to the plurality of present state facility parameter values and a customer notification circuit provides a notification to a customer in response.

Disclosed herein are systems and methods to efficiently execute predictions models to identify future values associated with various nodes. A server retrieves a set of nodes and generates a primary prediction model using data aggregated based on all nodes. The server then executes various clustering algorithms in order to segment the nodes into different clusters. The server then generates a secondary (corrective) prediction model to calculate a correction needed to improve the results achieved by executing the primary prediction model for each cluster. When a node with unknown/limited data and attributes is identified, the server identifies a cluster most similar the new node and further identifies a corresponding secondary prediction model. The server then executes the primary prediction model in conjunction with the identified secondary prediction model to populate a graphical user interface with an accurate predicted future attribute for the new node.

An online concierge system trains a machine learning conversion model that predicts a probability of receiving an order from a user when the user accesses the online concierge system. The conversion model predicts the probability of receiving the order based on a set of input features that include price and availability information. For each access to the online concierge system, the online concierge system applies the conversion model to a current price and availability and to an optimal price availability. The online concierge system generates a metric as the difference between the two predicted probabilities of receiving an order.

Disclosed herein is a method for facilitating predicting a future value of real estate assets. The method may include receiving at least one real estate asset indication of a real estate asset from at least one user device, identifying an asset location of the real estate asset, retrieving price information of the real estate asset from a distributed ledger, retrieving one or more indexes associated with the asset location from the distributed ledger, analyzing price trend and the one or more indexes, establishing a correlation between the price trend and the one or more indexes, generating the future value for the real estate asset at a future time, transmitting the future value of the real estate asset to the at least one user device and storing one or more datasets to the distributed ledger.

Respective initial feature sets are obtained for the nodes of a graph in which the nodes represent instances of entity types and edges represent relationships. Using the initial feature sets and the graph, a graph convolutional model is trained to generate one or more types of predictions. In the model, a representation of a particular node at a particular hidden layer is based on aggregated representations of neighbor nodes, and an embedding produced at a final hidden layer is used as input to a prediction layer. The trained model is stored.

Respective initial feature sets are obtained for the nodes of a graph in which the nodes represent instances of entity types and edges represent relationships. Using the initial feature sets and the graph, a graph convolutional model is trained to generate one or more types of predictions. In the model, a representation of a particular node at a particular hidden layer is based on aggregated representations of neighbor nodes, and an embedding produced at a final hidden layer is used as input to a prediction layer. The trained model is stored.

A method for calculating sales trend of a product at a store shelf based on crowdsourcing, includes receiving, by a retail store server, availability data of a product measured on a shelf in the retail store from a portable device, where the availability data is in the form of a picture acquired of the product on the shelf, identifying products on the shelf using tags attached to the shelves, calculating sales velocity and sales trends of the product from the identified products, and transmitting the sales velocity and sales trend of the product to one or more third parties' systems in a supply chain of said retail store. Products and their locations on retail store shelves have been cataloged in a product database.

A method for calculating sales trend of a product at a store shelf based on crowdsourcing, includes receiving, by a retail store server, availability data of a product measured on a shelf in the retail store from a portable device, where the availability data is in the form of a picture acquired of the product on the shelf, identifying products on the shelf using tags attached to the shelves, calculating sales velocity and sales trends of the product from the identified products, and transmitting the sales velocity and sales trend of the product to one or more third parties' systems in a supply chain of said retail store. Products and their locations on retail store shelves have been cataloged in a product database.

Methods and apparatuses are provided for use in managing product inventory, comprising: a control circuit; a memory storing instructions to cause the control circuit to perform: obtain a reference on-hand quantity value; determine an estimated on-hand adjustment value corresponding to a predicted error between the reference on-hand quantity value and a predicted actual on-hand value; receive a retail store supplied on-hand adjustment value; set an on-hand adjustment value to the retail store supplied on-hand adjustment value when the retail store supplied on-hand adjustment value is within an on-hand variation threshold; modify the estimated on-hand adjustment value as a function of a difference between the retail store supplied on-hand adjustment value and the estimated on-hand adjustment value when the retail store supplied on-hand adjustment value is not within the on-hand variation threshold, and set the on-hand adjustment value to the modified estimated on-hand adjustment value.

The present disclosure is directed to a technique to reduce latency in feedback-based system performance determination. A system receives, from an application developer device, indications of an in-application event and a first input value for an application content delivery profile. The system receives, via an interface from an application developed by an application developer and executed by a computing device remote from the data processing system and different from the application developer device, a ping indicative of an occurrence of the in-application event on the computing device. The system merges data from the ping with internal data determined by the data processing system to generate merged data. The system determines a predicted performance for the in-application event and provides an indication of the predicted performance. The system configures, responsive to the indication of the predicted performance, the application content delivery profile with a second input value.