Abstract: Pipeline information regarding real estate construction jobs may be obtained from a data feed. A new real estate development associated with a specified job type, and a building identification number for the new real estate development may be identified from the pipeline information. Additional information regarding the new real estate development may be obtained by sending a query that includes the building identification number to a data source. A geographic area and a unit type associated with the new real estate development may be determined based on information regarding the new real estate development. User data may be analyzed to identify a user interested in pipeline information associated with the geographic area and the unit type. An electronic message regarding the new real estate development may be sent to the user.

Abstract: A unit type selection may be obtained and a training data set may be determined based on the unit type. A plurality of real estate value estimating neural networks may be trained using the training data set. A testing data set may be determined based on the unit type and the plurality of real estate value estimating neural networks may be tested on the testing data set. Based on the testing, a subset of the best performing neural networks may be selected to create a set of real estate value estimating neural networks. Each neural network in the set of real estate value estimating neural networks may be retrained on the worst performing subset of the training data set for the respective neural network.