Abstract: Technology described herein identifies a person condition associated with a person, where the person condition is associated with a diagnosis of the person, and further where the person condition is associated with an affliction of the person. The technology receives a person input associated with a person preference of the person, determines a first path that extends between a source and a first destination based on the person input and the person condition, determines a first path condition associated with the first path based on the person condition and transmits the first path and the first path condition to a computing device associated with the person. The computing device has a digital interface to display the first path and the first path condition.

Abstract: Methods and systems for selecting a deep learning/machine learning model are described. In one embodiment, a plurality of models are optimized by addressing class imbalances among a first subset of records, each of the plurality of models are trained using the first subset of records, each of the plurality of models are implemented to predict a value of respective known target columns in each of a second subset of records, respective success rates for each of the plurality of models at predicting the respective known target columns for each of the second subset of records are determined, a first of the plurality of models having a highest success rate is selected, and the first of the plurality of models is implemented to decide a target column of a received authorization request based on predictor columns in the received authorization request.

Abstract: Methods and systems for selecting a deep learning/machine learning model are described. In one embodiment, a plurality of models are optimized by addressing class imbalances among a first subset of records, each of the plurality of models are trained using the first subset of records, each of the plurality of models are implemented to predict a value of respective known target columns in each of a second subset of records, respective success rates for each of the plurality of models at predicting the respective known target columns for each of the second subset of records are determined, a first of the plurality of models having a highest success rate is selected, and the first of the plurality of models is implemented to decide a target column of a received authorization request based on predictor columns in the received authorization request.

Abstract: Methods and systems for selecting a deep learning/machine learning model are described. In one embodiment, a plurality of models are trained using the first subset of records, each of the plurality of models are implemented to predict a value of respective known target columns in each of a second subset of records, respective success rates for each of the plurality of models at predicting the respective known target columns for each of the second subset of records are determined, a subset plurality of the plurality of models based on success rate is selected, and the subset plurality of the plurality of models is implemented to decide a target column of a received authorization request based on variables in the received authorization request using a democratic process.

Abstract: Technology identifies at least one object part of provided data from an object repository that corresponds to provided objects that were provided from the object repository, and extrapolates a first attribute associated with a condition based on the at least one object part. The technology receives a request for a first object associated with a first user and the condition. The technology determines whether to execute an automatic process to determine whether to permit the request based on the first attribute, when the automatic process is determined to be executed to determine whether to permit the request, automatically analyzes user data of the first user and an object attribute associated with the first object to determine whether to permit the request, and when the automatic process is determined not to be executed, assigning the request to a queue for a manual review to determine whether to permit the request.