Model mining and recommendation engine with simulation interfaces

A cloud infrastructure system comprising:

• a processor;
• and
• a non-transitory computer-readable medium including instructions that, when executed by the processor, cause the processor to:
• obtain a dataset from a client device;
• process the dataset to parse data identifying features of the dataset;
• compare the parsed data with terms associated with each of a plurality of models in a domain ontology store to identify a number of terms for each of the plurality of models that correspond with the parsed data for the dataset, each of the plurality of models associated with a domain grouping a portion of the plurality of models with a common attribute;
• identify one or more recommended models of the plurality of models based on the identified number of terms for each of the plurality of models that correspond with the parsed data;
• provide the one or more recommended models to the client device;
• receive a selection of a first recommended model of the one or more recommended models from the client device;
• responsive to receiving the selection of the first recommended model, execute a simulation of a portion of the dataset using the first recommended model to output a set of output data;
• provide the set of output data to the client device
• obtain a response message specifying an approval or a rejection of the first recommended model from the client device,
• wherein responsive to determining that the response message indicates the rejection of the first recommended model:
• provide an updated listing of the one or more recommended models without the first recommended model to the client device;
• obtain a selection of a second recommended model of the one or more recommended models provided in the updated listing;
• execute a second simulation of the portion of the dataset using the second recommended model to output a second set of output data;
• and
• provide the second set of output data to the client device.

A non-transitory computer-readable medium including stored thereon a sequence of instructions which, when executed by a processor causes the processor to execute a process, the process comprising:

• obtaining a dataset from a client device;
• parsing portions of the dataset to derive a set of parsed data for the dataset;
• comparing the set of parsed data with terms associated with each of a plurality of models stored in a domain ontology store of a model catalog to identify a number of terms for each of the plurality of models that correspond with the set of parsed data for the dataset;
• identifying one or more recommended models of the plurality of models based on a comparison the set of parsed data with terms associated with each of a plurality of models stored in a domain ontology store of the model catalog identifying a number of terms for each of the plurality of models that correspond with the set of parsed data for the dataset;
• providing the one or more recommended models to the client device;
• obtaining a selection of a first recommended model of the one or more recommended models;
• executing a simulation of a portion of the dataset using the first recommended model to output a set of output data;
• providing the set of output data to the client device
• obtaining a response message specifying an approval or a rejection of the first recommended model from the client device,
• wherein responsive to determining that the response message indicates the rejection of the first recommended model:
• providing an updated listing of the one or more recommended models without the first recommended model to the client device;
• obtaining a selection of a second recommended model of the one or more recommended models provided in the updated listing;
• executing a second simulation of the portion of the dataset using the second recommended model to output a second set of output data;
• and
• providing the second set of output data to the client device.