System for dynamic data aggregation and prediction for assessment of electronic non-fungible resources
Systems, computer program products, and methods are described herein for dynamic data aggregation and prediction for assessment of electronic non-fungible resources. The present invention is configured to receive, from a user input device, a request to predict an assessment of an NFT for a resource at a first time; capture, using a ML subsystem, one or more attributes associated with the NFT; trigger a vectorization engine to map the one or more attributes represented in the one or more data formats into a vector array; train, using the ML subsystem, an ML model using the vector array of the one or more attributes; generate, using the ML subsystem, a trained ML model based on at least the training; predict, using the trained ML model, the assessment of the NFT at the first time; and store the predicted assessment of the NFT at the first time in an assessment repository.
1 . A system for dynamic data aggregation and prediction for assessment of electronic non-fungible resources, the system comprising:
at least one non-transitory storage device; and
at least one processor coupled to the at least one non-transitory storage device,
wherein the at least one processor is configured to:
receive, from a user input device, a request to predict an assessment of a non-fungible token (NFT) for a resource at a first time;
capture, using a machine learning (ML) subsystem, one or more attributes associated with the NFT, wherein the one or more attributes are represented in one or more data formats, the one or more attributes comprises at least one or more mentions of identifiable engagement terminology associated with the NFT on one or more external sources, wherein the one or mor external sources comprises at least one or more web-based platforms;
extract, using the ML subsystem, polarity information and sentiment associated with the NFT from the one or more identifiable engagement terminology, wherein extracting further comprises:
identifying, using a web-crawler orchestrator, the one or more web-based platforms;
scheduling, using a job scheduler, an extraction strategy to detect the one or more identifiable engagement terminology from the one or more web-based platforms; and
triggering an information extractor to fetch the one or more identifiable engagement terminology from the one or more web-based platforms;
map, using the vectorization engine, the polarity information and sentiment into the vector array;
trigger, using the ML subsystem, a vectorization engine to map the polarity information and sentiment into a vector array;
train, using the ML subsystem, an ML model using the vector array;
generate, using the ML subsystem, a trained ML model based on at least the training;
predict, using the trained ML model, the assessment of the NFT at the first time; and
store the predicted assessment of the NFT at the first time in an assessment repository.
2 . The system of claim 1 , wherein the at least one processor is further configured to:
capture an actual assessment of the NFT at the first time;
ingest, using the ML subsystem, the actual assessment of the NFT at the first time to tune the trained ML model; and
tune, using the ML subsystem, the trained ML model using the actual assessment of the NFT at the first time.
3 . The system of claim 2 , wherein the at least one processor is further configured to:
retrieve, from the assessment repository, the predicted assessment of the NFT at the first time;
determine that the actual assessment of the NFT at the first time does not match the predicted assessment of the NFT at the first time; and
generate correction parameters based on at least determining that the actual assessment of the NFT at the first time does not match the predicted assessment of the NFT at the first time.
4 . The system of claim 3 , wherein the at least one processor is further configured to:
ingest, using the ML subsystem, the correction parameters to tune the trained ML model; and
tune, using the ML subsystem, the trained ML model using the correction parameters.
5 . The system of claim 1 , wherein the one or more attributes comprises at least at least security status level of a distributed ledger associated with the NFT, metadata storage type, lifetime of the NFT, information associated with a community of the NFT, information associated with a creator of the NFT, NFT scarcity, ownership history of the NFT, value of the resource associated with the NFT, utility of the NFT in virtual mediums, and/or previously recorded assessment of the NFT.
6 . A computer program product for dynamic data aggregation and prediction for assessment of electronic non-fungible resources, the computer program product comprising a non-transitory computer-readable medium comprising code causing a first apparatus to:
receive, from a user input device, a request to predict an assessment of a non-fungible token (NFT) for a resource at a first time;
capture, using a machine learning (ML) subsystem, one or more attributes associated with the NFT, wherein the one or more attributes are represented in one or more data formats, the one or more attributes comprises at least one or more mentions of identifiable engagement terminology associated with the NFT on one or more external sources, wherein the one or mor external sources comprises at least one or more web-based platforms;
extract, using the ML subsystem, polarity information and sentiment associated with the NFT from the one or more identifiable engagement terminology, wherein extracting further comprises:
identifying, using a web-crawler orchestrator, the one or more web-based platforms;
scheduling, using a job scheduler, an extraction strategy to detect the one or more identifiable engagement terminology from the one or more web-based platforms; and
triggering an information extractor to fetch the one or more identifiable engagement terminology from the one or more web-based platforms;
map, using the vectorization engine, the polarity information and sentiment into the vector array;
trigger, using the ML subsystem, a vectorization engine to map the polarity information and sentiment into a vector array;
train, using the ML subsystem, an ML model using the vector array;
generate, using the ML subsystem, a trained ML model based on at least the training;
predict, using the trained ML model, the assessment of the NFT at the first time; and
store the predicted assessment of the NFT at the first time in an assessment repository.
7 . The computer program product of claim 6 , wherein the first apparatus is further configured to:
capture an actual assessment of the NFT at the first time;
ingest, using the ML subsystem, the actual assessment of the NFT at the first time to tune the trained ML model; and
tune, using the ML subsystem, the trained ML model using the actual assessment of the NFT at the first time.
8 . The computer program product of claim 7 , wherein the first apparatus is further configured to:
retrieve, from the assessment repository, the predicted assessment of the NFT at the first time;
determine that the actual assessment of the NFT at the first time does not match the predicted assessment of the NFT at the first time; and
generate correction parameters based on at least determining that the actual assessment of the NFT at the first time does not match the predicted assessment of the NFT at the first time.
9 . The computer program product of claim 8 , wherein the first apparatus is further configured to:
ingest, using the ML subsystem, the correction parameters to tune the trained ML model; and
tune, using the ML subsystem, the trained ML model using the correction parameters.
10 . The computer program product of claim 6 , wherein the one or more attributes comprises at least at least security status level of a distributed ledger associated with the NFT, metadata storage type, lifetime of the NFT, information associated with a community of the NFT, information associated with a creator of the NFT, NFT scarcity, ownership history of the NFT, value of the resource associated with the NFT, utility of the NFT in virtual mediums, and/or previously recorded assessment of the NFT.
11 . A method for dynamic data aggregation and prediction for assessment of electronic non-fungible resources, the method comprising:
receiving, from a user input device, a request to predict an assessment of a non-fungible token (NFT) for a resource at a first time;
capturing, using a machine learning (ML) subsystem, one or more attributes associated with the NFT, wherein the one or more attributes are represented in one or more data formats, the one or more attributes comprises at least one or more mentions of identifiable engagement terminology associated with the NFT on one or more external sources, wherein the one or mor external sources comprises at least one or more web-based platforms;
extracting, using the ML subsystem, polarity information and sentiment associated with the NFT from the one or more identifiable engagement terminology, wherein extracting further comprises:
identifying, using a web-crawler orchestrator, the one or more web-based platforms;
scheduling, using a job scheduler, an extraction strategy to detect the one or more identifiable engagement terminology from the one or more web-based platforms; and
triggering an information extractor to fetch the one or more identifiable engagement terminology from the one or more web-based platforms;
mapping, using the vectorization engine, the polarity information and sentiment into the vector array;
triggering, using the ML subsystem, a vectorization engine to map the polarity information and sentiment into a vector array;
training, using the ML subsystem, an ML model using the vector array;
generating, using the ML subsystem, a trained ML model based on at least the training;
predicting, using the trained ML model, the assessment of the NFT at the first time; and
storing the predicted assessment of the NFT at the first time in an assessment repository.