Auto-segmentation of non-fungible tokens using machine learning

A method comprising:

• at a computing platform comprising at least one processor, a communication interface, and memory:
• training, based on historical non-fungible tokens (NFTs) and historical tier scores, a first model, wherein training the first model configures the first model to output tier scores corresponding to NFTs;
• training, based on historical NFT information corresponding to the historical NFTs, a second model, wherein training the second model configures the second model to output NFT validation ratings corresponding to NFTs;
• generating, based on a first NFT and user information and using the first model, a first tier score corresponding to the first NFT;
• comparing the first tier score to a tier threshold in order to identify storage rules, wherein the storage rules direct the computing platform to:
• based on identifying that the first tier score meets or exceeds the tier threshold, adding a new entry, corresponding to the first NFT, to a distributed ledger;
• and
• based on identifying that the first tier score is less than the tier threshold, store the first NFT in the memory;
• modifying, based on a change in the first tier score to a second tier score, a storage location of the first NFT, wherein modifying the storage location of the first NFT comprises:
• based on identifying that the second tier score meets or exceeds the tier threshold and previously was less than the tier threshold, shifting, the first NFT to a cloud computing platform;
• and
• based on identifying that the second tier score is less than the tier threshold and previously met or exceeded the tier threshold, shifting, the first NFT to the memory;
• generating, using the second model and based on the first NFT, an NFT validation rating for the first NFT;
• refining, based on the NFT validation rating and the NFT information, the second model;
• and
• refining, based on the first tier score, the second tier score, and the first NFT, the first model.

One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, a communication interface, and memory, causing the computing platform to:

• train, based on historical non-fungible tokens (NFTs) and historical tier scores, a first model, wherein training the first model configures the first model to output tier scores corresponding to NFTs;
• train, based on historical NFT information corresponding to the historical NFTs, a second model, wherein training the second model configures the second model to output NFT validation ratings corresponding to NFTs;
• generate, based on a first NFT and user information and using the first model, a first tier score corresponding to the first NFT;
• compare the first tier score to a tier threshold in order to identify storage rules, wherein the storage rules direct the computing platform to:
• based on identifying that the first tier score meets or exceeds the tier threshold and previously was less than the tier threshold, adding a new entry, corresponding to the first NFT, to a distributed ledger;
• and
• based on identifying that the first tier score is less than the tier threshold and previously met or exceeded the tier threshold, store the first NFT in the memory;
• modify, based on a change in the first tier score to a second tier score, a storage location of the first NFT, wherein modifying the storage location of the first NFT comprises:
• based on identifying that the second tier score meets or exceeds the tier threshold, shifting, the first NFT to a cloud computing platform;
• and
• based on identifying that the second tier score is less than the tier threshold, shifting, the first NFT to the memory;
• generate, using the second model and based on the first NFT, an NFT validation rating for the first NFT;
• refine, based on the NFT validation rating and the NFT information, the second model;
• and
• refine, based on the first tier score, the second tier score, and the first NFT, the first model.