Predicting the value of an asset using machine-learning techniques

A non-transitory computer readable storage medium comprising stored instructions, which when executed by at least one processor, cause the processor to:

• extract intrinsic data from a physical asset, the intrinsic data including an identifier of the asset, a subject of the asset, and a time associated with the asset;
• compile a set of extrinsic data based on the intrinsic data, the extrinsic data acquired through a web scraping of data associated with the intrinsic data;
• generate a principal component vector comprising the intrinsic data and the extrinsic data;
• input the principal component vector into a machine learning model, wherein the machine learning model is trained using a training dataset comprising training data, each entry of training data including an aggregation of principal components of a physical asset as labeled by a historical classification and a time associated with the entry;
• receive, as output from the machine learning model, a classification of the physical asset corresponding to a present time;
• and
• provide, for display to a user, the classification in visual association with a representation of the physical asset.

A system comprising:

• a plurality of computing devices comprising a provider device and at least one consumer device, the provider device configured to capture images;
• and
• an asset valuation platform configured to:
• receive, from the provider device, an image of a physical asset;
• extract intrinsic data from the image of the physical asset, the intrinsic data including an identifier of the asset, a subject of the asset, and a time associated with the asset;
• compile a set of extrinsic data based on the intrinsic data, the extrinsic data acquired through a web scraping of data associated with the intrinsic data;
• generate a principal component vector comprising the intrinsic data and the extrinsic data;
• input the principal component vector into a machine learning model, wherein the machine learning model is trained using a training dataset comprising training data, each entry of training data including an aggregation of principal components of a physical asset as labeled by a historical classification and a time associated with the entry;
• receive, as output from the machine learning model, a classification of the physical asset corresponding to a present time;
• and
• provide, for display to a user, the classification in visual association with a representation of the physical asset.