Distance points interactive interface and related methods

A computer-implemented method for predicting a plurality of future reachable locations, the method comprising:

• determining a number of distance points connected to a person at a point in time;
• identifying a plurality of journey possibilities for each journey host of a plurality of journey hosts, based on the number of distance points;
• providing past expenditure data of the person and the number of distance points as inputs to a first machine learning model trained to output predicted future distance points of the person based on the past expenditure data of the person and the number of distance points, wherein the first machine learning model is a supervised learning model trained using sample transaction data and corresponding sample future distance points;
• receiving a first machine learning output comprising the predicted future distance points from the first machine learning model;
• determining a plurality of predicted reachable locations based on the predicted future distance points, the plurality of predicted reachable locations comprising at least a subset of the plurality of journey possibilities correlated to the predicted future distance points;
• identifying one or more previous locations of a device associated with the person;
• providing the past expenditure data of the person as an input to a second machine learning model trained to output personal attributes of the person based on the past expenditure data of the person, wherein the second machine learning model is trained using one of a supervised or partially supervised sample expenditure data and associated sample personal attributes;
• receiving a second machine learning output comprising the personal attributes of the person;
• identifying a subset of the predicted reachable locations based on the previous locations of the device and attributes of the predicted reachable locations matching with the personal attributes;
• and
• causing display of a graphical interface comprising the subset of the predicted reachable locations on a map.

A computer-implemented method for predicting a plurality of future reachable locations, the method comprising:

• receiving past expenditure data of a person;
• providing the past expenditure data of the person as an input to a first machine learning model trained to output predicted future distance points of the person based on the past expenditure data of the person, wherein the first machine learning model is a supervised learning model trained using sample transaction data and corresponding sample future distance points;
• receiving a first machine learning output comprising the predicted future distance points from the first machine learning model;
• determining a plurality of predicted reachable locations based on the predicted future distance points;
• receiving content from a social media account associated with the person;
• determining a personal preference based on the content;
• providing the past expenditure data of the person as an input to a second machine learning model trained to output personal attributes of the person based on the past expenditure data of the person, wherein the second machine learning model is trained using one of a supervised or partially supervised sample expenditure data and associated sample personal attributes;
• receiving a second machine learning output comprising the personal attributes of the person;
• identifying a subset of the predicted reachable locations based on attributes of the predicted reachable locations matching with at least one of the personal attributes or the personal preferences;
• and
• causing display of a graphical interface comprising the subset of the predicted reachable locations on a map.

A system comprising:

• a data storage device storing processor-readable instructions;
• and
• a processor operatively connected to the data storage device and configured to execute the instructions to perform operations that include:
• receiving past expenditure data of a person;
• providing the past expenditure data of the person as an input to a first machine learning model trained to output predicted future distance points of the person based on the past expenditure data of the person, wherein the first machine learning model is a supervised learning model trained using sample transaction data and corresponding sample future distance points;
• receiving a first machine learning output comprising the predicted future distance points from the first machine learning model;
• determining a plurality of predicted reachable locations based on the predicted future distance points;
• providing the past expenditure data of the person as an input to a second machine learning model trained to output personal attributes of the person based on the past expenditure data of the person, wherein the second machine learning model is trained using one of a supervised or partially supervised sample expenditure data and associated sample personal attributes;
• receiving a second machine learning output comprising the personal attributes of the person;
• identifying a subset of the predicted reachable locations based on attributes of the predicted reachable locations matching with the personal attributes;
• and
• causing display of a graphical interface comprising the subset of the predicted reachable locations on a map.