A tangible, non-transitory, machine-readable medium storing instructions that, when executed by a computing system, effectuate operations comprising:
- obtaining, with an artificial intelligence engine, one or more datasets out of a plurality of datasets having a plurality of interaction-event records related to providing services related to real property, wherein:
- the interaction-event records describe respective interaction events,
- the interaction events are interactions in which a first entity has experiences or obtains other information pertaining to second entity, and
- at least some of the interaction-event records are associated with respective values by which sequences of at least some of the interaction events relative to one another are ascertainable;
- obtaining, with the artificial intelligence engine, a designation of one of the interaction events in the one or more datasets as a reference event;
- obtaining, with the artificial intelligence engine, a value ascribed to the reference event by the first entity;
- selecting, with the artificial intelligence engine, a portion of an event sequence including a subset of the interaction events among which is the reference event;
- determining, using a classifier of the artificial intelligence engine, relative values for at least some interaction events in the subset;
- assigning, with the artificial intelligence engine, a value index to individual interaction events among the subset;
- determining, with the artificial intelligence engine, based on at least some of the interaction-event records, sets of event-value scores, the sets corresponding to at least some of the interaction events, wherein:
- at least some respective event-value scores are indicative of a respective value ascribed by the first entity to a respective aspect of the second entity;
- and
- at least some respective event-value scores are based on both:
- respective contributions of respective corresponding events to a subsequent event in the one or more out of the plurality of datasets, and
- a value corresponding to the value index and ascribed to a subsequent event in the one or more out of the plurality of datasets, the subsequent event occurring after the respective corresponding events;
- obtaining a machine-learning model by pitting a first machine-learning algorithm against a second machine-learning algorithm in a competition, the competition including:
- selecting the first machine-learning algorithm and the second machine-learning algorithm from a set of candidate machine-learning algorithms;
- providing a problem to both the first machine-learning algorithm and the second machine-learning algorithm;
- solving the problem with both the first machine-learning algorithm and the second machine-learning algorithm;
- and
- comparing solutions to the problem from both the first machine-learning algorithm and the second machine-learning algorithm to determine whether to include the first machine-learning algorithm or the second machine-learning algorithm in the machine-learning model;
- and
- determining sets of event-value scores comprises:
- determining initial values of at least one type of score in the sets of event-value scores;
- and
- iteratively adjusting the at least one type of score with the machine-learning model;
- and
- storing, with the artificial intelligence engine, the sets of event-value scores in memory.