Abstract: Generating a synthetic dataset from road vehicle positioning data. The method involves iteratively selecting a seed record and determining a set of candidate partner records based on matching bigrams between the selected seed record and potential partner records. The method further includes determining subsequences for the candidate partner records and selected seed record based on locations of the matching bigrams. A candidate partner record is selected based on whether a length difference, in terms of time, distance, or number of road events, between the subsequences is less than a defined threshold. The subsequence of the selected seed record is replaced with the subsequence of the selected candidate partner record to produce a mutated seed record. The mutated seed records to produce a synthetic dataset.

Abstract: Relates to improving accuracy of a primary predictive model based on a residual model. A method includes determining, using a primary predictive model, a first set of training prediction residuals based on a first labeled training set and a first set of testing prediction residuals based on a first labeled testing set. A second dataset includes a second labeled training set, labeled based on the first set of training prediction residuals, and a second labeled testing set, labeled based on the first set of testing prediction residuals. The method further includes training the residual model using the second labeled training set. The primary predictive model is adjusted based on a set of training predictions and a set of testing predictions of the residual model to produce more accurate predictions.

Abstract: Generating a synthetic dataset from road vehicle positioning data. The method involves iteratively selecting a seed record and determining a set of candidate partner records based on matching bigrams between the selected seed record and potential partner records. The method further includes determining subsequences for the candidate partner records and selected seed record based on locations of the matching bigrams. A candidate partner record is selected based on whether a length difference, in terms of time, distance, or number of road events, between the subsequences is less than a defined threshold. The subsequence of the selected seed record is replaced with the subsequence of the selected candidate partner record to produce a mutated seed record. The mutated seed records to produce a synthetic dataset.