| CPC G06F 16/215 (2019.01) [G06F 16/287 (2019.01)] | 20 Claims |

|
1. A system for improved precision in detecting false-positive changepoints in time-series data, the system comprising:
one or more processors; and
one or more non-transitory, computer-readable mediums comprising instructions that when executed by the one or more processors cause operations comprising:
receiving a first dataset of time-series datapoints, wherein each datapoint in the time-series datapoints corresponds to a specific time stamp;
generating for display, in a user interface, a first changepoint detected in the first dataset, wherein the first changepoint comprises a first datapoint in a first segment of the time-series datapoints that comprises a different data distribution than a second segment of the time-series datapoints;
receiving, via the user interface, a first user input of a first category of known values for the first dataset;
receiving, via the user interface, a second user input of a second category of the first changepoint;
based on the first category and the second category, selecting a first model from a plurality of models for determining whether the first changepoint corresponds to a first false-positive changepoint, wherein each model of the plurality of models comprises a different algorithm for detecting false-positive changepoints;
in response to selecting the first model, processing, using the first model, the first changepoint and a value of the known values to determine a first output; and
generating for display, in a user interface, a first recommendation based on the first output, wherein the first recommendation indicates whether the first changepoint corresponds to the first false-positive changepoint.
|