Outlier discovery system selection
Systems, device and techniques are disclosed for outlier discovery system selection. A set of time series data including time series data objects may be received. A sample of time series data objects may be extracted from the time series data. The sample of time series data objects may be decomposed into sub-components. Statistical classification may be used to select an outlier discovery system based on the sub-components. A neural network may be used to select an outlier discovery system based on the sub-components. A level of error of the neural network may be determined based on a comparison of the outlier discovery system selection made using statistical classification and the outlier discovery system selection made by the neural network. Weight of the neural network may be updated based on the level of error of the neural network.
1. A computer-implemented method comprising:
receiving a set of time series data comprising time series data objects;
extracting a sample of time series data objects from the time series data;
decomposing the sample of time series data objects into sub-components;
selecting, using statistical classification, an outlier discovery system based on the sub-components;
selecting, using a neural network, an outlier discovery system based on the sub-components;
determining a level of error of the neural network based on a comparison of the outlier discovery system selection made using statistical classification and the outlier discovery system selection made by the neural network; and
updating weights of the neural network based on the level of error of the neural network.
2. The computer-implemented method of claim 1 , further comprising:
receiving a second set of time series data comprising time series data objects;
extracting a second sample of time series data objects from the second set of time series data;
decomposing the second sample of time series data objects into sub-components; and
selecting, using the neural network, an outlier discovery system based on the sub-components decomposed from the second sample of time series data objects.
3. The computer-implemented method of claim 2 , further comprising:
applying the outlier discovery system selected by the neural network based on the sub-components decomposed from the second sample of time series data objects to the second set of time series data to determine whether one or more of the time series data objects in the second set of time series data comprise outlying data.
4. The computer-implemented method of claim 3 , further comprising:
determining at least one corrective action when the one or more of the time series data objects in the second set of time series data are determined to comprise outlying data.
5. The computer-implemented method of claim 2 , further comprising receiving input evaluating the outlier discovery system selected using the neural network.
6. The computer-implemented method of claim 2 , wherein the time series data objects of the second set of time series data comprise data associated with either hardware or software of one or more computing devices.
7. The computer-implemented method of claim 1 , further comprising:
storing the sub-components and the outlier discovery system selection made using statistical classification in a database, and wherein the neural network receives the sub-components from the database.
8. The computer-implemented method of claim 1 , further comprising receiving input evaluating the outlier discovery system selection made using statistical classification.
9. The computer-implemented method of claim 1 , further comprising:
receiving configuration data associated with the set of time series data; and
extracting a sample of the configuration data, wherein the selecting, using statistical classification, an outlier discovery system based on the sub-components is also based on the sample of the configuration data.
10. The computer-implemented system of claim 1 , wherein the processor further receives a second set of time series data comprising time series data objects, extracts a second sample of time series data objects from the second set of time series data, decomposes the second sample of time series data objects into sub-components, selects, using the neural network, an outlier discovery system based on the sub-components decomposed from the second sample of time series data objects.
11. The computer-implemented system of claim 10 , wherein the processor further applies the outlier discovery system selected by the neural network based on the sub-components decomposed from the second sample of time series data objects to the second set of time series data to determine whether one or more of the time series data objects in the second set of time series data comprise outlying data.
12. The computer-implemented system of claim 11 , wherein the processor further determines at least one corrective action when the one or more of the time series data objects in the second set of time series data are determined to comprise outlying data.
13. The computer-implemented system of claim 10 , wherein the processor further receives input evaluating the outlier discovery system selected using the neural network.
14. The computer-implemented system of claim 10 , wherein the time series data objects of the second set of time series data comprise data associated with either hardware or software of one or more computing devices.
15. The computer-implemented system of claim 1 , wherein the processor further stores the sub-components and the outlier discovery system selection made using statistical classification in a database stored on the one or more storage devices, and wherein the neural network receives the sub-components from the database.
16. A computer-implemented system for outlier discovery system selection comprising:
one or more storage devices; and
a processor that receives a set of time series data comprising time series data objects, extracts a sample of time series data objects from the time series data, decomposes the sample of time series data objects into sub-components, selects, using statistical classification, an outlier discovery system based on the sub-components, selects, using a neural network, an outlier discovery system based on the sub-components, determines a level of error of the neural network based on a comparison of the outlier discovery system selection made using statistical classification and the outlier discovery system selection made by the neural network and update weights of the neural network based on the level of error of the neural network.
17. The computer-implemented system of claim 16 , wherein the processor further receives input evaluating the outlier discovery system selection made using statistical classification.
18. The computer-implemented system of claim 16 , wherein the processor further receives configuration data associated with the set of time series data, and extracts a sample of the configuration data, wherein the selecting, using statistical classification, an outlier discovery system based on the sub-components is also based on the sample of the configuration data.
19. A system comprising: one or more computers and one or more storage devices storing instructions which are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
receiving a set of time series data comprising time series data objects;
extracting a sample of time series data objects from the time series data;
decomposing the sample of time series data objects into sub-components;
selecting, using statistical classification, an outlier discovery system based on the sub-components;
selecting, using a neural network, an outlier discovery system based on the sub-components;
determining a level of error of the neural network based on a comparison of the outlier discovery system selection made using statistical classification and the outlier discovery system selection made by the neural network; and
updating weights of the neural network based on the level of error of the neural network.
20. The system of claim 19 , wherein the instructions further cause the one or more computers to perform operations further comprising:
receiving a second set of time series data comprising time series data objects;
extracting a second sample of time series data objects from the second set of time series data;
decomposing the second sample of time series data objects into sub-components; and
selecting, using the neural network, an outlier discovery system based on the sub-components decomposed from the second sample of time series data objects.