Visualizing feature variation effects on computer model prediction
A model visualization system analyzes model behavior to identify clusters of data instances with similar behavior. For a selected feature, data instances are modified to set the selected feature to different values evaluated by a model to determine corresponding model outputs. The feature values and outputs may be visualized in an instance-feature variation plot. The instance-feature variation plots for the different data instances may be clustered to identify latent differences in behavior of the model with respect to different data instances when varying the selected feature. The number of clusters for the clustering may be automatically determined, and the clusters may be further explored by identifying another feature which may explain the different behavior of the model for the clusters, or by identifying outlier data instances in the clusters.
1. A system for visualizing feature variation effects on computer model prediction, comprising:
a processor; and
a computer-readable medium having instructions executable by the processor for:
identifying a trained computer model configured to generate an output value based on an input having a plurality of features;
identifying a data set having a plurality of data instances, each data instance having a feature vector corresponding to the plurality of features;
for each data instance in the plurality of data instances, generating an associated instance-feature variation plot describing model outputs of the trained computer model for a range of values for a first feature in the feature vector for the data instance;
clustering the plurality of data instances to a plurality of clusters based on the associated instance-feature variation plots, each cluster describing data instances having similar model outputs with respect to the range of values for the first feature;
labeling each of the plurality of data instances with the respective cluster associated with the instance;
training an interpretation model to output predicted membership of a data instance in one or more clusters of the plurality of clusters based on features of the plurality of features other than the first feature with training data including the plurality of data instances using the associated cluster label as the output to be learned by the interpretation model;
determining, based on the trained interpretation model, a second feature of the plurality of features, different from the first feature, and a decision value of the second feature that predicts membership in a first cluster of the plurality of clusters relative to a second cluster of the plurality of clusters, such that the second feature and decision value most correlate with the cluster membership describing data instances having similar model outputs of the trained computer model for the range of values for the first feature; and
providing the clustered data instances for display to a user to view the effects of the first feature on the model outputs and an indication of the decision value of the second feature.
2. The system of claim 1 , wherein the plurality of data instances is clustered with k-means clustering.
3. The system of claim 1 , wherein a number of the plurality of clusters is automatically determined based on a statistical metric.
4. The system of claim 1 , wherein the instructions are further executable for:
identifying an outlier data instance of a cluster of the plurality of clusters; and
providing information about the outlier data instance for display to the user.
5. The system of claim 1 , wherein the interpretation model is a decision tree and wherein the second feature and the decision value are determined based a decision node of the decision tree.
6. The system of claim 1 , wherein the instructions are further executable for providing a visual display of second feature values of the data instances associated with each cluster of the plurality of clusters.
7. The system of claim 1 , wherein the instructions are further executable for:
comparing the plurality of clusters of the data set with a second plurality of clusters generated for instance-feature variation plots for the first feature of the model applied to another plurality of instances associated with a second data set;
determining that the data set and the second data set are sufficiently different based on the comparison; and
responsive to determining that the data set and second data set are sufficiently different, retraining the trained computer model with the second data set.
8. A method for visualizing feature variation effects on computer model prediction, comprising:
identifying a trained computer model configured to generate an output value based on an input having a plurality of features;
identifying a data set having a plurality of data instances, each data instance having a feature vector corresponding to the plurality of features;
for each data instance in the plurality of data instances, generating an associated instance-feature variation plot describing model outputs of the trained computer model for a range of values for a first feature in the feature vector for the data instance;
clustering the plurality of data instances to a plurality of clusters based on the associated instance-feature variation plots, each cluster describing data instances having similar model outputs with respect to the range of values for the first feature;
labeling each of the plurality of data instances with the respective cluster associated with the instance;
training an interpretation model to output predicted membership of a data instance in one or more of the plurality of clusters based on features of the plurality of features other than the first feature with training data including the plurality of data instances using the associated cluster label as the output to be learned by the interpretation model;
determining, based on the trained interpretation model, a second feature of the plurality of features, different from the first feature, and a decision value of the second feature that predicts membership in a first cluster of the plurality of clusters relative to a second cluster of the plurality of clusters, such that the second feature and decision value most correlate with the cluster membership describing data instances having similar model outputs of the trained computer model for the range of values for the first feature; and
providing the clustered data instances for display to a user to view the effects of the first feature on the model outputs and an indication of the decision value of the second feature.
9. The method of claim 8 , wherein the plurality of data instances is clustered with k-means clustering.
10. The method of claim 8 , wherein a number of the plurality of clusters is automatically determined based on a statistical metric.
11. The method of claim 8 , further comprising:
identifying an outlier data instance of a cluster of the plurality of clusters; and
providing information about the outlier data instance for display to the user.
12. The method of claim 8 , wherein the interpretation model is a decision tree and wherein the second feature and the decision value are determined based a decision node of the decision tree.
13. The method of claim 8 , further comprising providing a visual display of second feature values of the data instances associated with each cluster of the plurality of clusters.
14. The method of claim 8 , further comprising:
comparing the plurality of clusters of the data set with a second plurality of clusters generated for instance-feature variation plots for the first feature of the model applied to another plurality of instances associated with a second data set;
determining that the data set and the second data set are sufficiently different based on the comparison; and
responsive to determining that the data set and second data set are sufficiently different, retraining the trained computer model with the second data set.
15. A non-transitory computer-readable medium for visualizing feature variation effects on computer model prediction, the non-transitory computer-readable medium comprising instructions executable by a processor for:
identifying a data set having a plurality of data instances, each data instance having a feature vector corresponding to a plurality of features;
for each data instance in the plurality of data instances, generating an associated instance-feature variation plot describing model outputs of the trained computer model for a range of values for a first feature in the feature vector for the data instance;
clustering the plurality of data instances to a plurality of clusters based on the associated instance-feature variation plots, each cluster describing data instances having similar model outputs with respect to the range of values for the first feature;
training an interpretation model to output predicted membership of a data instance in one or more clusters of the plurality of clusters based on features of the plurality of features other than the first feature with training data including the plurality of data instances using the associated cluster label as the output to be learned by the interpretation model;
determining, based on the trained interpretation model, a second feature of the plurality of features, different from the first feature, and a decision value of the second feature that predicts membership in a first cluster of the plurality of clusters relative to a second cluster of the plurality of clusters, such that the second feature and decision value most correlate with the cluster membership describing data instances having similar model outputs of the trained computer model for the range of values for the first feature; and
providing the clustered data instances for display to a user to view the effects of the first feature on the model outputs and an indication of the decision value of the second feature.
16. The non-transitory computer-readable medium of claim 15 , wherein the plurality of data instances is clustered with k-means clustering.
17. The non-transitory computer-readable medium of claim 15 , wherein a number of the plurality of clusters is automatically determined based on a statistical metric.
18. The non-transitory computer-readable medium of claim 15 , wherein the instructions are further executable for:
identifying an outlier data instance of a cluster of the plurality of clusters; and
providing information about the outlier data instance for display to the user.
19. The non-transitory computer-readable medium of claim 15 , wherein the interpretation model is a decision tree and wherein the second feature and the decision value are determined based a decision node of the decision tree.
20. The non-transitory computer-readable medium of claim 15 , wherein the instructions are further executable for:
comparing the plurality of clusters of the data set with a second plurality of clusters generated for instance-feature variation plots for the first feature of the model applied to another plurality of instances associated with a second data set;
determining that the data set and the second data set are sufficiently different based on the comparison; and
responsive to determining that the data set and second data set are sufficiently different, retraining the trained computer model with the second data set.