Systems and methods for determining data criticality based on causal evaluation
Techniques described herein relate to methods and systems for determining data asset criticality. Such techniques may include making a first determination that a plurality of data asset attributes are part of a causal attribute set; calculating a SHapeley Additive explanation (SHAP) value for each of the plurality of data asset attributes in the causal attribute set; and performing a weighted mean calculation using the SHAP values for each of the plurality of data asset attributes and a corresponding attribute value for each of the plurality of data asset attributes of a data asset to obtain a criticality score for the data asset.
1 . A method for determining data asset criticality, the method comprising:
making a first determination that a plurality of data asset attributes are part of a causal attribute set;
calculating a SHapley Additive explanation (SHAP) value for each of the plurality of data asset attributes in the causal attribute set;
performing a weighted mean calculation using the SHAP values for each of the plurality of data asset attributes and a corresponding attribute value for each of the plurality of data asset attributes of a data asset to obtain a criticality score for the data asset;
including the data asset in a ranking of data assets using the criticality score; and
classifying the data asset into a criticality classification based on a criticality threshold;
generating a backup recommendation set based on the criticality classification,
wherein the backup recommendation set comprises backup actions comprising at least one selected from a group consisting of a key rotation frequency adjustment, a backup retention adjustment, a backup storage type adjustment, and a backup storage location adjustment; and
adjusting an attribute of the data asset to include a backup action of the backup actions.
2 . The method of claim 1 , wherein making the first determination that the plurality of data asset attributes are part of the causal attribute set comprises:
performing a data category value calculation using a historical attribute set of a plurality of data assets to obtain a plurality of data category values for a plurality of data assets; and
performing a causal inference analysis using the historical attribute set, a causal graph, and the plurality of data category values to obtain the causal attribute set.
3 . The method of claim 2 , wherein the data category value calculation comprises a linear regression analysis.
4 . The method of claim 2 , wherein the causal graph is a directed acyclic graph (DAG).
5 . The method of claim 1 , wherein, before the weighted mean calculation, the SHAP values are scaled to values between zero and one.
6 . A non-transitory computer readable medium comprising computer readable program code, which when executed by a computer processor enables the computer processor to perform a method for determining data asset criticality, the method comprising:
making a first determination that a plurality of data asset attributes are part of a causal attribute set;
calculating a SHapley Additive explanation (SHAP) value for each of the plurality of data asset attributes in the causal attribute set; and
performing a weighted mean calculation using the SHAP values for each of the plurality of data asset attributes and a corresponding attribute value for each of the plurality of data asset attributes of a data asset to obtain a criticality score for the data asset;
including the data asset in a ranking of data assets using the criticality score; and
classifying the data asset into a criticality classification based on a criticality threshold;
generating a backup recommendation set based on the criticality classification,
wherein the backup recommendation set comprises backup actions comprising at least one selected from a group consisting of a key rotation frequency adjustment, a backup retention adjustment, a backup storage type adjustment, and a backup storage location adjustment; and
adjusting an attribute of the data asset to include a backup action of the backup actions.
7 . The non-transitory computer readable medium of claim 6 , wherein making the first determination that the plurality of data asset attributes are part of the causal attribute set comprises:
performing a data category value calculation using a historical attribute set of a plurality of data assets to obtain a plurality of data category values for a plurality of data assets; and
performing a causal inference analysis using the historical attribute set, a causal graph, and the plurality of data category values to obtain the causal attribute set.
8 . The non-transitory computer readable medium of claim 7 , wherein the data category value calculation comprises a linear regression analysis.
9 . The non-transitory computer readable medium of claim 7 , wherein the causal graph is a directed acyclic graph (DAG).
10 . The non-transitory computer readable medium of claim 6 , wherein, before the weighted mean calculation, the SHAP values are scaled to values between zero and one.
11 . A system for determining data asset criticality, the system comprising:
a data valuator, comprising a processor, memory, and a storage device, operatively connected to a plurality of data assets, and configured to:
make a first determination that a plurality of data asset attributes are part of a causal attribute set;
calculate a SHapley Additive explanation (SHAP) value for each of the plurality of data asset attributes in the causal attribute set; and
perform a weighted mean calculation using the SHAP values for each of the plurality of data asset attributes and a corresponding attribute value for each of the plurality of data asset attributes of a data asset to obtain a criticality score for the data asset;
include the data asset in a ranking of data assets using the criticality score; and
classify the data asset into a criticality classification based on a criticality threshold;
generate a backup recommendation set based on the criticality classification,
wherein the backup recommendation set comprises backup actions comprising at least one selected from a group consisting of a key rotation frequency adjustment, a backup retention adjustment, a backup storage type adjustment, and a backup storage location adjustment; and
adjust an attribute of the data asset to include a backup action of the backup actions.
12 . The system of claim 11 , wherein, to make the first determination that the plurality of data asset attributes are part of the causal attribute set, the data valuator is further configured to:
perform a data category value calculation using a historical attribute set of a plurality of data assets to obtain a plurality of data category values for a plurality of data assets; and
perform a causal inference analysis using the historical attribute set, a causal graph, and the plurality of data category values to obtain the causal attribute set.
13 . The system of claim 12 , wherein the data category value calculation comprises a linear regression analysis, and the causal graph is a directed acyclic graph (DAG).
14 . The system of claim 11 , wherein, before the weighted mean calculation, the SHAP values are scaled to values between zero and one.