Computing tool risk discovery
Risk associated with end-user computing tools can be discovered automatically. Machine learning and other approaches can be employed to automate discovery of risk associated with end-user computing tools. In one instance, a machine learning model can be constructed and fine-tuned through training that can classify end-user computing tools in terms of risk. The risk can be of a particular type, such as financial or reputational risk, and extent, such as high or low. In another instance, end-user computing tools can be subject to automatic clustering and subsequent risk assessment. Mitigation action can be performed to reduce risk associated with high-risk end-user computing tools.
1. A system, comprising:
a processor coupled to a memory that includes instructions that when executed by the processor cause the processor to:
receive a computing tool comprising a software-based spreadsheet tool created by an end user that comprises at least one mathematical calculation or logical operation;
determine a risk type associated with the computing tool, wherein the risk type comprises one of a financial risk, a reputational risk, or a regulatory risk;
determine, using a machine learning model, a risk level associated with the determined risk type of the computing tool, wherein the risk level pertains to the determined risk type, wherein the machine learning model is trained with multiple spreadsheets labeled with the risk level; and
responsive to determining that the risk level exceeds a predetermined threshold, apply a mitigation action to the computing tool.
2. The system of claim 1 , wherein the machine learning model comprises an unsupervised learning model that automatically clusters computing tools based on similarity.
3. The system of claim 1 , wherein the machine learning model comprises an artificial neural network.
4. The system of claim 1 , wherein the machine learning model comprises a product of supervised learning and a classification process.
5. The system of claim 1 , wherein the mitigation action further comprises application of a control to monitor the computing tool.
6. The system of claim 1 , the memory further comprising instructions that, when executed by the processor, cause the processor to locate the computing tool and pre-process the computing tool prior to providing the computing tool to the machine learning model.
7. The system of claim 1 , wherein the machine learning model is adapted from an industry standard model.
8. The system of claim 7 , wherein the industry standard model corresponds to financial services.
9. A method, comprising:
executing, on a processor, instructions that cause the processor to perform operations comprising:
receiving a spreadsheet, wherein the spreadsheet comprises a software-based computing tool created by an end user that includes at least one mathematical calculation or logical operation;
determining a risk type associated with the computing tool, wherein the risk type comprises one of a financial risk, a reputational risk, or a regulatory risk;
determining, using a machine learning model, a risk level associated with the spreadsheet, wherein the risk level pertains to the determined risk type, wherein the machine learning model is trained with multiple spreadsheets labeled with the risk level; and
responsive to determining that the risk level exceeds a predetermined threshold, applying a mitigation action to the spreadsheet.
10. The method of claim 9 , wherein the operations further comprise forwarding the spreadsheet to an individual for manual review if the determined risk level exceeds a first predetermined value associated with low risk and is below a second predetermined value associated with high risk.
11. The method of claim 9 , wherein determining the risk type further comprises determining an extent of risk.
12. A non-transitory computer readable medium comprising program code that when executed by one or more processors causes the one or more processors to:
receive a computing tool comprising a software-based spreadsheet tool created by an end user that comprises at least one mathematical calculation or logical operation;
determine a risk type associated with the computing tool, wherein the risk type comprises one of a financial risk, a reputational risk, or a regulatory risk;
determine, using a machine learning model, a risk level associated with the determined risk type of the computing tool, wherein the risk level pertains to the determined risk type, wherein the machine learning model is trained with multiple spreadsheets labeled with the risk level; and
responsive to determining that the risk level exceeds a predetermined threshold, apply a mitigation action to the computing tool.
13. The non-transitory computer readable medium of claim 12 , wherein the machine learning model comprises an unsupervised learning model that automatically clusters computing tools based on similarity.
14. The non-transitory computer readable medium of claim 12 , wherein the machine learning model comprises an artificial neural network.
15. The non-transitory computer readable medium of claim 12 , wherein the machine learning model comprises a product of supervised learning and a classification process.
16. The non-transitory computer readable medium of claim 12 , wherein the mitigation action further comprises application of a control to monitor the computing tool.