# US 12,118,494 B1 · System and method for mitigating risk associated with a machine-generated forecast > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,118,494 B1 - Document ID: US12118494B1 - Status: Granted - Kind: B1 - Application number: 18/531,183 - Filed: 2023-12-06 - Granted: 2024-10-15 - Earliest claimed: 2023-09-25 - Assignees: Asper.AI Inc. - Applicants: Asper.AI Inc. - Inventors: Guha Athreya; Yadunath Gupta; Vibhor Mishra; Pooja Jayaprakash; Raul Jurado - Web page: https://patentgrep.com/patent/US12118494B1 ## CPC - G06Q 10/0635: Risk analysis of enterprise or organisation activities - G06Q 10/04: Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202) - G06Q 30/0202: Market predictions or forecasting for commercial activities - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract A system and a method for mitigating risk associated with a machine-generated forecast. The system may receive data comprising at least one of product attributes, historical demand for a set of Stock Keeping Units (SKUs), a machine-generated forecast for the set of SKUs, and historical forecast adjustment for the set of SKUs. Further, the system may determine one or more metrics based on the received data. The one or more metrics are fed to a risk analyzer model. A Demand Planning Risk Index (DPRI) score for an SKU from the set of SKUs may be generated using the risk analyzer model. The DPRI score indicates a risk quotient for the SKU. Further, a forecast adjustment for the SKU with a high risk quotient may be recommended to mitigate the risk associated with the machine-generated forecast of the SKU. ## Claims ### Claim 1 A method for mitigating risk associated with a machine-generated forecast, the method comprises: receiving data comprising at least one of product attributes, historical demand for a set of Stock Keeping Units (SKUs), a machine-generated forecast for the set of SKUs, and historical forecast adjustment for the set of SKUs; determining one or more metrics based on the received data, wherein the one or more metrics comprises an accuracy, a bias, a difference between accuracy of an adjusted forecast of an SKU when compared to the machine-generated forecast of the SKU; training a risk analyzer model using a machine learning algorithm, wherein the machine learning algorithm is trained based on two or more of the determined metrics and labeled data of the set of SKUs categorized into one or more risk classes comprising a high risk and a low risk, and wherein the risk analyzer model is configured to generate a Demand Planning Risk Index (DPRI) score indicating a risk quotient for respective SKUs of the set of SKU; generating a Demand Planning Risk Index (DPRI) score for one or more SKUs from the set of SKUs using the risk analyzer model; identifying the one or more SKUs with high-risk quotient based on respective DPRI scores exceeding a threshold risk quotient; and recommending a forecast adjustment for the identified one or more SKUs with high risk quotient to mitigate the risk associated with the machine-generated forecast of those SKU. ### Claim 2 (depends on 1) The method of claim 1, wherein the one or more metrics further comprise an average actual demand, an average machine-generated forecasted demand, and a difference in the machine-generated forecast of last two times. ### Claim 3 (depends on 1) The method of claim 1, wherein generating the DPRI score for the SKU further comprises classifying, based on the risk quotient, the one or more SKUs between a high risk and a low risk. ### Claim 4 (depends on 3) The method of claim 3, wherein classifying the one or more SKUs further comprises assessing the machine-generated forecast of the one or more SKU with high risk with a pre-defined set of rules to identify one or more reasons for the one or more SKU being classified as the high risk. ### Claim 5 (depends on 4) The method of claim 4, further comprises ranking the one or more reasons based on relevancy using a machine learning model. ### Claim 6 (depends on 1) The method of claim 1, wherein a low DPRI score indicates a low risk associated with the one or more SKUs, and wherein the one or more SKUs with the low DPRI score is classified as a low touch. ### Claim 7 (depends on 1) The method of claim 1, wherein a high DPRI score indicates a high risk associated with the one or more SKU, and wherein the one or more SKUs with the high DPRI score is classified as a high touch. ### Claim 8 A system for mitigating risk associated with a machine-generated forecast comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute program instructions stored in the memory to: receive data comprising at least one of product attributes, historical demand for a set of Stock Keeping Units (SKUs), a machine-generated forecast for the set of SKUs, and historical forecast adjustment for the set of SKUs; determine one or more metrics based on the received data, wherein the one or more metrics comprises an accuracy, a bias, a difference between accuracy of an adjusted forecast of an SKU when compared to the machine-generated forecast of the SKU; training a risk analyzer model using a machine learning algorithm, wherein the machine learning algorithm is trained based on two or more of the determined metrics and labeled data of the set of SKUs categorized into one or more risk classes comprising a high risk and a low risk, and wherein the risk analyzer model is configured to generate a Demand Planning Risk Index (DPRI) score indicating a risk quotient for respective SKUs of the set of SKU; generate a Demand Planning Risk Index (DPRI) score for one or more SKUs from the set of SKUs using the risk analyzer model; identifying one or more SKUs with high-risk quotient based on respective DPRI scores exceeding a threshold risk quotient; and recommend a forecast adjustment for the identified one or more SKUs with a high risk quotient to mitigate the risk associated with the machine-generated forecast of those SKU. ### Claim 9 (depends on 8) The system of claim 8, wherein the one or more metrics comprise an average actual demand, an average machine-generated forecasted demand, and a difference in the machine-generated forecast of last two times. ### Claim 10 (depends on 8) The system of claim 8, wherein generating the DPRI score for the one or more SKUs further comprises classifying, based on the risk quotient, the one or more SKUs between a high risk and a low risk. ### Claim 11 (depends on 10) The system of claim 10, wherein classifying the one or more SKUs further comprises assessing the machine-generated forecast of the one or more SKUs with high risk with a pre-defined set of rules to identify one or more reasons for the one or more SKUs being classified as the high risk. ### Claim 12 (depends on 11) The system of claim 11, further comprises ranking the one or more reasons based on relevancy using a machine learning model. ### Claim 13 (depends on 8) The system of claim 8, wherein a low DPRI score indicates a low risk associated with the one or more SKUs, and wherein the one or more SKUs with the low DPRI score is classified as a low touch. ### Claim 14 (depends on 8) The system of claim 8, wherein a high DPRI score indicates a high risk associated with the one or more SKUs, and wherein the one or more SKUs with the high DPRI score is classified as a high touch. ### Claim 15 A non-transitory computer program product having embodied thereon a computer program for mitigating risk associated with a machine-generated forecast, the computer program product storing instructions for: receiving data comprising at least one of product attributes, historical demand for a set of Stock Keeping Units (SKUs), a machine-generated forecast for the set of SKUs, and historical forecast adjustment for the set of SKUs; determining one or more metrics based on the received data, wherein the one or more metrics comprises an accuracy, a bias, a difference between accuracy of an adjusted forecast of an SKU when compared to the machine-generated forecast of the SKU; training a risk analyzer model using a machine learning algorithm, wherein the machine learning algorithm is trained based on two or more of the determined metrics and labeled data of the set of SKUs categorized into one or more risk classes comprising a high risk and a low risk, and wherein the risk analyzer model is configured to generate a Demand Planning Risk Index (DPRI) score indicating a risk quotient for respective SKUs of the set of SKU; generating a Demand Planning Risk Index (DPRI) score for an SKU from the set of SKUs using the risk analyzer model; identifying one or more SKUs with high-risk quotient based on respective DPRI scores exceeding a threshold risk quotient; and recommending a forecast adjustment for the identified one or more SKUs with a high risk quotient to mitigate the risk associated with the machine-generated forecast of those SKUS. ### Claim 16 (depends on 1) The method of claim 1, wherein recommend the forecast adjustment comprises: identify one or more reasons for each high-risk SKU being classified as high-risk; access a stored set of recommended forecast adjustments mapped to the one or more reasons for an SKU being classified as high-risk; and select, from the stored set, at least one recommended forecast adjustment corresponding to the identified one or more reasons for each high-risk SKU. ### Claim 17 (depends on 8) The system of claim 8, wherein recommending the forecast adjustment comprises: identifying one or more reasons for each high-risk SKU being classified as high-risk; accessing a stored set of recommended forecast adjustments mapped to the one or more reasons for an SKU being classified as high-risk; and selecting, from the stored set, at least one recommended forecast adjustment corresponding to the identified one or more reasons for each high-risk SKU.