| CPC G06Q 10/0635 (2013.01) [G06F 16/215 (2019.01); G06N 20/00 (2019.01); G06Q 10/06375 (2013.01); G06Q 10/06393 (2013.01); G06Q 30/018 (2013.01); G06Q 30/0201 (2013.01); G06Q 30/0202 (2013.01)] | 15 Claims |
|
1. A processor-implemented method comprising:
receiving, via one or more hardware processors, data related to one or more suppliers, and data related to one or more sustainability impact factors from one or more internal data sources and one or more external data sources wherein the one or more suppliers, the one or more sustainability impact factors are associated with an industry segment;
pre-processing, via the one or more hardware processors, the data related to the one or more sustainability impact factors by performing a data validation, a data harmonization and a data curation process;
assigning, via the one or more hardware processors, weights to the one or more sustainability impact factors based on the industry segment and the data related to the one or more suppliers;
generating, via the one or more hardware processors, one or more key performance indictors based on the one or more sustainability impact factors along with the assigned weights using a decision matrix;
training, via the one or more hardware processors, an artificial intelligence model to estimate a sustainability risk assessment for the one or more suppliers based on the data related to the one or more suppliers and the one or more key performance indicators using a ridge regression technique, wherein the sustainability risk assessment is estimated by forecasting risk for the one or more sustainability impact factors through a weighted risk calculation method, wherein the artificial intelligence model returns the weighted risk according to type and volume of commodity sourced;
performing, via the one or more hardware processors, a scenario-based analysis to provide one or more recommendations by analyzing the data related to the one or more suppliers, estimated sustainability risk assessment and the one or more key performance indicators,wherein the scenario-based analysis is performed by automatically capturing geo-coordinates and mapping data from the geo-coordinates using Geographic Information System (GIS) on vector data of baseline water stress value (BWS);
providing, via the one or more hardware processors, the one or more recommendations on a user interface for switching the one or more suppliers based on the scenario-based analysis, wherein the user interface is a personalized user interface (UI) and logging into the UI by a user, and the user is at least one of a central digital, analytics, a procurement, a supply chain and sustainability teams;
utilizing, via the one or more hardware processors, a natural language understanding (NLU) AI algorithm to intelligently map the industry segment to the one or more sustainability impact factors and assign relevant weights as per use case definition, wherein the (NLU) based artificial intelligence (AI) algorithm is created to aid procurement decisions to avoid upstream supply chain disruptions by forecasting alternate supplier scenarios to meet sustainability goals;
creating, via the one or more hardware processors, map mashups to provide a dynamic view of location based risks based on the industry segment;
performing, via the one or more hardware processors, location mapping to integrate geo coordinate based sustainability impact factors with values derived from buffer and overlay point-in-polygon analysis of variables related to a target location;
using, via the one or more hardware processors, a conversational system based on the NLU AI algorithm to capture data related to the one or more suppliers;
capturing, via the one or more hardware processors, exact location details of the one or more suppliers by picking raster data around given radius of the one or more suppliers; and
providing via the one or more hardware processors, validated, cleansed and harmonized real-time data from the one or more external and internal data sources.
|