Claims:WE CLAIM
1. A machine learning prediction system, comprising:
a hardware processor; and
a memory storing instructions executable by the hardware processor for:
obtaining, via the hardware processor, for a supply chain, identifiers for one or more supply chain contributors, one or more supply chain parameters including a supply chain type and an identification of a supply chain process flow; and one or more user parameters including a user query;
performing, via the hardware processor, a natural language processing algorithm on the user query to extract one or more text components including: one or more keywords, one or more names, one or more nouns, and one or more named entities;
analyzing, via the hardware processor, the extracted text components to identify one or more supply chain component clusters;
identifying, via the hardware processor, one or more risk identifiers by comparing the extracted text components to risk identifiers included in the one or more supply chain component clusters;
executing, via the hardware processor, a machine learning technique for learning of the one or more identified risk identifiers;
generating, via the hardware processor, one or more co-occurrence rules between the identified risk identifiers, as well as associated rule support and rule confidence parameters;
sorting, via the hardware processor, the one or more co-occurrence rules to generate a prioritized rules list;
generating, via the hardware processor, a risk prediction model for the supply chain using the prioritized rules list, using a classifier algorithm;
training, via the hardware processor, the risk prediction model using a machine learning techniques for incremental learning; and
generating, via the hardware processor, a supply chain element modification using the trained risk prediction model.

2. The system of claim 1, the memory further storing instructions executable by the hardware processor for:
deleting, via the hardware processor, one or more words from the user query using a text analyzing algorithm.

3. The system of claim 2, wherein the text analyzing algorithm is further utilized to identify at least one co-reference relationship between two or more sentences included in the user query.

4. The system of claim 1, wherein the one or more co-occurrence rules are generated based on a apriori item-set generation algorithm.

5. The system of claim 1, the memory further storing instructions executable by the hardware processor for:
storing, via the hardware processor, the one or more identified risk identifiers in a structured database.

6. The system of claim 1, wherein generating, via the hardware processor, the risk prediction model uses a probabilistic classifier algorithm.

7. The system of claim 1, the memory further storing instructions executable by the hardware processor for:
upon detecting presence of a predicted risk in the supply chain, providing an alert for the one or more supply chain contributors.

8. A machine learning prediction method, comprising:
obtaining, via a hardware processor, for a supply chain, identifiers for one or more supply chain contributors, one or more supply chain parameters including a supply chain type and an identification of a supply chain process flow; and one or more user parameters including a user query;
performing, via the hardware processor, a natural language processing algorithm on the user query to extract one or more text components including: one or more keywords, one or more names, one or more nouns, and one or more named entities;
analyzing, via the hardware processor, the extracted text components to identify one or more supply chain component clusters;
identifying, via the hardware processor, one or more risk identifiers by comparing the extracted text components to risk identifiers included in the one or more supply chain component clusters;
executing, via the hardware processor, a machine learning technique for learning of the one or more identified risk identifiers;
generating, via the hardware processor, one or more co-occurrence rules between the identified risk identifiers, as well as associated rule support and rule confidence parameters;
sorting, via the hardware processor, the one or more co-occurrence rules to generate a prioritized rules list;
generating, via the hardware processor, a risk prediction model for the supply chain using the prioritized rules list, using a classifier algorithm;
training, via the hardware processor, the risk prediction model using a machine learning techniques for incremental learning; and
generating, via the hardware processor, a supply chain element modification using the trained risk prediction model.

9. The method of claim 8, further comprising:
deleting, via the hardware processor, one or more words from the user query using a text analyzing algorithm.

10. The method of claim 9, wherein the text analyzing algorithm is further utilized to identify at least one co-reference relationship between two or more sentences included in the user query.

11. The method of claim 8, wherein the one or more co-occurrence rules are generated based on a apriori item-set generation algorithm.

12. The method of claim 8, further comprising:
storing, via the hardware processor, the one or more identified risk identifiers in a structured database.

13. The method of claim 8, wherein generating, via the hardware processor, the risk prediction model uses a probabilistic classifier algorithm.

14. The method of claim 8, further comprising:
upon detecting presence of a predicted risk in the supply chain, providing an alert for the one or more supply chain contributors.

Dated this 11th day of March, 2016

Swetha SN
Of K&S Partners
Agent for the Applicant
, Description:TECHNICAL FIELD
This disclosure relates generally to machine learning, and more particularly to system and method for predicting and managing the risks in a supply chain network.