Data record anomaly reconciliation using machine learning models

1. A method, comprising:

obtaining a data record comprising a plurality of line items;

assigning each of the line items in the data record to a given cluster, of a plurality of clusters, of similar line items to determine a line item neighborhood score for each line item based on a comparison of a given line item to other available line items in the assigned cluster;

applying a plurality of features of the data record to a machine learning model to determine a data record score for the data record based on a combination of the line item neighborhood scores for each line item in the data record, wherein the data record score indicates a likelihood that the data record will be anomalous;

identifying one or more anomalies in the data record based on one or more of the data record score and the line item neighborhood score for each line item in the data record; and

adjusting one or more parameters of one or more of the plurality of line items of the data record to address the one or more anomalies identified in the data record to produce a reconciled data record, based on one or more of the line item neighborhood scores and one or more predefined adjustment rules;

wherein the method is performed by at least one processing device comprising a processor coupled to a memory.

2. The method of claim 1 , wherein the step of applying the plurality of features of the data record to the machine learning model further comprises using a plurality of trained quality metrics to determine the data record score.

3. The method of claim 1 , wherein the data record score for the data record indicates a likelihood that the data record will be approved.

4. The method of claim 1 , wherein the data record score for the data record compares a quality of the data record in comparison to a plurality of similar historical data records, based on one or more predefined similarity criteria.

5. The method of claim 1 , wherein the line item neighborhood score for each line item is determined for a combination of geographic region and product.

6. The method of claim 1 , further comprising providing a user with one or more predefined factors that contribute to the one or more of the data record score and the line item neighborhood score for each line item.

7. The method of claim 1 , wherein the data record is an order quotation and wherein the one or more predefined adjustment rules maintain one or more of a total price and a total margin of the order quotation.

8. The method of claim 7 , wherein the one or more line items having one or more parameters that are adjusted are selected based on the respective line item neighborhood score.

9. A computer program product, comprising a tangible machine-readable storage medium having encoded therein executable code of one or more software programs, wherein the one or more software programs when executed by at least one processing device perform the following steps:

obtaining a data record comprising a plurality of line items;

assigning each of the line items in the data record to a given cluster, of a plurality of clusters, of similar line items to determine a line item neighborhood score for each line item based on a comparison of a given line item to other available line items in the assigned cluster;

applying a plurality of features of the data record to a machine learning model to determine a data record score for the data record based on a combination of the line item neighborhood scores for each line item in the data record, wherein the data record score indicates a likelihood that the data record will be anomalous;

identifying one or more anomalies in the data record based on one or more of the data record score and the line item neighborhood score for each line item in the data record; and

adjusting one or more parameters of one or more of the plurality of line items of the data record to address the one or more anomalies identified in the data record to produce a reconciled data record, based on one or more of the line item neighborhood scores and one or more predefined adjustment rules.

10. The computer program product of claim 9 , wherein the step of applying the plurality of features of the data record to the machine learning model further comprises using a plurality of trained quality metrics to determine the data record score.

11. The computer program product of claim 9 , wherein the data record score for the data record indicates a likelihood that the data record will be approved.

12. The computer program product of claim 9 , wherein the data record score for the data record compares a quality of the data record in comparison to a plurality of similar historical data records, based on one or more predefined similarity criteria.

13. The computer program product of claim 9 , further comprising providing a user with one or more predefined factors that contribute to the one or more of the data record score and the line item neighborhood score for each line item.

14. The computer program product of claim 9 , wherein the data record is an order quotation and wherein the one or more predefined adjustment rules maintain one or more of a total price and a total margin of the order quotation, and wherein the one or more line items having one or more parameters that are adjusted are selected based on the respective line item neighborhood score.

15. An apparatus, comprising:

a memory; and

at least one processing device, coupled to the memory, operative to implement the following steps:

obtaining a data record comprising a plurality of line items;

assigning each of the line items in the data record to a given cluster, of a plurality of clusters, of similar line items to determine a line item neighborhood score for each line item based on a comparison of a given line item to other available line items in the assigned cluster;

applying a plurality of features of the data record to a machine learning model to determine a data record score for the data record based on a combination of the line item neighborhood scores for each line item in the data record, wherein the data record score indicates a likelihood that the data record will be anomalous;

identifying one or more anomalies in the data record based on one or more of the data record score and the line item neighborhood score for each line item in the data record; and

adjusting one or more parameters of one or more of the plurality of line items of the data record to address the one or more anomalies identified in the data record to produce a reconciled data record, based on one or more of the line item neighborhood scores and one or more predefined adjustment rules.

16. The apparatus of claim 15 , wherein the step of applying the plurality of features of the data record to the machine learning model further comprises using a plurality of trained quality metrics to determine the data record score.

17. The apparatus of claim 15 , wherein the data record score for the data record indicates a likelihood that the data record will be approved.

18. The apparatus of claim 15 , wherein the data record score for the data record compares a quality of the data record in comparison to a plurality of similar historical data records, based on one or more predefined similarity criteria.

19. The apparatus of claim 15 , further comprising providing a user with one or more predefined factors that contribute to the one or more of the data record score and the line item neighborhood score for each line item.

20. The apparatus of claim 15 , wherein the data record is an order quotation and wherein the one or more predefined adjustment rules maintain one or more of a total price and a total margin of the order quotation, and wherein the one or more line items having one or more parameters that are adjusted are selected based on the respective line item neighborhood score.