Model-based data validation
Various embodiments herein each include at least one of systems, methods, and software for model-based data validation to identify when self-scan checkout data requires validation. Some embodiments, in the form of a method includes receiving, via a network from a self-scanning device, a self-scan dataset of items for purchase within a purchase data processing transaction and evaluating the self-scan dataset to determine whether to require a rescan of items represented in the self-scan dataset. In such embodiments when a rescan is determined to be required, the method includes transmitting via the network to at least one of the self-scan device and at least one device of a store employee data indicating a rescan is required. However, when a rescan is not determined to be required, the method includes permitting the purchase data processing transaction to proceed.
1. A method comprising:
receiving, via a network from a self-scanning device, a self-scan dataset of items for purchase within a purchase data processing transaction;
evaluating the self-scan dataset to determine whether to require a rescan of items represented in the self-scan dataset by classifying the self-scan dataset based at least upon a transaction classification model generated by a machine learning algorithm processing of completed transaction data that included data of transactions with un-scanned items that were identified through rescanning;
when a rescan is determined to be required, transmitting via the network to at least one of the self-scan device and at least one device of a store employee data indicating a rescan is required; and
when a rescan is not determined to be required, permitting the purchase data processing transaction to proceed.
2. The method of claim 1 , wherein the completed transaction data processed by the machine learning algorithm includes data representative of scanning behaviors of items scanned and added to the self-scan dataset and subsequently removed prior to submission of the self-scan dataset within the purchase data processing transaction.
3. The method of claim 1 , wherein evaluating the self-scan dataset to determine whether to require a rescan of items represented in the self-scan dataset further includes applying one or more configurable rules.
4. The method of claim 3 , wherein the one or more configurable rules include at least one of:
a transaction trigger that identifies a data condition with regard to one or more data items that trigger a rescan requirement when present within a self-scan dataset;
periodic and random rescan requirements with regard to all transactions;
periodic and random rescan requirements with regard to a known customer;
periodic and random rescan requirements with regard to an unknown customer; and
a data input by an employee requiring a rescan.
5. The method of claim 4 , wherein periodic and random rescan requirements of known customers are influenced by a determined trust level of respective customers that are influenced at least in part by a history of prior transactions including at least one item identified through rescanning.
6. The method of claim 1 , wherein the data indicating a rescan is required includes a transaction interrupt to prevent the purchase transaction from proceeding until input is received from an authorized store employee.
7. The method of claim 1 , wherein:
the data indicating a rescan is required includes a command that prevents a customer from making a payment to complete the purchase data processing transaction; and
permitting the purchase data processing transaction to proceed includes transmitting data to the self-scanning device to instruct a user of the self-scanning device to make a payment.
8. The method of claim 1 , wherein the self-scanning device is a customer mobile device.
9. A method comprising:
generating and storing a fraud predictive model based on historic transaction data including data of at least some transactions known to include fraud and indicated as such within the historic transaction data;
receiving, via a network from a self-scanning device, a self-scan dataset of items for purchase within a purchase transaction;
evaluating the self-scan dataset based on the fraud predictive model to determine whether to require a rescan of items represented in the self-scan dataset;
when a rescan is determined to be required, transmitting via the network to at least one of the self-scan device and at least one device of a store employee data indicating a rescan is required; and
when a rescan is not determined to be required, permitting the purchase data processing transaction to proceed.
10. The method of claim 9 , wherein:
the fraud predictive model is generated through execution of a machine learning algorithm with regard to the historic transaction data; and
the fraud predictive model is periodically updated based on transaction data of transactions that occur subsequent to a last generation of the fraud predictive model.
11. The method of claim 10 , wherein the transaction data processed by the machine learning algorithm includes data representative of scanning behaviors of items scanned and added to the self-scan dataset and subsequently removed prior to submission of the self-scan dataset within the purchase data processing transaction.
12. The method of claim 9 , wherein evaluating the self-scan dataset to determine whether to require a rescan of items represented in the self-scan dataset further includes applying one or more configurable rules.
13. The method of claim 12 , wherein the one or more configurable rules include at least one of:
a transaction trigger that identifies a data condition with regard to one or more data items that trigger a rescan requirement when present within a self-scan dataset;
periodic and random rescan requirements with regard to all transactions;
periodic and random rescan requirements with regard to a known customer;
periodic and random rescan requirements with regard to an unknown customer; and
a data input by an employee requiring a rescan.
14. The method of claim 13 , wherein periodic and random rescan requirements of known customers are influenced by a determined trust level of respective customers that are influenced at least in part by a history of prior transactions including at least one item identified through rescanning.
15. The method of claim 9 , wherein the self-scan device is a store provided device.
16. A system comprising:
at least one processor;
a network interface device;
at least one memory device storing instructions executable by the at least one processor to perform data processing activities comprising:
receiving, via the network interface device from a self-scanning device, a self-scan dataset of items for purchase within a purchase data processing transaction;
evaluating the self-scan dataset to determine whether to require a rescan of items represented in the self-scan dataset by classifying the self-scan dataset based at least upon a transaction classification model generated by a machine learning algorithm processing of completed transaction data that included data of transactions with un-scanned items that were identified through rescanning;
when a rescan is determined to be required, transmitting via the network interface device to at least one of the self-scan device and at least one device of a device of a store employee data indicating a rescan is required; and
when a rescan is not determined to be required, permitting the purchase data processing transaction to proceed.
17. The system of claim 16 , wherein permitting the purchase transaction to proceed includes transmitting data via network interface device to at least the self-scanning device.