Dynamic transaction card optimization
The present disclosure relates to devices and methods relating to an optimized electronic transaction card where various data inputs associated with a dynamic transaction card optimize operational configurations and/or a user experience of the dynamic transaction card to extend an energy storage life of the dynamic transaction card, promote various behaviors, and/or detect system and/or device defects. A dynamic transaction card may include a dynamic transaction card with various configuration and/or functionality that use the power components (e.g., printed circuit board (PCB), energy storage component, battery, and/or the like) of the dynamic transaction card. The configuration and/or functionality data may include, for example, sensor input, connection data, transaction data, display data, and/or the like. The configuration and/or functionality data may then be used to determine optimal configuration settings.
1. A dynamic transaction card comprising:
a microcontroller within the dynamic transaction card;
data storage within the dynamic transaction card storing optimal configurations; wherein:
the microcontroller:
monitors a plurality of hardware components of the dynamic transaction card in order to determine functionality data and a plurality of software configurations used to derive configuration data;
transmits, via a network, the functionality data and configuration data to a processor configured to use machine learning to cluster the functionality and/or configuration data to process the functionality data and configuration data with respect to a user group segment;
receives, via the network, optimal configuration data from the processor; and
applies the optimal configurations to the dynamic transaction card.
2. The dynamic transaction card of claim 1 , wherein the processor calculates the optimal configuration data by maximizing energy storage length using the functionality data and configuration data as variables.
3. The dynamic transaction card of claim 1 , wherein the processor calculates the optimal configuration data by determining a desired user behavior, determining a probability that a particular functionality data and a particular configuration data results in the desired user behavior, and where the probability is higher than a predetermined threshold, assigning the configuration data as the optimal configuration data.
4. The dynamic transaction card of claim 1 , further comprising a sensor that monitors a plurality of hardware components of the dynamic transaction card in order to determine functionality data and a plurality of software configurations in order to determine configuration data.
5. The dynamic transaction card of claim 4 , wherein the functionality data and configuration data comprise sensor input, connection data, transaction data, and/or display data.
6. The dynamic transaction card of claim 1 , wherein the optimal configurations are calculated at the processor by determining a desired user behavior, determining a probability that a particular functionality data and a particular configuration data results in the desired user behavior, and where the probability is higher than a predetermined threshold, assigning the configuration data as the optimal configuration data.
7. The dynamic transaction card of claim 1 , wherein the dynamic transaction card and/or data storage associated with a merchant system, a backend system and/or a mobile device stores functionality data and/or configuration data.
8. The dynamic transaction card of claim 1 , wherein the optimal configurations are calculated at the processor by linear regression, logistic regression, ridge regression, lasso regression, Bayesian regression, and/or machine learning algorithms.
9. The dynamic transaction card of claim 1 , wherein the optimal configurations are calculated on a transaction card basis, a grouping of transaction card basis, and/or an entirety of transaction card basis.
10. The dynamic transaction card of claim 1 , wherein the functionality and configuration data are optimized to determine a maximum number of transaction attempts.
11. The dynamic transaction card of claim 1 , wherein the microcontroller transmits functionality data, configuration data and/or optimal configurations at a timed interval and/or on an event basis.
12. The dynamic transaction card of claim 1 , wherein the optimal configurations are pushed to the dynamic transaction card using a EuroPay-MasterCard-Visa (EMV) Issuer script.
13. The dynamic transaction card of claim 1 , wherein the microcontroller continuously monitors the functionality data, configuration data, and/or optimal configurations.
14. The dynamic transaction card of claim 1 , wherein the processor detects system and/or device defects by determining outlier data associated with dynamic transaction card data and outlier data associated with functionality and/or configuration data.
15. The dynamic transaction card of claim 14 , wherein the outlier data is transmitted via a network to the dynamic transaction card, a backend system and/or a mobile device associated with the dynamic transaction card.
16. A method, comprising:
monitoring, using a microcontroller within a dynamic transaction card, a plurality of hardware components of the dynamic transaction card in order to determine functionality data and a plurality of software configurations used to derive configuration data;
transmitting, via a network, the functionality data and configuration data to a processor;
utilizing machine learning to cluster functionality and/or configuration data to process the functionality data and configuration data with respect to a user group segment;
calculating, using a processor, optimal configuration data;
storing, in data storage within the dynamic transaction card, the optimal configurations; and
applying, using the microcontroller, the optimal configurations to the dynamic transaction card.
17. The method of claim 16 , wherein the optimal configurations are calculated at the processor by maximizing energy storage length using the functionality data and configuration data as variables.
18. The method of claim 16 , wherein the optimal configurations are calculated at the processor by determining a desired user behavior, determining a probability that a particular functionality data and a particular configuration data results in the desired user behavior, and where the probability is higher than a predetermined threshold, assigning the configuration data as the optimal configuration data.
19. The method of claim 16 , wherein the functionality data and configuration data comprise sensor input, connection data, transaction data, and/or display data.
20. The method of claim 16 , further comprising storing the functionality data and/or configuration data in the dynamic transaction card and/or data storage associated with a merchant system, a backend system and/or a mobile device.
21. The method of claim 16 , wherein the optimal configurations are calculated at the processor by linear regression, logistic regression, ridge regression, lasso regression, Bayesian regression, and/or machine learning algorithms.
22. The method of claim 16 , wherein the optimal configurations are calculated on a transaction card basis, a grouping of transaction card basis, and/or an entirety of transaction card basis.
23. The method of claim 16 , wherein the functionality and configuration data are optimized to determine a maximum number of transaction attempts.
24. The method of claim 16 , wherein the transmitting of functionality data, configuration data and/or optimal configurations are performed at a timed interval and/or on an event basis.
25. The method of claim 16 , further comprising pushing the optimal configurations to the dynamic transaction card using a EuroPay-MasterCard-Visa (EMV) Issuer script.
26. The method of claim 25 , further comprising applying the EMV Issuer script during the completion of a transaction via contacts of an EMV chip within the dynamic transaction card.
27. The method of claim 16 , further comprising continuously monitoring the functionality data, configuration data, and/or optimal configurations.
28. The method of claim 16 , further comprising detecting system and/or device defects by determining outlier data associated with dynamic transaction card data and outlier data associated with functionality and/or configuration data.
29. The method of claim 28 , further comprising transmitting the outlier data via a network to the dynamic transaction card, a backend system and/or a mobile device associated with the dynamic transaction card.