Method and system for ATM cash servicing and optimization

• US 10,395,199 B1
• Filed: 10/17/2014
• Issued: 08/27/2019
• Est. Priority Date: 10/17/2014
• Status: Active Grant

• Current Assignee: JP Morgan Chase Bank, N.A. (JP Morgan Chase & Co)
• Original Assignee: JP Morgan Chase Bank, N.A. (JP Morgan Chase & Co)
• Inventors: Gibson, Donovan, Gearheart, James, Bates, Matthew, Naylor, Jacob Andrew
• Primary Examiner(s): Brockington, III, William S
• Assistant Examiner(s): Leal, Hector
• Application Number:
  US14/516,898
• Time in Patent Office: 1,775 Days
• Field of Search: 705 725
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/06315 Needs-based resource requirements planning or analysis
• CPC Class Codes: G06Q 20/18 involving self-service terminals [SST], vending machines, kiosks or multimedia terminals
• CPC Class Codes: G07F 19/209 Monitoring, auditing or diagnose of functioning of ATMs

Abstract

According to an embodiment of the present invention, a computer implemented method and system for determining an optimization schedule comprising: executing, via the computer processor, a volume forecast determination for at least one ATM device to generate forecast data, wherein the volume forecast comprises a withdrawal forecast and a deposit forecast; executing, via the computer processor, a simulation based on the forecast data to develop a set of possible schedules for the at least one ATM, wherein the simulation considers one or more identified uncertainties; automatically, via the computer processor, generating one or more fault risks based at least in part on the one or more identified uncertainties; and automatically, via the computer processor, determining an optimal schedule for the at least one ATM device based on the one or more fault risks.

Claims

1. An automated computer implemented method for determining and implementing an optimized schedule for deposit pickup, cash replenishment, and service timing for one or more ATM devices, wherein the method is executed by a programmed computer processor which communicates with a user via a network, the method comprising the steps of:

executing, via the computer processor, a volume forecast determination for at least one ATM device to generate forecast data, wherein the volume forecast comprises a withdrawal forecast and a deposit forecast, and where the withdrawal forecast and deposit forecast utilize distinct methodologies;

executing, via the computer processor, a simulation based on the forecast data to develop a plurality of possible ATM schedules for the at least one ATM, each of the plurality of possible ATM schedules comprises a replenishment schedule, a deposit schedule and a total cost associated with servicing each of the plurality of possible ATM schedules, wherein the simulation considers one or more identified uncertainties and wherein the simulation comprises a withdrawal simulation and a deposit simulation, the withdrawal simulation is based on forecast uncertainty and vendor arrival time uncertainty and the deposit simulation is based on deposit bin capacity uncertainty, forecast uncertainty and vendor arrival time uncertainty;

automatically, via the computer processor, generating one or more fault risks for each of the plurality of possible ATM schedules based at least in part on the one or more identified uncertainties, the one or more fault risks comprises a cumulative fault risk and an incremental fault risk;

automatically, via the computer processor, determining an optimal schedule for the at least one ATM device based on the one or more fault risks; and

initiating, via the computer processor, the optimal schedule for the at least one ATM based on the one or more fault risks.

2. The method of claim 1, wherein the simulation comprises a Monte Carlo simulation.

3. The method of claim 1, wherein the volume forecast is based on a regression model applied to historic ATM volume data.

4. The method of claim 1, wherein the volume forecast considers one or more seasonal factors.

5. The method of claim 1, wherein the step of determining an optimal schedule further comprises computing cost of a plurality of deposit and withdrawal combinations.

6. The method of claim 1, wherein the optimal schedule further comprises a service frequency.

7. The method of claim 1, wherein the optimal schedule is further based on one or more business rules.

8. The method of claim 1, wherein the at least one ATM device comprises a plurality of ATMs in one or more geographic locations.

9. A system that determines an optimization schedule for one or more ATM devices, wherein the system comprises a programmed computer processor which communicates with a user via a network, comprising:

a processor; and

a memory comprising computer-readable instructions which when executed by the processor cause the processor to perform the steps comprising;

executing a volume forecast determination for at least one ATM device to generate forecast data, wherein the volume forecast comprises a withdrawal forecast and a deposit forecast, and where the withdrawal forecast and deposit forecast utilize distinct methodologies;

executing a simulation based on the forecast data to develop a plurality of possible ATM schedules for a specific ATM, each of the plurality of possible ATM schedules comprises a replenishment schedule, a deposit schedule and a total cost associated with servicing each of the plurality of possible ATM schedules, wherein the simulation considers one or more identified uncertainties and wherein the simulation comprises a withdrawal simulation and a deposit simulation, the withdrawal simulation is based on forecast uncertainty and vendor arrival time uncertainty and the deposit simulation is based on deposit bin capacity uncertainty, forecast uncertainty and vendor arrival time uncertainty;

automatically generating one or more fault risks for each of the plurality of possible ATM schedules based at least in part on the one or more identified uncertainties, the one or more fault risks comprises a cumulative fault risk and an incremental fault risk;

automatically determining an optimal schedule for the at least one ATM device based on the one or more fault risks; and

initiating, via the computer processor, the optimal schedule for the at least one ATM based on the one or more fault risks.

10. The system of claim 9, wherein the simulation comprises a Monte Carlo simulation.

11. The system of claim 9, wherein the volume forecast is based on a regression model applied to historic ATM volume data.

12. The system of claim 9, wherein the volume forecast considers one or more seasonal factors.

13. The system of claim 9, wherein determining an optimal schedule further comprises computing cost of a plurality of deposit and withdrawal combinations.

14. The system of claim 9, wherein the optimal schedule further comprises a service frequency.

15. The system of claim 9, wherein the optimal schedule is further based on one or more business rules.

16. The system of claim 9, wherein the at least one ATM device comprises a plurality of ATMs in one or more geographic locations.