| CPC G06N 5/047 (2013.01) [G06F 18/2413 (2023.01); G06Q 40/02 (2013.01)] | 17 Claims |
|
1. A computer-implemented method comprising:
receiving transactional data by a computing device, the transactional data received from at least two users in a plurality of users, the transactional data comprises at least one timestamp;
identifying by the computing device, a known fraudulent signal within the received transactional data, the known fraudulent signal comprises a signal that was associated with a fraudulent transaction from a previous time period;
determining by the computing device, a pattern within the received transactional data using a computer-based frequency-based domain conversion, where the frequency-based domain conversion uses a Fourier transformation algorithm to decompose a function into its constituent frequencies, wherein the pattern is associated with a determined periodicity, and wherein the pattern is based in part on the identified known fraudulent signal;
determining by the computing device, a delay within the received transactional data by identifying contextual factors associated with the received transactional data based on an analysis of the received transaction data and the known fraudulent signal and measuring an amount of time between each identified contextual factors within a plurality of identified contextual factors using a computer-based signal processing algorithm, where a contextual factor is a factor having an impact on the determined pattern within the transactional data and comprises at least one of a starting timestamp and an ending timestamp;
aligning by the computing device, the received transactional data from the at least two users by placing at least two signal forms associated based on the determined delay within the received transactional data at a same point;
generating a line graph depicting the aligned transactional data; and
transmitting the generated line graph to a user interface display device.
|