Detecting unauthorized online applications using machine learning
A method of detecting whether electronic fraud alerts are false positives includes receiving data detailing a financial transaction, inputting the data into a rules-based engine that determines whether to generate an electronic fraud alert for the financial transaction based upon the data, and, when an electronic fraud alert is generated, inputting the data into a machine learning program trained to identify one or more facts indicated by the data. The method may also include determining whether the identified facts can be verified by customer data and, in response to determining that the facts can be verified, retrieving or receiving first customer data. The method may further include verifying that the electronic fraud alert is not a false positive based upon analysis of the first customer data, and transmitting the verified electronic fraud alert to a mobile device of the customer to alert the customer to fraudulent activity.
1. A computer-implemented method for authorizing online applications, the method comprising:
receiving, by a machine learning (ML) rule generator including one or more processors, training data including:
(i) historical authorization determinations made in connection with a plurality of previous online applications, and
(ii) search history data associated with a plurality of computing devices;
training a ML program, by the ML rule generator, and based at least in part on the historical authorization determinations and the search history data, to determine a set of authorization rules for processing online applications;
receiving, from an applicant computing device, application data indicative of input entered in one or more fields of an online application, the application data including first identification information provided by an applicant;
retrieving, from a database, first search history data associated with at least one of the applicant data or the applicant computing device, the first search history data indicative of one or more search terms submitted to an Internet-based search engine;
determining, using the set of authorization rules, and based at least in part on the application data and the first search history data, that the received application data is indicative of an unauthorized online application;
updating, by the ML rule generator, the set of authorization rules based at least in part on determining that the received application data is indicative of an unauthorized online application; and
applying, by the processor, the updated set of set of authorization rules to additional application data and additional search term data.
2. The computer-implemented method of claim 1 , wherein receiving the first search history data includes identifying an Internet Protocol (IP) address of the applicant computing device.
3. The computer-implemented method of claim 2 , wherein the first search history data is indicative of one or more search terms submitted to the Internet-based search engine from the identified IP address.
4. The computer-implemented method of claim 3 , wherein determining that the received application data is indicative of an unauthorized online application includes comparing information included in the one or more search terms to information included in the input.
5. The computer-implemented method of claim 3 , wherein determining that the received application data is indicative of an unauthorized online application includes comparing a name included in the one or more search terms to a name included in the input.
6. The computer-implemented method of claim 5 , wherein determining that the received application data is indicative of an unauthorized online application includes determining that the one or more search terms are directed to discovering an address associated with the name.
7. The computer-implemented method of claim 5 , wherein determining that the received application data is indicative of an unauthorized online application further includes determining that the one or more search terms are directed to discovering an employment history associated with the name.
8. A computer system for authorizing online applications, the system comprising:
a search history database configured to store data associated with a plurality of Internet searches;
one or more processors; and
a non-transitory memory storing instructions that, when executed by the one or more processors, cause the one or more processors to:
receive, by a machine learning (ML) rule generator, training data including:
(i) historical authorization determinations made in connection with a plurality of previous online applications, and
(ii) search history data associated with a plurality of computing devices;
train a ML program, by the ML rule generator, and based at least in part on the historical authorization determinations and the search history data, to determine a set of authorization rules for processing online applications;
receive, from an applicant computing device, application data indicative of input entered in one or more fields of an online application, the application data including first identification information provided by an applicant;
retrieve, from a database, first search history data associated with at least one of the applicant data or the applicant computing device, the first search history data indicative of one or more search terms submitted to an Internet-based search engine;
determine, using the set of authorization rules, based at least in part on the application data and the first search history data, that the received application data is indicative of an unauthorized online application; and
update, by the ML rule generator, the set of authorization rules based at least in part on determining that the received application data is indicative of an unauthorized online application.
9. The computer system of claim 8 , wherein receiving the first search history data includes identifying an Internet Protocol (IP) address of the applicant computing device.
10. The computer system of claim 9 , wherein the first search history data is indicative of one or more search terms submitted to the Internet-based search engine from the identified IP address.
11. The computer system of claim 10 , wherein the instructions cause the one or more processors to determine that the received application data is indicative of an unauthorized online application includes comparing information included in the one or more search terms to information included in the input.
12. The computer system of claim 11 , wherein the instructions cause the one or more processors to determine that the received application data is indicative of an unauthorized online application includes comparing a name included in the one or more search terms to a name included in the input.
13. The computer system of claim 12 , wherein the instructions cause the one or more processors to determine that the received application data is indicative of an unauthorized online application includes determining that the one or more search terms are directed to discovering an address associated with the name.
14. The computer system of claim 12 , wherein the instructions cause the one or more processors to determine that the received application data is indicative of an unauthorized online application includes determining that the one or more search terms are directed to discovering an employment history associated with the name.
15. A non-transitory, computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to:
receive, by a machine learning (ML) rule generator, training data including:
(i) historical authorization determinations made in connection with a plurality of previous online applications, and
(ii) search history data associated with a plurality of computing devices;
train a ML program, by the ML rule generator, and based at least in part on the historical authorization determinations and the search history data, to determine a set of authorization rules for processing online applications;
receive, from an applicant computing device, application data indicative of input entered in one or more fields of an online application, the application data including first identification information provided by an applicant;
retrieve, from a database, first search history data associated with at least one of the applicant data or the applicant computing device, the first search history data indicative of one or more search terms submitted to an Internet-based search engine;
determine, using the set of authorization rules, based at least in part on the application data and the first search history data, that the received application data is indicative of an unauthorized online application; and
update, by the ML rule generator, the set of authorization rules based at last in part on determining that the received application data is indicative of an unauthorized online application.
16. The non-transitory, computer-readable medium of claim 15 , wherein receiving the first search history data includes identifying an Internet Protocol (IP) address of the applicant computing device.
17. The non-transitory, computer-readable medium of claim 16 , wherein the first search history data is indicative of one or more search terms submitted to the Internet-based search engine from the identified IP address.
18. The non-transitory, computer-readable medium of claim 17 , wherein the instructions cause the one or more processors to determine that the received application data is indicative of an unauthorized online application includes comparing information included in the one or more search terms to information included in the input entered in the one or more fields.
19. The non-transitory, computer-readable medium of claim 18 , wherein the instructions cause the one or more processors to determine that the received application data is indicative of an unauthorized online application includes comparing a name included in the one or more search terms to a name included in the one or more fields.
20. The non-transitory, computer-readable medium of claim 19 , wherein the instructions cause the one or more processors to determine that the received application data is indicative of an unauthorized online application includes determining that the one or more search terms are directed to discovering an address associated with the name.