SYSTEM AND METHOD FOR DETECTING INTERNET FRAUD USING A MACHINE LEARNING MODEL

1 . A computerized method of detecting internet fraud, the method comprising:

determining, by a computer processor, one or more combinations of one or more items, wherein a cost for each of the determined one or more combinations equals a cost for a transaction to take place at a target website;

for each of the items in each determined combination, predicting, by a machine learning model, a likelihood value for a quantity of the item in the determined combination, wherein the predicted likelihood value is indicative of whether the quantity of the item in the determined combination is common in historical data, wherein the predicting of the likelihood value comprises inputting a tag describing the item into the machine learning model;

generating, by the processor, a probability of fraud for the transaction to take place at the target website based on one or more of the predicted likelihood values; and

blocking or enabling the transaction to take place at the target website based on the generated probability of fraud.

2 . The computerized method of claim 1 , comprising scanning, by a server comprising the processor, the target website to identify:

a plurality of items provided by the website, the plurality of items provided by the website including the one or more items, and

a plurality of tags associated with one or more of the items, the plurality of tags including the tag describing the item.

3 . The computerized method of claim 1 , wherein the generating of the probability of fraud comprises:

calculating a probability of fraud for each of the determined combinations using one or more of the predicted likelihood values; and

aggregating one or more of the calculated probabilities of fraud for the determined combinations.

4 . The computerized method of claim 1 , wherein the historical data comprises one or more past transactions associated with the tag describing the item.

5 . The computerized method of claim 1 , wherein the determining of the one or more combinations is performed based on the cost for the transaction to take place at the target website not being found in a white list of transaction costs.

6 . The computerized method of claim 2 , comprising determining, by a second machine learning (ML) model, one or more tags of the plurality of tags, wherein the second ML model is trained using information linking item names to tags.

7 . The computerized method of claim 1 , wherein the determining of one or more of the combinations comprises recursively solving a subset sum problem.

8 . The computerized method of claim 2 , wherein the scanning comprises executing a web scraping process, the web scraping process comprising triggering one or more dynamic internet browser events to reveal one or more hidden elements in the target website.

9 . The computerized method of claim 2 , wherein the method is executed using a hardware-accelerated computer system, and wherein the method comprises determining, using a convolutional neural network (CNN), one or more tags of the plurality of tags, wherein the CNN is trained using a plurality of image files.

10 . A computerized system for detecting internet fraud, the system comprising:

a memory; and

one or more processors configured to:

determine one or more combinations of one or more items, wherein a cost for each of the determined one or more combinations equals a cost for a transaction to take place at a target website;

for each of the items in each determined combination, predict, by a machine learning model, a likelihood value for a quantity of the item in the determined combination, wherein the predicted likelihood value is indicative of whether the quantity of the item in the determined combination is common in historical data, wherein the predicting of the likelihood value comprises inputting a tag describing the item into the machine learning model;

generate a probability of fraud for the transaction to take place at the target website based on one or more of the predicted likelihood values; and

block or enable the transaction to take place at the target website based on the generated probability of fraud.

11 . The computerized system of claim 10 , wherein one or more of the processors is to scan the target website to identify:

a plurality of items provided by the website, the plurality of items provided by the website including the one or more items, and

a plurality of tags associated with one or more of the items, the plurality of tags including the tag describing the item.

12 . The computerized system of claim 10 , wherein the generating of the probability of fraud comprises:

calculating a probability of fraud for each of the determined combinations using one or more of the predicted likelihood values; and

aggregating one or more of the calculated probabilities of fraud for the determined combinations.

13 . The computerized system of claim 10 , wherein the historical data comprises one or more past transactions associated with the tag describing the item.

14 . The computerized system of claim 10 , wherein the determining of the one or more combinations is performed based on the cost for the transaction to take place at the target website not being found in a white list of transaction costs.

15 . The computerized system of claim 11 , wherein one or more of the processors is to determine, by a second machine learning (ML) model, one or more tags of the plurality of tags, wherein the second ML model is trained using information linking item names to tags.

16 . The computerized system of claim 10 , wherein the determining of one or more of the combinations comprises recursively solving a subset sum problem.

17 . The computerized system of claim 11 , wherein the scanning comprises executing a web scraping process, the web scraping process comprising triggering one or more dynamic internet browser events to reveal one or more hidden elements in the target website.

18 . The computerized system of claim 11 , wherein one or more of the processors include a hardware accelerated computer system, and wherein one or more of the processors is to determine, using a convolutional neural network (CNN), one or more tags of the plurality of tags, wherein the CNN is trained using a plurality of image files.

19 . A computerized method of detecting internet fraud, the method comprising:

computing, by a computer processor, one or more subsets of one or more items, wherein a cost for each of the determined one or more subsets equals a cost for a transaction to take place at a website;

for each of the items in each determined subset, generating, by a machine learning model, a probability value for a number of units of the item in the determined subset, wherein the generated probability value is indicative of whether the number of units of the item in the determined subset is common in historical data, wherein the generating of the probability value comprises inputting a label describing the item into the machine learning model;

generating, by the processor, an authentication score for the transaction to take place at the target website based on one or more of the generated probability values; and

preventing or permitting the transaction to take place at the target website based on the generated authentication score.

20 . The computerized method of claim 19 , wherein the historical data comprises one or more past transactions associated with the label describing the item.