Integrated fraud detection using light sensors

Abstract

Aspects described herein may allow for detecting fraudulent transaction requests using light sensors on smartcards. A computing device may receive, from a terminal, a request to approve a transaction. The request may comprise a timestamp corresponding to a time when the transaction was requested, a transaction type associated with the transaction, and an identification of a card associated with the transaction. The computing device may also receive, from one or more light sensors associated with the card, light data. The light data indicates an amount of ambient light during a time period when the transaction was requested. The computing device may determine, based on the transaction type, a model of expected ambient light. If the light data corresponds to the model, the computing device may send, based on the determination that the light data corresponds to the model, an approval of the request.

What is claimed is: 
     
         1 . A method for evaluating a card transaction for fraud comprising:
 receiving, by a computing device, a request to approve a transaction, wherein the request comprises a transaction type associated with the transaction, and an identification of a card associated with the transaction;   receiving, by the computing device and after receiving the request to approve the transaction, light data from one or more light sensors disposed on the card, wherein the light data indicates an amount of ambient light, which is detected by the one or more light sensors, during a time period comprising a time when the transaction was requested; and   based on a determination that the light data corresponds to a model, sending an approval of the request.   
     
     
         2 . The method of  claim 1 , further comprising making the determination that the light data corresponds to the model, the making the determination comprising:
 determining an amount of light detected by a first light sensor associated with a first portion of the card; and   determining an amount of light detected by a second light sensor associated with a second portion of the card,   wherein a difference between the amount of light detected by the first light sensor and the amount of light detected by the second light sensor exceeds a threshold.   
     
     
         3 . The method of  claim 2 , wherein the first light sensor and the second light sensor detect light on opposite sides of the card. 
     
     
         4 . The method of  claim 1 , wherein the time period starts based on a change of light exceeding a threshold. 
     
     
         5 . The method of  claim 1 , wherein the transaction type associated with the transaction comprises one of:
 the card being presented in close proximity to a contactless payment reader;   the card being swiped through a magnetic stripe reader; or   a portion of the card being inserted into a chip reader.   
     
     
         6 . The method of  claim 1 , wherein the light data further indicates a change of ambient light over the time period. 
     
     
         7 . The method of  claim 1 , further comprising making the determination that the light data corresponds to the model, the making the determination comprising:
 determining the card was exposed to light emitted from a display device at a particular time.   
     
     
         8 . The method of  claim 1 , further comprising determining the model based on a location of the transaction. 
     
     
         9 . The method of  claim 1 , further comprising determining the model based on a data set indicating a habit of a user associated with the card. 
     
     
         10 . The method of  claim 1 , further comprising:
 obtaining, from a database, a training data set comprising a plurality of training light data associated with prior transactions of the transaction type;   updating the training data set by adding the light data to the training data set; and   updating the model based on the updated training data set.   
     
     
         11 . A computing device comprising:
 one or more processors; and   memory configured to store computer instructions that, when executed by the one or more processors, cause the computing device to perform actions comprising:
 receiving a request to approve a transaction, wherein the request comprises a transaction type associated with the transaction, and an identification of a card associated with the transaction; 
 receiving, after receiving the request to approve the transaction, light data from one or more light sensors disposed on the card, wherein the light data indicates an amount of ambient light, which is detected by the one or more light sensors, during a time period comprising a time when the transaction was requested; 
 based on a determination that the light data corresponds to a model, sending an approval of the request; 
 obtaining, from a database, a training data set comprising a plurality of training light data associated with prior transactions of the transaction type; 
 updating the training data set by adding the light data to the training data set; and 
 updating the model based on the updated training data set. 
   
     
     
         12 . The computing device of  claim 11 , wherein the computer instructions are configured to cause the computing device to make the determination that the light data corresponds to the model by performing actions comprising:
 determining an amount of light detected by a first light sensor associated with a first portion of the card; and   determining an amount of light detected by a second light sensor associated with a second portion of the card,   wherein a difference between the amount of light detected by the first light sensor and the amount of light detected by the second light sensor exceeds a threshold.   
     
     
         13 . The computing device of  claim 12 , wherein the first light sensor and the second light sensor detect light on opposite sides of the card. 
     
     
         14 . The computing device of  claim 11 , wherein the time period starts based on a change of light exceeding a threshold. 
     
     
         15 . The computing device of  claim 11 , wherein the transaction type associated with the transaction comprises one of:
 the card being in close proximity to a contactless payment reader;   the card being swiped through a magnetic stripe card reader; or   a portion of the card being inserted into a chip reader.   
     
     
         16 . A non-transitory computer-readable medium storing computer instructions that, when executed by one or more processors, cause performance of actions comprising:
 receiving a request to approve a transaction, wherein the request comprises a transaction type associated with the transaction, and an identification of a card associated with the transaction;   receiving, after receiving the request to approve the transaction, light data from one or more light sensors disposed on the card, wherein the light data indicates an amount of ambient light, which is detected by the one or more light sensors, during a time period comprising a time when the transaction was requested, wherein the one or more light sensors comprises a first light sensor associated with a first portion of the card and a second light sensor associated with a second portion of the card;   determining, based on the transaction type, a model of ambient light, associated with the transaction type, expected during the time period;   determining whether the light data corresponds to the model based on: 
 determining an amount of light detected by the first light sensor at a time; and 
 determining an amount of light detected by the second light sensor at the time, 
 wherein a difference between the amount of light detected by the first light sensor and the amount of light detected by the second light sensor exceeds a threshold; 
   declining, based on determining that the light data does not correspond to the model, the request; and   based on a determination that the light data corresponds to a model, sending an approval of the request.   
     
     
         17 . The non-transitory computer-readable medium of  claim 16 , wherein the computer instructions are further configured to cause performance of actions comprising:
 obtaining, from a database, a training data set comprising a plurality of training light data associated with prior transactions of the transaction type;   updating the training data set by adding the light data to the training data set; and   updating the model based on the updated training data set.   
     
     
         18 . The non-transitory computer-readable medium of  claim 16 , wherein the first light sensor and the second light sensor detect light on opposite sides of the card. 
     
     
         19 . The non-transitory computer-readable medium of  claim 16 , wherein the transaction type associated with the transaction comprises one of:
 the card being in close proximity to a contactless payment reader;   the card being swiped through a magnetic stripe card reader; or   a portion of the card being inserted into a chip reader.   
     
     
         20 . The non-transitory computer-readable medium of  claim 16 , wherein the computer instructions are further configured to cause performance of actions comprising determining the model based on a location of the transaction.