Unauthorized activity detection at automated teller machine

A method, comprising:

• receiving, by a computing platform, the computing platform having at least one processor, and memory, an indication that a transaction has been initiated at a transaction processing device, wherein the transaction is initiated via an interaction between a transaction processing card and a card reader of the transaction processing device;
• receiving, by the at least one processor and from one or more sensors in the transaction processing card, capacitance data associated with a capacitance measured when the transaction processing card is inserted into the card reader;
• executing, by the at least one processor, a machine learning model, wherein executing the machine learning model includes inputting the capacitance data to the machine learning model to output identification of any discrepancies in the capacitance data;
• based on detecting, by the at least one processor and via the machine learning model, a discrepancy in the capacitance data, determining, by the at least one processor, that a skimming device is present in the card reader of the transaction processing device;
• generating, by the at least one processor, a notification indicating that the skimming device is present in the card reader of the transaction processing device;
• and
• transmitting, by the at least one processor and to the transaction processing card, the generated notification, wherein transmitting the generated notification to the transaction processing card causes a light emitting diode on the transaction processing card to illuminate.

One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, memory, and a communication interface, cause the computing platform to:

• receive an indication that a transaction has been initiated at a transaction processing device, wherein the transaction is initiated via an interaction between a transaction processing card and a card reader of the transaction processing device;
• receive, from one or more sensors in the transaction processing card, capacitance data associated with a capacitance measured when the transaction processing card is inserted into the card reader;
• execute a machine learning model, wherein executing the machine learning model includes inputting the capacitance data to the machine learning model to output identification of any discrepancies in the capacitance data;
• based on detecting, via the machine learning model, a discrepancy in the capacitance data, determine that a skimming device is present in the card reader of the transaction processing device;
• generate a notification indicating that the skimming device is present in the card reader of the transaction processing device;
• and
• transmit, to the transaction processing card, the generated notification, wherein transmitting the generated notification to the transaction processing card causes a light emitting diode on the transaction processing card to illuminate.