Biometric Technologies in Fintech and Banking

Today we will describe the existing technologies, their development prospects and the benefits that are contained in their proper application. The FINTECH industry is currently developing at a huge pace, changing the financial infrastructure and even approaches to doing business. At the same time, there are only two key requirements for this industry: improving the efficiency of the financial system or individual business, and security. Biometric technologies meet both of these requirements and are perfectly combined with the latest achievements of FINTECH. The most obvious area of biometrics use is rapid and reliable identification of the client at different steps and in different scenarios of financial interactions. The second area is ensuring security when working with personal information and financial data. This is also true for all kinds of payment and transfer systems, banking and personal Finance, lending, asset and investment management, and, finally, insurance. The simplest biometrics is used in fingerprint scanners of modern smartphones and tablets, and they can be used to access the Google Pay and Apple Pay systems. Many large international banks already use biometrics in their mobile apps both for logging in to the app and for confirming transactions (usually instead of confirming via SMS). But this is also difficult to call a decent protection-smartphone manufacturers focus on the speed of the fingerprint sensor, which does not affect the accuracy of recognition in the best way. The sensor usually reads only part of the fingerprint. Both a recent study by scientists from Michigan and the creation of the so-called MasterPrint (a kind of “arithmetic mean” fingerprint) confirm this.

The international payment system MasterCard has launched in 12 European countries the ability to confirm online purchases using selfies. Amazon, Uber, and even some government organizations in the United States are moving in the same direction. Of course, this technology is convenient, but it is not a panacea, especially since you can change the password stolen by hackers, but it will be more difficult with the face. There is also 3D Secure 2.0 – a new version of the Protocol that received a modified verification procedure. The payment confirmation itself is implemented using various biometric parameters – facial contours, fingerprints, palm veins, and so on. At the same time, the internal risk assessment system is responsible for up to 95% of total transactions, and only in the case of the remaining 5%, the system will request a verification code. HSBC Corporation announced the launch of a voice payment confirmation service, which also cannot be a 100% reliable method of identification. Ubiquitous mobility has become one of the essential trends for FINTECH, and it is difficult to imagine any new financial application without using biometrics, so either sensor manufacturers will have to catch up with FINTECH, or start using additional identification systems other than fingerprints. Only a multi – modal approach-authentication using several biometric indicators at once-can provide the proper level of protection while maintaining comfort and speed of use. The weakest and most vulnerable modality is the voice, which is highly dependent on ambient noise and is easily intercepted by third-party technical means. Similar problems arise when choosing video identification as the only way – the quality of lighting, weather, and minor changes in appearance greatly complicate the process and affect the result. Much better is the case with identification by drawing the veins of the palm, a three-dimensional model of the face, a photo taken in the IR range, or the iris, especially when they are superposed in order to control compromise and manage risks.  An undoubted plus for the banks themselves is additional expansion into the regions, because if there is an adequate identification and authorization system, the client will be able to fully use the Bank’s services from any city or even country. If, after testing in several banks, the project is considered successful, the authoritative bodies will be able to create a special biometric basis and the banks will be able to significantly expand the range of financial services provided using methods of biometric verification of the credit institution’s client in remote service channels. Here, more than anywhere else, it is important to ensure data security and reliable authentication at all stages of interaction. This is not difficult to do, as we mentioned above, you only need to select “strong” modalities and provide multi-modal verification. Let’s look at the areas where RecFaces technologies can speed up, optimize, and secure the use of financial services. During the credit or insurance scoring process, Id-Me can provide reliable and fast verification of the client, and a stop list reconciliation can also be performed in identification mode. When scanning a passport, the biometric face image verification rule will help you verify the authenticity of the document, exclude people who look similar, and exclude the use of someone else’s document. For any remote financial transactions, multi-modal biometric verification will be the key to convenient and secure transaction.

Identification process:

With the help of external equipment installed on the various client application, creates a biometric template (BT) of a particular person. Various equipment can be used (retinal scanner, fingerprint scanner, camera, microphone, etc.), including for creating a multi-modal client profile. The client user interface (UI) and client services communicate with the web server and send the BO through it to the Id-Me platform. The BO is placed in an isolated storage module using depersonalization mechanisms. When a request is received in the biometric sample processing Module, the following steps are performed:

• Getting the BO from the storage;
• Checking the quality of the BO (photo quality, distance, illumination, blurring, head angles, integral quality indices, level of extraneous noise, etc.);
• If the quality is poor, the process is interrupted with the corresponding message.
• In case of satisfactory quality, the BO is converted to a biometric template (BS).
• the BS is placed in the storage module using depersonalization mechanisms.
• The anti-compromise control module starts the pipeline for checking the BO and BS for falsification, substitution, non-compliance, replacement of persons, etc.
• The pipeline can include mechanisms that work on various grounds (analysis of context, human behavior, optical distortion, etc.).
• The recognition and search module receives a request to search for BS in the reference database of BS profiles of people:
• The recognition and search module receives the BO/BS of the current operation.
• the biometric verification function is Implemented.
• Returns the similarity measure and the value authenticated/not authenticated as the result.

The user identification result is uploaded to the client UI or hardware execution mechanisms. It is important to note that all this multi-stage process provides high reliability of the result, and takes only 1.5-2 seconds.

What practical benefits does an organization get when using the Id-Me multi-modal platform?

1. Convenient and secure biometric authentication of clients in remote service channels;
2. Biometric mechanisms for checking the customer in the lending process;
3. Convenient and secure biometric authentication of personnel, control and confirmation of certain types of operations and employee presence;
4. Effective modern biometric tools to combat internal and external fraud;
5. Ways to manage customer service prioritization;
6. The required combination of biometric modalities to successfully solve business problems.

RecFaces cooperates productively with financial organizations, and in the near future we will be able to write here about successful cases in banking and FINTECH. However, biometrics is not limited to financial security, it can be applied equally successfully and effectively at transport infrastructure facilities, and we are planning the following material on this.