PSFraud is a web application / backend system that uses which can respond in real time to the threat of fraud. PSFraud uses sophisticated mathematical and classification (Artificial Intelligence, Machine Learning) technology that provides self-learning capabilities. Additionally, PSFraud incorporates different best known computing techniques, combining them in the most efficient way in order to produce better external fraud detection rates on multiple channels with lower alert levels.

The learning capacity allows to continuously update the profile of each consumer or of an analysis object whose pattern you are looking for. It does this to assimilate the knowledge of the consumer or object and to automatically update the rules and parameters necessary to stop the problem. Predisoft’s analysts, however, are regularly reviewing the analysis results with your specialized staff with the aim of making sure the efficiency level is always optimal.

Predisoft has also specialized PSFraud for internal fraud detection purposes with PSFraud-Internal, and has also offers an authorizer level solution with PSFraudAuthorizer.

  • , , , ,


    PSAML is a web application that runs on servers communicating with Bantotal’s Banking Core. PSAML is a robust solution which monitors your institution’s electronic transactions looking for suspicious behavior, thereby complying with your anti-legitimization / anti-money laundering program, under the concept of an all-in-one system.

    The PSAML computer application has had years of development and increasingly offers more and more features that make it innovative, complete and effective.

    Both with a simple and friendly design, with a effective architecture, as well as with computational-mathematical technology specialized in profiling and atypicality detection, and together with best practices and expert knowledge, the tool is capable of alerting transactions and suspicious behavior. Suspicious cases can be investigated in detail employing any number of personnel throughout the organization, employing a general workflow sub-system.

    Additionally, Predisoft has a mathematical laboratory for data analysis, where we perform segmentation and profiling processes in addition to collaborating with the creation of risk rating matrices for both customers and products.



  • , , ,


    PSMLA  is a web application and backend software system that analyzes electronic transactions of various kinds. It is used to monitor transactions and detect suspicious patterns related to various forms of Money Laundering.

    The PSAML system is all-inclusive: it allows for monitoring, reporting, blacklisting, execution of workflows, population segmentation and for the creation of risk rating matrices, all unified in the same system, thereby optimizing all the management of compliance departments in financial entities.



Artificial intelligence technology (Machine Learning) and mathematical data mining algorithms contained in PSFraud, as well as the use of the Symbolic Vector to monitor the atypicality of user behavior, allow the identification of fraud with the greatest certainty. In addition, the compact symbolic vector storage scheme and the parallelism of the systems allow to extend the processing to loads of any size, being able to analyze millions of transactions in a few seconds, i.e., practically in real time.

In order to obtain these results, PSFraud incorporates the best-known computing techniques, combining them in a unique way, producing better detection rates with lower alert levels.

The ability to learn continuously from incoming transactions allows the user profile of the Bantotal banking system to be continuously updated, in order to assimilate knowledge of behavioral patterns with their evolution and automatically update the rules and parameters necessary to stop fraud. The behavior pattern of the banking system user is calculated continuously, always looking for strong changes that indicate atypical behavior which, ultimately, may be associated with a fraud attempt by a third party.

PSFraud’s self-learning capability significantly reduces false alarms, making it less necessary for human effort to monitor them, as well as reducing associated indirect costs.