Supervised and unsupervised learning techniques for fraud detection.

Artificial intelligence is redefining fraud prevention techniques as it allows to obtain information based on experience. This information consists of transaction activities, behavior and trends. Before the use of artificial intelligence, the applied methods were based on rules that helped to analyze historical fraud patterns but could not prevent them. Although these models could identify fraud attempts, they did not provide information of the future.

Nevertheless, the technological sophistication of fraud crimes is higher and more precise and efficient attacks have grown during the last few years

As a result, leading companies dealing with potential fraud crimes, mainly in banking and insurance, must increase monitoring accuracy and acuity of customers potential risk for the institution. Decision-making on accepting or rejecting payments, limiting charges refund and reducing operational and reputational risks is much easier now.

Fraud prevention in the future will depend on a combination of supervised and unsupervised automatic learning techniques. Supervised automatic learning finds patters based on historical events, factors, trends, etc., and unsupervised automatic learning looks for relationships and variable links, a combination of both methodologies would help to prevent fraud in the following:

Detection in real time. The use of artificial intelligence enables the detection of attacks in real time, instead of weeks that usually takes to start receiving reverse requests of charges.

Thwarting the most sophisticated attempts of fraud. Fraud techniques get more and more sophisticated. Artificial intelligence would help to prevent and reduce these attacks.

Scoring in real time. Provide analysts a scoring for a better perspective to set the limits to maximize sales and minimize losses in real time.

Immediate transactions. Fraud prevention systems based on AI enable immediate transaction´s approval provided it is within the reverse charges threshold of the main debit and credit cards.

Reduction of false positives. False positives are reduced thanks to supervised and unsupervised automatic learning, whereas current techniques cannot efficiently detect them. Frequently, when a customer pays an unusual amount of money or from a new location, the card is blocked by the system as it interprets it wrongly as a suspicious activity. With artificial intelligence, it is possible to identify more precisely any change in customers expenditure habits.

Profitability in low margin products. AI has allowed insurance companies to continue their profitable business and attract new customers whose historical purchases are not part of the historical supervised learning of fraud systems

Supervised and unsupervised learning should be complemented with experts´ knowledge aiming at a mixed approach to focus their attention in more suspicious cases detected by AI.

Health, the new challenge in Artificial Intelligence

Data has significantly grown with the advent of network devices in the health sector such as medical clinical histories, diagnostic processes, and more particularly, medical imaging -the introduction of Real-World Evidence. Making correct use of this data could save a great number of lives and reduce sanitary costs.

En los Programas de Continuidad citan al Grupo AIA

Grupo AIA as an example of Artificial Intelligence use in the session “The great impact of Artificial Intelligence: reality and challenges”

What are the challenges Artificial Intelligence is facing today? How is this technology impacting on different industrial sectors? , Nuria Agell, Operation and Data Science Department Director of ESADE, has gathered directors of different sectors: health, retail, etc. within the Continuity programs of Esade, Programas de Continuidad de ESADE to answer these questions.

Agell talked about Artificial Intelligence revival in the industry and of how this technology has allowed to develop intelligent systems designed to improve diverse industrial processes and everyday life: Smart phones, virtual assistants and the evolution of autonomous systems.

Nuria Agell presented Grupo AIA as one of the companies using Artificial Intelligence for diverse industrial sectors through innovations in Machine Learning and Deep Learning and at the state of the art in advance technological solutions.

Grupo AIA´s unique methodologies provide solutions to companies challenges as it combines Artificial Intelligence and advanced analysis to tackle the problem thoroughly and accurately to meet customers´ needs.

Grupo AIA has participated in the ENERGOS project´s closure

Last September 26th, 2013, Gas Natural Fenosa held the ENERGOS´ closure for presenting the results of the project at the company´s headquarters in Madrid.

As part of the Energos project, AIA carried out research in diverse areas and developed several software modules exploring different technologies. The developments were mainly involved in smart network operation and planning.

This network Intelligent Observation Systems implemented through events processing engines to obtain high-level conclusions from low-level information about the network performance.

On the other hand, artificial intelligence techniques have been used for finding the optimal operation at each situation and provide the necessary steps for automatic resetting in case of incidents. It has also developed a micro-network economic management prototype through multi-agent technologies for the interaction between storage devices, generators of renewable and non-renewable energies, demand management, etc.

Other areas of the project: a predictive maintenance tool, a mobility simulator for electric cars and the use of nanocomposites for fault diagnosis in cables.


Success in AIA´s First Forum in Artificial Intelligence Applications in Chile

Most banks and telecommunications companies attended the Forum held in the city of Santiago, Chile last July 4-5, 2012 at the Hotel W Santiago. The main objective of the meeting was to share AIA’s experience in projects for the banking and telecommunication sectors.

According to a survey of the participants, “the applications have great potential for the solution of complex problems” and provide a new vision of reality. They also assure they would attend future editions.


SISCLAP Proyecto Salud


The SISCLAP project’s objective is to obtain an SCP, which achieves capitation payment models, adjusted for the risk level of the beneficiaries of a health service. Thus it is intended to improve the efficiency of resources, reducing use and consumption and the differences between budgets and expenditure. As an added value seeks to improve the access of users of increased risk to the most efficient and necessary.

The SISCLAP project is basically based on the application of algorithms and predictive models (using artificial intelligence) for segmenting all patients operated on supercomputing infrastructure with a focus on improving the efficiency of the Spanish health system. This improvement will be through three related levels, which ordered from micro to macro: Professional Management, Strategic Management and Organization and Financing of health centres, and budget allocation of healthcare providers.


The “Ministerio de Industria, Energía y Turismo” of Spain, within the “Plan Nacional de Investigación Científica, Desarrollo e Innovación Tecnológica 2008-2011”, has funded the project SISCLAP.


SISCLAP consortium has been formed by:

  • FlowLab
  • Baladona Serveis Assistencials
  • Fundación Parque Científico de Murcia



Reference number : TSI-020100-2011-193