Decision support system
“Aggregation and Ranking method” (C-FARm), use an innovative
approach to create composite indicators allowing ranking various
items (countries, firms, consumers, etc.).
C-FARm is a helpful tool to aggregate multi-dimensional information
and extract knowledge for decision-making in many areas.
Why Composite indicators?
Composite indicators are used to summarise complex information and
constitute a precious instrument of action and decision.
These indicators facilitate the task of ranking on complex issues in
benchmarking exercise in different areas such :
Economy and Finance: rank countries, regions, banks, businesses,
academic institutions, etc.
Marketing: rank products, strategies, customers, etc.
Medicine: rank diseases, hospitals, patients, etc.
Growth in use of Composite indicators
The demand in composite indicators is rapidly growing for at least two
• Complexity of modern economics.
• Enormous amount of information has to be processed.
Google searches on composite indicators Google ; juin-07;
Google scholar Google
Google ; Oct :2005; Google ; juin-06; juin-07; 174000
Oct :2005; 992 juin-06; 1440
Oct:2005 june:2006 june:2007
Robust and Objective Decision Maker
C-FARm is based on an new approach using neural networks insuring a
high level of robustness – Its main features are:
• Objectivity : No empirical manipulation of weights
• Specificity : A specific equation for each item
• Decision support : Ability to perform simulations and propose action
plans and optimal sequence of reforms to decision-makers.
Three steps to aggregate complex information
First, C-FARm realizes self-organization of items into homogeneous
subsets (clustering), through a learning process that takes into account
the positive and negative interactions.
Second, an appropriate weights vector is determined for each item.
Finally, the weighting vectors are applied to original data to calculate
the composite indicator and make the overall ranking.
C-FARm solves a major concern of aggregation problems whereby the
question of the importance of each variable is still valid.
The weighting system can be characterized as objective since it
emanates from the informational content of the variables themselves and
their internal dynamics.
This last feature of C-FARm represents a valuable step forward and a going-
beyond what is currently practiced in terms of classification / aggregation.
These advances are based on benefits of Artificial Neural Networks model.
C-FARm references and Success
The model has attracted interest from several organizations:
• Construction of an indicator of governance and country rankings.
• Developing a plan of reforms to improve standards of
governance in Algeria.
Other international organizations have also expressed interest in it.
• International Labor Organisation (OIT)
• African Development Bank (ADB)
• Ministry of Economy, Finance and Industry in France (MINEFI)
• African Union (AU)
• Banks and Insurance Companies
• Rating Agencies
• The Office of Research and Investment advice
• Large Enterprises
• Research Institutions
• International Organizations