Objective
Many experiments have been conducted in the field of neural network-based forecasting in economy and finance. This technology often shows better performances than conventional approaches, as neural networks can infer complex, non-linear and structurally unstable relationships between inputs and outputs. However, in real-world financial applications, forecasting is only a step of the decision process, although a major one.
Portfolio allocation consists in selecting the best combination of investments, or assets, in order to maximise the return on the global fund. A rational approach to this decision takes into account an expectation of both the return of each asset, and of the risk inherent to these expectations. In other words, as some part of the future events cannot be predicted, modelling and managing the risk is as important as a good forecast.
The project aims at applying the neural network technology in an actual asset allocation problem. The specific target application is an operational decision support system for the Strategic Allocation Committee of AXA Asset Management. This system will address the first step of the global allocation process, called country selection, which provides monthly the recommended allocation among the three main types of assets (equities, cash, fixed-income) for the G7 countries.
The technical objectives of A5/T are:
- to design and implement neural portfolio optimisation architectures;
- to show that these architectures can yield a higher performance that these architectures can be generalised to similar contexts.
From the user point of view, this will first increase the quality of the decision process. As the allocation recommendations will partly rely on a quantitative model, they will be easier to monitor, consistent over time, and what-if simulations will be made easier. Furthermore, performances achieved with neural networks in financial forecasting, especially within AXA-AM, will lead most probably the returns of the funds managed by the company to increase substantially.
For the technology providers, the project will confirm a leading position in Europe and probably world-wide for the use of neural networks in financial applications. This demonstrator also has a very important exploitation potential. First, the same type of application can be deployed inside AXA-AM for sector selection and stockpicking, the tactical steps of the portfolio management process. Secondly, the solution developed within this trial application can be generalised to other financial institutions world-wide for similar problems. Thirdly, in the medium term, the approach of embedding neural networks in global decision processes will be extended to other applications in economy and finance, through the development of an application generator.
The A5/T consortium is co-ordinated by ELSEWARE, a French software SME specialised in neural networks applications in economy and finance. SNAT is the subsidiary of SIEMENS in charge of the development of new technologies and especially of neural networks. SNAT is marketing SENN, the neural network simulator, which has been used extensively in economic and financial forecasting. AXA is one of the leading European insurance companies, AXA Asset Management being its subsidiary in charge of managing the funds of the company and of third parties. AXA Asset Management is a highly experienced neural networks user, through its more than two-year co-operation with ELSEWARE, for building forecasting models. ELSEWARE is also the French partner of SNAT for consulting in the banking and finance sector.
Fields of science (EuroSciVoc)
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: The European Science Vocabulary.
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: The European Science Vocabulary.
- natural sciences computer and information sciences software
- natural sciences computer and information sciences artificial intelligence computational intelligence
You need to log in or register to use this function
Programme(s)
Multi-annual funding programmes that define the EU’s priorities for research and innovation.
Multi-annual funding programmes that define the EU’s priorities for research and innovation.
Topic(s)
Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.
Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.
Call for proposal
Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.
Data not available
Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.
Funding Scheme
Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.
Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.
Coordinator
75015 Paris
France
The total costs incurred by this organisation to participate in the project, including direct and indirect costs. This amount is a subset of the overall project budget.