Transparent Rational Decisions by Argumentation (TRaDAr)

Argumentation provides a powerful mechanism for dealing with incomplete, possibly inconsistent information and for the resolution of conflicts and differences of opinion amongst different parties. Further, it is useful for justifying outcomes. Thus, argumentation can support several aspects of decision-making, either by individual entities performing critical thinking (needing to evaluate pros and cons of conflicting decisions) or by multiple entities dialectically engaged to come to mutually agreeable decisions (needing to assess the validity of information the entities become aware of and resolve conflicts), especially when decisions need to be transparently justified (e.g. in medicine).

Because of its potential to support decision-making when transparently justifying decisions is essential, the use of argumentation has been considered in a number of settings, including medicine, law, e-procurement, e-business and design rationale in engineering. Potential users of existing argumentation-based decision-making methods are empowered by transparent methods, afforded by argumentation, but lack either means of formal evaluation sanctioning decisions as (individually or collectively) rational or a computational framework for supporting automation. The combination of these three features (transparency, rationality and computational tools for automation) is essential for argumentation-based decision-making to have a fruitful impact on applications. Indeed, for example, a medical practitioner would not find a "black-box" recommended decision useful, but he/she would also not trust a fully transparent, dialectically justified decision unless he/she were sure that this is the best one (rational). In addition, the plethora of information doctors need to take into account nowadays to make decisions requires automated support.

TRaDAr aims at providing methods and prototype systems for various kinds of argumentation-based (individual and collaborative) decision-making that generate automatically transparent, rational decisions, while developing case studies in smart electricity and e-health to inform and validate methods and systems. In this context, TRaDAr's technical objectives are:

(O1) to provide novel argumentation-based formulations of decision problems for individual and collaborative decision-making;

(O2) to study formal properties of the formulations at (O1), sanctioning the rationality of decisions;

(O3) to provide real-world case studies in smart electricity and e-health for (individual and collaborative) decision-making, using the formulations at (O1) and demonstrating the importance of the properties at (O2) as well as the transparent nature of argumentation-based decision-making;

(O4) to define provably correct algorithms for the formulations at (O1), supporting rational and transparent (individual and collaborative) decision-making;

(O5) to implement prototype systems incorporating the computational methods at (O4), and use these systems to demonstrate the methodology at (O1-O2) for the case studies at (O3).

The project intends to develop novel techniques within an existing framework of computational argumentation, termed assumption-based argumentation, towards the achievements of these objectives, and adapting notions and techniques from classical (quantitative) decision theory and mechanism design in economics.

The envisaged TRaDAr's methodology and systems will contribute to a sustainable society supported by the digital economy, and in particular they will support people in making informed choices. The project will focus on demonstrating the proposed techniques in specific case studies (smart electricity and e-health for breast cancer) in two chosen application areas (digital economy and e-health), but its outcomes could be far-reaching into other case studies (e.g. in other areas of medicine) as well as other sectors (e.g. in engineering, for supporting decisions on design choices).

The need for automated computational support for transparent, justifiable decisions that are at the same time rational is widespread in several domains, notably medicine. This is recognised, for instance, within EPSRC digital economy theme, envisaging tools that ` will support people in making informed choices'. TRaDAr aims at developing argumentation-based decision-making methods for supporting the computation of transparent and rational decisions. These methods could be deployed to provide systems and apps of widespread use, thus potentially impacting society in a significant way.

Overall, the project will benefit, in addition to the artificial intelligence academic community (as discussed in the Case for Support and the section Academic Beneficiaries), at least the following: (1) developers of applications necessitating (semi-)autonomous but transparent and auditable decision-making, either by a single entity or by several collaborating entities, including e-health and smart electricity, but also other applications such as design rationale in engineering, trust computing and waste water management; (2) developers of e-health and smart electricity applications (e.g., for the latter, in the form of mobile phone apps or smart meter devices incorporating intelligence for decision support); (3) researchers in psychology and the social sciences who wish to explore computational theories and applications of argumentation and decision-making.

We shall support pathway to impact by disseminating results in four forms: (i) top-quality academic publications (see the Case for Support and Academic Beneficiaries); (ii) open-source software tools for argumentation-based decision-making, available from SourceForge; (iii) publications and soft-
ware tools from suitable web pages; (iv) demonstrating videos, e.g. on utube.

The involvement of key (academic, medical and industrial) players (AIT, UCLH and Fujistu, respectively) will further support dissemination of ideas and tools to practitioners and prompt feedback to guarantee appropriate functionalities and usability for deployment. Organisation of and participation in suitable outreaching events (such as events organised by the Technology Strategy Board) will pave the way towards impact.

Our software tools will be made available for academic research and teaching. Their use for other purposes will require further agreements to protect and benefit from intellectual property. In this context, Imperial College London will provide ideal expertise, via its technology transfer programme, which endeavours to protect intellectual property, and Imperial Innovations Limited, helping to commercially exploit academic research. We believe that the possibility of commercial exploitation of our systems is very high, in both e-health (where decision support of the form we envisage is very much in demand in virtually every medical domain) and smart electricity (as we will demonstrate the added value of smart meters in a novel manner that could benefit all citizens).