Interactive Machine Learning for Improved Customer Experience.

Machine learning is a field which is inspired by human or animal learning and has the objective to create automated systems, which learn from their past, to solve complicated problems. These methods often appear as algorithms which are set in stone. For example, an algorithm trained on images of animals to recognise the difference between a cat or a dog. This project instead concentrates on statistical and probabilistic problems which deal with an interaction between the learner and some environment. For instance, if our learner is an online store which wishes to learn customer preferences by recommending adverts and receiving feedback on these adverts through whether or not customer clicks on them. Multi-armed bandit methods are often used here. These methods are designed to pick the best option out of a set of options through some learner-environment interaction. Multi-armed bandit methods are often unrealistic, therefore, a major objective of this project is to design alterations to the multi-armed bandit methods for use in real-world applications.

In partnership with Amazon Research Berlin.

The proposal will benefit (i) the UK economy and society, (ii) our industrial partners, (iii) the wider community of non-academic employers of doctoral graduates in STOR, (iv) the scientific disciplines of statistics and operational research (STOR) and associated academic communities, (v) UK doctoral students in STOR, and (vi) the CDT students themselves.

(i) The UK economy will gain a competitive edge through a significant increase in the supply of doctoral STOR professionals with the skills to achieve impact for their work, and who have been trained with the goal of becoming future leaders. Our goal is that those of our graduates who enter industry will assume leading roles in realising the major impact which STOR can make in achieving effective data driven decision-making. A wider societal benefit will accrue from research contributions, inter alia, to the EPSRC themes of Energy, Living with Environmental Change and Global Uncertainties.

(ii) Many of our industrial partners will benefit from the skills supply identified in (i), as likely future employers of STOR-i graduates. They further benefit from teaming with a community of leading edge STOR researchers in the solution of substantive industrial challenges. Mechanisms for the latter include doctoral projects co-funded by and co-supervised with industry, industrial internships and industrial problem-solving days. Our training programme will give students the skills they need to make sure that research outcomes are successfully communicated to beneficiaries. The value that our industrial partners place on working with STOR-i can be seen in over £5M of pledged support.

(iii) A wider benefit will accrue from the employment of STOR-i graduates, equipped as described in (i), across non-partner industrial, government and public sectors organisations. These will also benefit from the networking opportunities afforded by access to STOR-i events and from the dissemination of research outcomes accessibly within non-academic communities.

(iv) The STOR academic community will benefit from methodological advances and from the increase in supply of STOR researchers who value and have experience of collaborative research. Our recruitment strategy will further benefit this community in achieving a healthier supply of high quality doctoral candidates beyond STOR-i: our research intern programme gives top undergraduates from across the UK an experience of STOR research while STOR-i recruitment roadshows partner with the STOR community of the hosting institution. Experience with the current Centre has shown that both of these lead to an increase in applicants for STOR PhD programmes across the UK.

(v) Elements of the STOR-i programme will benefit the wider community of UK doctoral students in STOR. Using the financial support of our external partners, we will develop a STOR-i national associate scheme for UK STOR doctoral students working with industry. This will give funding and access to elements of the STOR-i training programme while an annual event will provide opportunities for learning, networking and sharing research progress to members of the scheme.

(vi) The STOR-i students will benefit from a programme which will support their growth toward research leadership, whether in academia or industry. They will be challenged to achieve their maximum scientific potential and also given the tools and opportunities to develop the broader skills which will enable them to achieve maximum scientific impact. They will be highly employable.