Stay Happy: Understanding Urban Wellbeing Using a Behavioural Machine Learning Approach
Lead Research Organisation:
University of Birmingham
Department Name: Economics
Abstract
Recent advances in information and communication technology (ICT) have created opportunities for the public sector to increase citizens' wellbeing by better understanding their preferences. Machine learning, a subfield of computer science, is a valuable tool to understand consumer/user preferences, including those relevant to urban development and urban service provision. Indeed, it can help to create new urban value propositions by applying data-driven approaches to urban business modelling. Machine learning algorithms in the urban domain provide valuable insights to policymakers. While the existing methodology produces models that can explain some data well, it can be improved by incorporating mathematical modelling from Decision and Behavioural Science to better capture the behavioural component of urban wellbeing.
Research in behavioural science offers models of individual decision-making that generate accurate predictions, and yet these models are not usually applied to large datasets; they are used on small amounts of data obtained through decision-making experiments. Understanding how behavioural science models can enrich existing machine learning to improve the personalisation of urban services - and by doing so increase citizen satisfaction - is the focus of the proposed research programme.
Our programme will address urban wellbeing through: an innovative approach to data analytics, Behavioural Machine Learning (BML); the creation of new urban policies as a result of improved personalisation; and the interaction with data (including self-generated data by citizens as well as citizen data by businesses and policymakers) in day-to-day decision-making. The proposed research involves large datasets collected from field experiments as well as publicly available data, the former particularly focused on the complex and large datasets that capture individual citizen characteristics and wellbeing.
Our programme is innovative because it: (a) broadens and integrates research in behavioural science, data analytics, computer science, and human-data interaction (HDI); (b) examines decision design for complex data-driven urban decisions that involve datasets with low informativeness, very large datasets which are difficult to manage, and noisy data; and (c) focuses on how the data is used by citizens, businesses, and policymakers.
It will have a broad impact in several ways. Firstly, we will work directly with multiple stakeholders to generate solutions that have practical implications for creating new urban policies in practice with measurable benefits. Secondly, its research outputs will suggest improved participatory modes for analysis and presentation of different types of data in the digital economy more generally. Its third value is methodological, as we offer a model of close collaboration and integration for social and natural sciences research. As a result of this project, qualitative and quantitative researchers will better understand the limits and possibilities of the other's methodology, leading to better and more applicable interdisciplinary research. A final impact is on general education in science: blending social and natural science enriches and motivates students of all ages, as well as the members of the general public.
Research in behavioural science offers models of individual decision-making that generate accurate predictions, and yet these models are not usually applied to large datasets; they are used on small amounts of data obtained through decision-making experiments. Understanding how behavioural science models can enrich existing machine learning to improve the personalisation of urban services - and by doing so increase citizen satisfaction - is the focus of the proposed research programme.
Our programme will address urban wellbeing through: an innovative approach to data analytics, Behavioural Machine Learning (BML); the creation of new urban policies as a result of improved personalisation; and the interaction with data (including self-generated data by citizens as well as citizen data by businesses and policymakers) in day-to-day decision-making. The proposed research involves large datasets collected from field experiments as well as publicly available data, the former particularly focused on the complex and large datasets that capture individual citizen characteristics and wellbeing.
Our programme is innovative because it: (a) broadens and integrates research in behavioural science, data analytics, computer science, and human-data interaction (HDI); (b) examines decision design for complex data-driven urban decisions that involve datasets with low informativeness, very large datasets which are difficult to manage, and noisy data; and (c) focuses on how the data is used by citizens, businesses, and policymakers.
It will have a broad impact in several ways. Firstly, we will work directly with multiple stakeholders to generate solutions that have practical implications for creating new urban policies in practice with measurable benefits. Secondly, its research outputs will suggest improved participatory modes for analysis and presentation of different types of data in the digital economy more generally. Its third value is methodological, as we offer a model of close collaboration and integration for social and natural sciences research. As a result of this project, qualitative and quantitative researchers will better understand the limits and possibilities of the other's methodology, leading to better and more applicable interdisciplinary research. A final impact is on general education in science: blending social and natural science enriches and motivates students of all ages, as well as the members of the general public.
Planned Impact
Beyond academia, beneficiaries will include: (1) citizens; (2) businesses; (3) the public sector; and (4) data analysts.
(1) Citizens: The proposed research will suggest ways to improve the personalisation of city services and thus urban lifestyles, which, through the creation of new services and environments, will benefit citizens because they will receive more personalised urban services, improved experiences, better communication, and more convenient delivery options. All these improvements will positively impact citizens' wellbeing, allowing them to engage with their self-generated urban data in more optimal ways and make 'better' (more optimal) decisions, which would increase their quality of life.
(2) Businesses: This project will provide a practical tool in the form of a ready-to-use BML repository, which would propose ways of anticipating future citizens' needs/wants through BML and resulting improvements in personalisation and new business models for urban environments. Urban product and service providers will be able to use the repository to increase citizen satisfaction. This, in turn, will increase business profitability through optimising data analytics and personalisation and offering better value-for-money to citizens. Businesses which may particularly benefit from this research are in such sectors as architecture and development, landscape design, energy, etc.
(3) Policymakers: The research results will offer new ways in which policymakers can use data and citizens can engage with their self-generated urban data. This will produce useful policy recommendations as to how the interactions between citizens, urban services, and data could be regulated and supported by the public sector.
(4) Data analysts: Data analysts will benefit from the new analytical methodology developed within BML.
Our impact and outreach efforts will focus on the following:
(1) Citizens: Our project will engage citizens through experiments. All experimental participants will receive educational feedback after each study. As a result, consumers will be informed about how to engage with their self-generated data more effectively, make 'better' decisions to improve their wellbeing. This will be facilitated through blog posts on the project's website, http://behavioural-analytics.com. Outreach to the general public and wider society will be accomplished through working with the press offices at UoB and Turing as well as via the use of social media (particularly, the dedicated YouTube channel: https://www.youtube.com/channel/UC1RadUEnNYrbdZW5nTVFsUw).
(2) Businesses: We will work with Project Partner, HATDeX, and with City-REDI (UoB) as well as with the Warwick Institute for the Science of Cities (WISC, University of Warwick), for existing capacity and connections in the private sector to design meaningful tests of BML.
(3) Policymakers: As a lead researcher on several smart city projects, the PI will involve policymakers (particularly long-term partners Birmingham City Council and the West Midlands Combined Authority) in BML discussions through regular meetings. Online and printed publicity materials will be designed to attract attention to the issues related to the project. Papers produced by the team will suggest policy implications of our results.
(4) Data analysts will be able to use the BML-repository as a practical tool, as the research team will make all analytical innovations and codes for all BML methods available via the project website, http://behavioural-analytics.com. Data analysts will also be invited to share their own modelling approaches and codes via the repository to facilitate feedback between the research team and practitioners working in data analytics.
(1) Citizens: The proposed research will suggest ways to improve the personalisation of city services and thus urban lifestyles, which, through the creation of new services and environments, will benefit citizens because they will receive more personalised urban services, improved experiences, better communication, and more convenient delivery options. All these improvements will positively impact citizens' wellbeing, allowing them to engage with their self-generated urban data in more optimal ways and make 'better' (more optimal) decisions, which would increase their quality of life.
(2) Businesses: This project will provide a practical tool in the form of a ready-to-use BML repository, which would propose ways of anticipating future citizens' needs/wants through BML and resulting improvements in personalisation and new business models for urban environments. Urban product and service providers will be able to use the repository to increase citizen satisfaction. This, in turn, will increase business profitability through optimising data analytics and personalisation and offering better value-for-money to citizens. Businesses which may particularly benefit from this research are in such sectors as architecture and development, landscape design, energy, etc.
(3) Policymakers: The research results will offer new ways in which policymakers can use data and citizens can engage with their self-generated urban data. This will produce useful policy recommendations as to how the interactions between citizens, urban services, and data could be regulated and supported by the public sector.
(4) Data analysts: Data analysts will benefit from the new analytical methodology developed within BML.
Our impact and outreach efforts will focus on the following:
(1) Citizens: Our project will engage citizens through experiments. All experimental participants will receive educational feedback after each study. As a result, consumers will be informed about how to engage with their self-generated data more effectively, make 'better' decisions to improve their wellbeing. This will be facilitated through blog posts on the project's website, http://behavioural-analytics.com. Outreach to the general public and wider society will be accomplished through working with the press offices at UoB and Turing as well as via the use of social media (particularly, the dedicated YouTube channel: https://www.youtube.com/channel/UC1RadUEnNYrbdZW5nTVFsUw).
(2) Businesses: We will work with Project Partner, HATDeX, and with City-REDI (UoB) as well as with the Warwick Institute for the Science of Cities (WISC, University of Warwick), for existing capacity and connections in the private sector to design meaningful tests of BML.
(3) Policymakers: As a lead researcher on several smart city projects, the PI will involve policymakers (particularly long-term partners Birmingham City Council and the West Midlands Combined Authority) in BML discussions through regular meetings. Online and printed publicity materials will be designed to attract attention to the issues related to the project. Papers produced by the team will suggest policy implications of our results.
(4) Data analysts will be able to use the BML-repository as a practical tool, as the research team will make all analytical innovations and codes for all BML methods available via the project website, http://behavioural-analytics.com. Data analysts will also be invited to share their own modelling approaches and codes via the repository to facilitate feedback between the research team and practitioners working in data analytics.
People |
ORCID iD |
| Ganna Pogrebna (Principal Investigator / Fellow) |
Publications
Anderez DO
(2020)
A COVID-19-Based Modified Epidemiological Model and Technological Approaches to Help Vulnerable Individuals Emerge from the Lockdown in the UK.
in Sensors (Basel, Switzerland)
Belen Saglam R
(2020)
A Data-Driven Analysis of Blockchain Systems' Public Online Communications on GDPR
Butler, D.
(2018)
Predictably Intransitive Preferences
in Judgement and Decision Making
Chizema A
(2019)
The impact of government integrity and culture on corporate leadership practices: Evidence from the field and the laboratory
in The Leadership Quarterly
Del Vecchio M
(2020)
Improving productivity in Hollywood with data science: Using emotional arcs of movies to drive product and service innovation in entertainment industries
in Journal of the Operational Research Society
Perroni, C.
(2019)
Are Donors Afraid of Core Costs? Economies of Scale and Contestability in Charity Markets
in Economic Journal
Plackett B
(2022)
The rural areas missing out on AI opportunities
in Nature
Pogrebna G
(2018)
Female babies and risk-aversion: Causal evidence from hospital wards.
in Journal of health economics
Pogrebna G.
(2021)
Behavioural Data Science of Urban Wellbeing
Pogrebna G.
(2022)
Cambridge Handbook of Behavioural Data Science
| Title | Happiness in Cities Festival Exhibition |
| Description | Within the frame of my project, I have organised the Happiness in Cities week-long festival in October 2019.Using an example of the city of Birmingham, the Happiness in Cities Festival tried to understand how different communities across Birmingham contribute to the city's development and how this diversity can help us build happier cities. The Festival featured many different events as well as the Art of Happiness in Cities Exhibition - a custom photo exhibition produced (free of charge) especially for this event by the local art photographer Alexander Kharlamov. The festival featured a number of events: workshops, performances, student competition, but it also produced a unique photo exhibition, which reached over 2,000 people regionally. |
| Type Of Art | Artistic/Creative Exhibition |
| Year Produced | 2019 |
| Impact | The exhibition raised awareness among the general public about how inclusivity and diversity can increase happiness in cities. According to the United Nations, 68% of the world population will live in urban areas by 2050. Yet, modern cities still fail to maximize people's potential. Using the city of Birmingham as an example, the Happiness in Cities project aims to understand how different communities across Birmingham contribute to the city's development and how this diversity can help us build happier cities. Each day of the festival took place in the Lloyd Room at the University of Birmingham Edgbaston Park Hotel within a unique photographic exhibition inspired by the Happiness in Cities Project. The Art of Happiness in Cities Exhibition has been produced by Alexander Kharlamov using Film Photography & Silver Gelatin Fine Printing. The exhibition featured many different communities from all parts of Birmingham to showcase diversity, inclusivity and multi-cultural vibrancy of city and highlighted how this diversity contributed to the increased happiness. Follow the link below to see the Happiness in Cities Festival report. |
| URL | https://www.inclusionai.org/ |
| Description | The project developed across 3 main use cases: (1) time perception and wellbeing in application to cities; (2) responsible business and wellbeing in cities; (3) wellbeing and security in urban context. So far, I have published 5 methodological papers and 2 empirical papers addressing different aspects of behavioural data science modelling and applications which helped to inform further work within the frame of this project as well as. Published papers addressed risk perceptions and wellbeing of parents in urban contexts across two countries (UK and Ukraine); developed new methodological approach to map global citizens' preferences in risky, uncertain, complex and noisy environments; addressed the methodological approaches to third sector activities within cities; explored how diversity and inclusion impact happiness; as well as explored how behavioural data science could impact data-driven supply chains. This work laid foundations for the main part of the project where I used the methodology of Anthropomorphic Learning (based on the synergy between decision theory and machine learning) to better predict human behaviour in urban contexts (several papers on urban applications of my method are still under review in various journals). Currently the work on development of the core Anthropomorphic Learning approach is finished. Testing work is still on-going and will lead to further research projects. Current research project has produced important results, resulting in 13 papers (some of which are still under review in reputable peer-refereed journals, while others have been already published as explained above). Due to COVID-19, I have experienced delays in publishing the papers as currently all refereeing processes take longer than expected. However, I am hoping that in 2022 the journal systems would have sufficiently adjusted to the "new normal" and refereeing processes will not take as long as in 2020-2021. I have released the first version of Behavioural Data Science Repository for Urban Applications at the end of 2019, and then revised it to include comments and suggestions from colleagues and scholars working on urban analytics. Updated repository was released in January 2022. The project has also produced an interesting spin-off in the domain of cybersecurity of cities where the Anthropomorphic Learning approach may be particularly useful and valuable. The project has already generated further funding which was spent to address the problem of citizen satisfaction with financial services within urban areas. In October 2019, I have organised a site visit to Birmingham from the Turing team, where my work on urban wellbeing was showcased to the University of Birmingham as well as to Turing. I have also organised a week-long Festival for the general public, which included an art exhibition; an inclusivity and leadership event; an industrial event on services in the city; an academic urban analytics workshop as well as student competition (please, see details here: https://www.inclusionai.org/). The exhibition was developed by the local artist for free and over 2,000 citizens were reached by the Festival locally, attracting attention to the urban wellbeing issues. From September to December 2019 we have also worked closely with HSBC on increasing customer wellbeing and we are currently in preparation of a paper on customer sentiment and financial services. In January 2020, I have received the TechWomen100 award for my contributions to AI and urban science. Throughout 2020-2021, I worked on delivering the Repository and produced more research papers. I have also disseminated research outputs via numerous workshops and conferences as well as set up the Data Driven YouTube Channel, where I talk about behavioural data science and hybrid modelling approaches between decision theory and data science. The following of the channel has grown to more than 7,000 people. In 2021 I have also created the Behavioural Data Science community for practitioners on LinkedIn. We meet regularly for workshops and talks. The community currently has over 800 members. I am also currently in the process of editing the new Handbook in Behavioural Data Science which will be published by Cambridge University Press in 2022. The book in co-edited by professor Thomas Hills from the University of Warwick. This publication will incorporate contributions from many academics working in the area of behavioural data science around the globe and will be a major reference manual in the field. The project also produced a spin-off collaboration in 2022-2023 with the Commonwealth Bank of Australia, which funded 2 postdoctoral fellows to do research on behavioural data science in financial services concentrating on maximizing customer wellbeing in urban and rural contexts. |
| Exploitation Route | The outputs of my current research are useful not only to cities but also to third sector and members of general public. Current research informs decision making of cities (in the way they should incorporate behavioural factors into their strategy); third sector (as my research suggests ways in which these organisations can deliver better urban services and develop more successful fundraising campaigns) as well as general public (as they can better understand their risk preference and biases which prevent them from making more optimal decisions). I have also built the Behavioural Data Science Repository for Urban Applications which will provide practical decision support tools to different stakeholders in the project. Additionally, the Cambridge Handbook of Behavioural Data Science will be used as a reference manual in behavioural data science field by students, academics, and practitioners. |
| Sectors | Communities and Social Services/Policy,Digital/Communication/Information Technologies (including Software),Financial Services, and Management Consultancy,Leisure Activities, including Sports, Recreation and Tourism,Government, Democracy and Justice,Retail,Security and Diplomacy,Transport,Other |
| URL | https://www.inclusionai.org/ |
| Description | The methodology of Anthropomorphic Learning has been successfully tested in several environments. Specifically, the methodology was applied to improve citizen's decision making in the context of urban and retail services. Tests show that suggestions generated by the decision support systems based on Anthropomorphic Learning is associated with much higher citizen satisfaction rates (72-86%) compared with systems based on Machine Learning (33-54%) and Deep Learning (43-59%). Applications of Behavioural Data Science modelling which resulted from the project are also of particular interest to policy makers who are engaged in cybersecurity decision making. Safe Cities modelling which emerged from this project has already attracted attention of the Metropolitan Police as well as other stakeholders. In 2019-2020, the Anthropomorphic Learning approach was tested in three use cases: (1) time perceptions and wellbeing; (2) responsible business and wellbeing; (3) wellbeing and security - all in application to urban contexts. In 2020-2021 an additional application to satisfaction in media sector was discovered, tested, and a paper was published to showcase this additional use case. The results are promising: 16 papers were written on methodology and applications of the new method. Results were showcased at different conferences, workshops, as well as through the media. In 2022-2023 I explored how the impact from my findings could be better achieved in the original 3 domains as well as look at potential extensions into other domains. This led to a new collaboration with the Commonwealth Bank of Australia, where I developed a new behavioural science model, which allowed me to predict financial hardship for customers based on their financial habits. The project delivered better customer well-being as the bank can now predict the financial hardship of their customers 1 year in advance and intervene to help these customers strengthen their financial resilience. |
| First Year Of Impact | 2021 |
| Sector | Communities and Social Services/Policy,Digital/Communication/Information Technologies (including Software),Financial Services, and Management Consultancy,Government, Democracy and Justice,Security and Diplomacy,Transport |
| Impact Types | Societal,Policy & public services |
| Description | Keynote Address on Cybersecurity of Cities at the "Secure Cities - Human Behaviours" Public Debate organised by the London Metropolitan Police |
| Geographic Reach | National |
| Policy Influence Type | Influenced training of practitioners or researchers |
| Impact | On February 26, 2019 the Metropolitan Police hosted a public debate on "Secure Cities - Human Behaviours". The event was attended by representatives of police, defence institutions as well as policy makers. The goal of the event was to raise awareness amongst police and policy makers about current behavioural science methodologies in application to safe cities. My presentation educated policy makers about new methodologies and was a subject of a public discussion. |
| Description | National Consultation on Experimentation |
| Geographic Reach | National |
| Policy Influence Type | Contribution to a national consultation/review |
| Impact | We are exploring how data policymakers and data practitioners can work in more innovative and experimental ways. Currently, the main impact was the development of roadmap for experimentation and providing a link between research and public policy using experimentation. Public policy makers who attended the consultations benefited from the new understanding of the limitations and benefits of experimental methods for policy making. |
| URL | https://docs.google.com/document/d/1Ok65iZqlmEM3JqApH99JDlUtS0XlT1LeOMxPUw2Qmoo/edit |
| Description | Using AI and Behavioural Insights to Optimize Complaint Resolution for Better Service Delivery |
| Amount | £33,827 (GBP) |
| Organisation | HSBC Bank plc |
| Sector | Public |
| Country | United Kingdom |
| Start | 04/2019 |
| End | 10/2019 |
| Description | Value in a Smart City Context: New Business Models for Sustainable Urban Environments |
| Amount | £10,000 (GBP) |
| Organisation | Alan Turing Institute |
| Sector | Academic/University |
| Country | United Kingdom |
| Start | 07/2018 |
| End | 09/2018 |
| Title | Anthropomorphic Learning |
| Description | The Anthropomorphic Learning approach is a synergy between decision theory methodology and machine learning. It is fully tractable, explainable, requires relatively small training sets and generally predicts with higher accuracy than existing machine learning or deep learning algorithms (according to preliminary test results). |
| Type Of Material | Model of mechanisms or symptoms - human |
| Year Produced | 2019 |
| Provided To Others? | No |
| Impact | We have not observed impacts yet as the methodology is still being developed. |
| Title | Behavioural Data Science Repository for Urban Applications |
| Description | The repository represents a collection of data on global urban preferences as well as toolbox of useful decision support methods for different stakeholders. In 2019-2020 a preliminary version of the repository was released via https://www.inclusionai.org/ (the tool, which I have developed for this purpose). I have received many comments and suggestions from the urban data science community. During 2019-2021, I incorporated these comments and released the new version of the repository at the beginning of 2022. |
| Type Of Material | Database/Collection of data |
| Year Produced | 2022 |
| Provided To Others? | Yes |
| Impact | Preliminary version of the repository was released at the end of 2019. Current version was released in January 2022. The repository is hosted at https://www.inclusionai.org. |
| URL | https://www.inclusionai.org/ |
| Description | Artificial Intelligence Innovation Network (AIIN) Keynote Address on Behavioural Science and Artificial Intelligence |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | I have presented my work on Behavioural Science and AI at the AIIN event in London. The talk sparkled many debates around hybrid modelling approaches and the value added by behavioural science in AI modelling. |
| Year(s) Of Engagement Activity | 2018 |
| URL | https://www.youtube.com/watch?v=at1mXnRClMY |
| Description | Behavioural Data Science of Diversity and Inclusion talk at the Alan Turing Institute |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | I gave talk at the Alan Turing Institute, which reached 70 participants. Most of them were representatives of UK businesses. The talk led to further discussions of potential research projects with 2 companies. |
| Year(s) Of Engagement Activity | 2021 |
| Description | DREAM CDT Keynote Address: Understanding Risk and (Cyber) Security of Cities through Human Behaviour |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Postgraduate students |
| Results and Impact | Keynote address at the DREAM CDT on security of cities was attended by 40 postgraduate students, academics and practitioners. Future collaborations were discussed. |
| Year(s) Of Engagement Activity | 2019 |
| URL | https://twitter.com/EmmanouilTranos/status/1108691184522838016/photo/1 |
| Description | Data Driven YouTube Channel |
| Form Of Engagement Activity | A broadcast e.g. TV/radio/film/podcast (other than news/press) |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Public/other audiences |
| Results and Impact | In 2020 I have set-up a new YouTube channel to disseminate results of my Fellowship. The channel is called "Data Driven". Over the course of 2020-2021, I produced over 100 videos and podcasts and grown the audience of the channel from 0 to almost 7,000 followers. |
| Year(s) Of Engagement Activity | 2020,2021 |
| URL | https://www.youtube.com/channel/UC7QY4zs_ASJej2CvQTGikhg |
| Description | Decision Under Uncertainty: from Theory to Practice, Conference Presentation, St Gallen, Switzerland |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | The talk on the topic Behavioural Data Science of Decision Making was delivered at a conference in St Gallen, Switzerland. The talk was well-attended by a diverse audience of individuals who were interested in the topic. Practitioners were interested in applying insights to improve their decision-making processes in their respective industries. |
| Year(s) Of Engagement Activity | 2022 |
| Description | Invited Lecture at the Frankfurt School of Finance and Management |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | On February 18-24, 2019 I visited Frankfurt School of Finance & Management, Department of Management to establish collaboration and work on a joint project with Dr Yevgen Bogodistov: https://www.frankfurt-school.de/home/research/staff/Yevgen-Bogodistov Dr Bogodistov and I started to work on a joint paper "Urban Wellbeing and Sustainable Business". On February 19th, 2019 Professor Pogrebna also gave a research seminar for the faculty of the Department of Management at the Frankfurt School of Finance & Management. Return visit for Dr Bogodistov to the University of Birmingham is planned for 2020. |
| Year(s) Of Engagement Activity | 2019 |
| Description | Invited Talk at Tilburg University |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Undergraduate students |
| Results and Impact | On April 19-28, 2019 I visited Vrije Universiteit Amsterdam (Amsterdam) and Tilburg University (Tilburg). During her visit, I established collaborations with Prof Philipp Koellinger (https://research.vu.nl/en/persons/philipp-koellinger) as well as Dr Spyros Angelopoulos (https://www.tilburguniversity.edu/staff/s-angelopoulos) As a result of this visit, the work on the paper "Urban Wellbeing and Time Perceptions" started in April 2019. I also gave two research seminars at Tilburg University - one to students at the Department of Management on October 23, 2019 and the other - to faculty at the School of Economics and Management on October 24, 2019. Since April 2019, Dr Amgelopoulos visited the University of Birmingham in May 2019 and in October 2019. A visit from Prof Koellinger is planned for 2020. |
| Year(s) Of Engagement Activity | 2019 |
| Description | Invited Talk at the MCI, Innsbruck, Austria |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | The invited talk on "Using Behavioural Data Science for Content Creation in Media Applications" was delivered at the Management Center Innsbruck (MCI) in Austria. The audience comprised of practitioners, academics, and postdoctoral students interested in behavioural data science and its application in content creation for media applications. The objective of the talk was to explore the emerging field of behavioural data science and its potential in creating engaging and interactive content for media applications. The speaker began the session by introducing the concepts of behavioural data science and its applications in various industries, including media and entertainment. The talk highlighted how behavioural data science can help understand user behaviour, preferences, and interests, and how this information can be used to create personalised and relevant content for different media applications. This content can include digital ads, social media posts, videos, podcasts, and more. The audience learned about the different data sources and tools used in behavioural data science, such as data mining, machine learning, and predictive analytics. The speaker explained how these tools can help analyse massive amounts of user data, identify patterns, and predict future behaviour. The audience was also introduced to real-world examples of how behavioural data science is being used in the media industry. Examples included Netflix's recommendation engine, YouTube's video recommendations, and Spotify's music recommendations, among others. These platforms utilise behavioural data science to provide personalised recommendations to their users, based on their listening and viewing history, search preferences, and other behavioural data. The session concluded with a discussion on the challenges and ethical considerations of using behavioural data science in content creation. The speaker emphasised the importance of respecting user privacy and ensuring that data is collected and used ethically, with user consent and transparency. |
| Year(s) Of Engagement Activity | 2022 |
| Description | Invited Talk: NSW Government, Department of Customer Service, Sydney, Australia |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Policymakers/politicians |
| Results and Impact | Invited talk "Behavioural data Science of Consumer Choice" was delivered to NSW Government, Department of Customer Service in Sydney, Australia on October 26, 2022. 50 policy-makers attended the talk. The talk led to further conversations with policy makers about behavioural data science. |
| Year(s) Of Engagement Activity | 2022 |
| Description | Invited Talk: University of Haifa |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Other audiences |
| Results and Impact | I travelled to the University of Haifa, School of Political Sciences to establish collaboration with the local team - Professor Michael Gross, Professor Daphna Canetti and their PhD students. I gave a talk at the University of Haifa on November 6, 2019 on urban wellbeing, sentiment and security of cities. The visit was scheduled from November 2nd to November 8th, 2019. University of Haifa covered the cost of accommodation in Haifa, transfer from and to Ben Guiron airport in Tel Aviv, as well as subsistence costs. The Alan Turing Institute covered the cost of local UK travel from Birmingham to London and back. Joint project on security and wellbeing in cities is planned with the Haifa researchers. |
| Year(s) Of Engagement Activity | 2019 |
| Description | Keynote Address at The Institution of Engineering and Technology Conference on Behavioural Science in Transport |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | Ganna Pogrebna gave a keynote talk at the Behavioural Science in Transport Event organised on November 5, 2018 by the Institution of Engineering and Technology in London (UK). The talk title was "Behavioural Aspects of the Cybersecurity of Transport". The event was attended by policy makers, practitioners, academics, students, and the general public. |
| Year(s) Of Engagement Activity | 2018 |
| URL | https://www.theiet.org/events/documents/bst-presentations.cfm |
| Description | Keynote Address at the 15th Australia and New Zealand Workshop on Experimental Economics in Sydney, Australia |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Postgraduate students |
| Results and Impact | Keynote address "Behavioural Data Science of Leadership" was delivered at the the 15th Australia and New Zealand Workshop on Experimental Economics in Sydney (Australia). The event was attended by early career researcher 9postgraduate students) and academics. |
| Year(s) Of Engagement Activity | 2022 |
| URL | https://www.sydney.edu.au/content/dam/corporate/documents/faculty-of-arts-and-social-sciences/school... |
| Description | Keynote Address at the 2018 FintechTalents Conference |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | I have presented new methodologies (synergies between AI and decision theory) at the FintechTalents 2018 Conference in London. The talk covered application to financial services within the city. There was a high interest from businesses as a result of that event. |
| Year(s) Of Engagement Activity | 2018 |
| URL | https://www.fintechtalents.com/ |
| Description | Keynote Address at the 24th International Congress on Modelling and Simulation (MODSIM2021): Anthropomorphic Learning: Bridging Behavioural Science and Data Science to Predict Human Behaviour |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Other audiences |
| Results and Impact | I gave a keynote address at the 24th International Congress on Modelling and Simulation (MODSIM2021): Anthropomorphic Learning: Bridging Behavioural Science and Data Science to Predict Human Behaviour. The even was face to face and attended by over 400 people in person and close to 1000 online. Most participants were academics, some were practitioners and business representatives. |
| Year(s) Of Engagement Activity | 2021 |
| URL | https://mssanz.org.au/modsim2021/plenary.html |
| Description | Keynote Address at the Australia and New Zealand Regional Science Association International (ANZRSAI) 45th Annual Conference in Wagga Wagga, Australia |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Keynote address "Anthropomorphic Learning: Bridging Behavioural Science and Data Science to Predict Human Behaviour" was delivered at the Australia and New Zealand Regional Science Association International (ANZRSAI) 45th Annual Conference in Wagga Wagga, Australia. Practitioner audience, postdoctoral students and academics attended the talk. The talk led to requests for collaboration. |
| Year(s) Of Engagement Activity | 2022 |
| URL | https://www.anzrsai.org/ |
| Description | Keynote Address at the Deep Learning Computer Vision Practitioner Evening |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | On November 25, 2020 I gave a keynote address at the Deep Learning Computer Vision Practitioner Evening to a group of practitioners/businesses. Approximately 50 people attended the talk. The purpose was to showcase the methodology of anthropomorphic learning. |
| Year(s) Of Engagement Activity | 2020 |
| Description | Keynote Address at the Financial Services Forum "Keeping Pace with Tech: Ethics, Digitisation and Understanding Risk" |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Industry/Business |
| Results and Impact | I gave a Keynote Address at the Financial Services Forum "Keeping Pace with Tech: Ethics, Digitisation and Understanding Risk". The talk reached over 2,000 people online. Most of them were business professionals. The activity led to further discussions with industry. |
| Year(s) Of Engagement Activity | 2021 |
| Description | Keynote Address at the Google AI Services Workshop in Dublin |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Over 500 Google AI data scientists attended Google Service summit in 2018 in Dublin, where I showcased my current algorithmic work on synergies between machine learning and decision theory models in application to urban environments. My method of "anthropomorphic learning" - enhanced machine learning algorithm which allows to predict human behaviour using relatively small training sets through a tractable and explainable model has attracted a lot of attention and response from Google analysts. |
| Year(s) Of Engagement Activity | 2018 |
| Description | Keynote Address at the Warwick Behavioural Science Summit Roundtable on New Methods in Behavioural Science |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Postgraduate students |
| Results and Impact | Over 100 students, policy makers and business practitioners attended the Warwick Behavioural Summit where I presented my methodology of anthropomorphic learning in application to predicting behaviour in urban context. There was a lot of interest to my work from businesses as a result. |
| Year(s) Of Engagement Activity | 2018 |
| Description | Keynote Address, Australian Conference of Economists (ACE) in Brisbane, Australia, forthcoming |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Keynote address "Behavioural Data Science as a Game Changer for Understanding the Interface between Human and Digital Systems in the New Digital Economy" is planned for the Australian Conference of Economists (ACE) in Brisbane, Australia, forthcoming. Several practitioners have already reached out for further information. |
| Year(s) Of Engagement Activity | 2023 |
| URL | https://ace2023.org.au/ |
| Description | Keynote Talk on Data Science and City Services at the Turing Social Sciences Workshop |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | I presented my work in progress on ,modelling optimal city services at the Turing Social Sciences Workshop in London. The audience engaged with me afterwards about different methodologies covered in the talk. |
| Year(s) Of Engagement Activity | 2018 |
| Description | Keynote address at the Operations Research and Artificial Intelligence Summit of the Operations Research Society |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Online keynote address was delivered to the audience of the Artificial Intelligence Summit of the Operations Research Society. The talk reached over 500 practitioners and led to interest from many companies in my hybrid modelling approach. |
| Year(s) Of Engagement Activity | 2021 |
| URL | https://www.customerinsightleader.com/events/thinking-more-deeply-with-the-or-society/ |
| Description | Keynote on Behavioural Data Science at Turing-HSBC Event |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | I presented my work on Behavioural Data Science (including applications to urban science) at the Turing-HSBC Event in London. The talk and the podcast became very popular and I have received many request for further information. |
| Year(s) Of Engagement Activity | 2019 |
| URL | https://www.youtube.com/watch?v=eoLL906SnLk |
| Description | MIT Sloan Invited Talk |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Industry/Business |
| Results and Impact | On March 5, 2020 I gave a talk at MIT Sloan talking about behavioural data science and anthropomorphic learning. The purpose of the talk was to showcase the current results of the project to the US business community, who actively attend the seminar series. |
| Year(s) Of Engagement Activity | 2021 |
| Description | Presentation at the 7th International Conference on Business Servitization (ICBS 2018) |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | I presented my research on Anthropomorphic Learning and city services at the ICBS 2018 Conference in Portugal. The talk generated a lot of interest to new modelling techniques among scientists and business practitioners. |
| Year(s) Of Engagement Activity | 2018 |
| URL | https://www.servitization.org/p/home.html |
| Description | Presentation at the Foundations of Risk and Utility Conference in York |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | I have presented my concept of Anthropomorphic Learning in application to urban decision making at the Foundations of Risk and Utility (FUR) Conference at York. FUR conference is a global decision theory forum and the most prestigious conference in decision and behavioural science. The audience commented on learning about new ways in which urban decisions could be modelled. |
| Year(s) Of Engagement Activity | 2018 |
| URL | https://www.furconference.org/fur-2018/ |
| Description | Presentation at the IAREP-SABE 2018 Conference in London |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Over 200 people attended IAREP-SABE conference in London, where I presented my work on cybersecurity in application to urban decision making. My session attracted a lot of attention and Cyber Domain Specific Scale which I presented at the conference was widely discussed. |
| Year(s) Of Engagement Activity | 2018 |
| URL | https://economics.mdx.ac.uk/sabe-2018/program/ |
| Description | Presentation at the Royal Economic Society Conference 2018 at the University of Sussex |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | I have presented my work on risk perceptions in application to urban decision making at the Royal Economic Society Conference 2018. Presented methodology generated a lot of interest from fellow economists from all around the UK. |
| Year(s) Of Engagement Activity | 2018 |
| URL | https://editorialexpress.com/conference/RESConf2018/program/RESConf2018.html |
| Description | Research Applications and Methods for Economics and Transport Studies (RAMETS) Keynote Address: Smart Cities, Happiness and Transport |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Postgraduate students |
| Results and Impact | 40 people attended the workshop (postgraduate students, academics, practitioners and industry representatives). One on-going research collaborations with Dr Charisma Choudhury emerged from this activity. |
| Year(s) Of Engagement Activity | 2019 |
| URL | https://www.res.org.uk/events-page/research-applications-and-methods-in-economics-and-transport-stud... |
| Description | Responsible Business: The Challenges of Optimising AI Responsibly for Business Success |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | On July 28, 2020 I was a part of the expert panel organized by the Lloyds Centre for Responsible Business. Over 100 people attended the event, where we discussed the new AI methodologies and ethical considerations associated with them. |
| Year(s) Of Engagement Activity | 2020 |
| URL | https://www.birmingham.ac.uk/research/responsible-business/events/2020/the%20challenge%20of%20optimi... |
| Description | SAGE Publishing Filming for the SAGE Data Science Repository |
| Form Of Engagement Activity | A broadcast e.g. TV/radio/film/podcast (other than news/press) |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Public/other audiences |
| Results and Impact | In collaboration with the SAGE publishing I have filmed a tutorial on Anthropomorphic Learning which will become a part of the SAGE Data Science Online Repository (to be released in 2019). The Repository will have global reach and I have already received requests for further information from several viewers. |
| Year(s) Of Engagement Activity | 2018 |
| URL | https://sage.figshare.com/ |
| Description | Talk at the Resilient Cities group at the University of Birmingham |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Professional Practitioners |
| Results and Impact | 60 people attended my talk on "Smart Cities and New Analytics" at the University of Birmingham. I have presented several research strands I am working on within my fellowship project. The audience commented on the new behavioural approach to modelling behaviour within cities and reported changed attitudes towards modelling approaches for urban science. |
| Year(s) Of Engagement Activity | 2018 |
| Description | Talk on Time Perceptions and Urban Wellbeing at the Urban Analytics Workshop |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Other audiences |
| Results and Impact | Around 50 people attended the workshop. Industrial partners (Aecom in particular) are currently in discussion with me about potential projects. |
| Year(s) Of Engagement Activity | 2019 |
| URL | https://www.birmingham.ac.uk/schools/business/departments/economics/events/2019/10/urban-analytics-w... |
| Description | The Open Data Institute Roundtable Address: Experimentalism and the Fourth Industrial Revolution Keynote Address |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Policymakers/politicians |
| Results and Impact | I have spoken at the The Open Data Institute Roundtable Address: Experimentalism and the Fourth Industrial Revolution roundtable. The audience were primarily policy makers. The presentation led to further discussions with policy makers. |
| Year(s) Of Engagement Activity | 2021 |
| URL | https://theodi.org/article/asimovs-data-revolution/ |
| Description | The Turing Roundtable on Understanding, Measuring and Improving Wellbeing at Scale |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Public/other audiences |
| Results and Impact | I co-organized a roundtable on Understanding, Measuring and Improving Wellbeing at Scale at the Warwick Behavioural Science Summit on June 20, 2019. Over 100 people attended the roundtable. Interest from many organisations working on city services at Birmingham and Coventry was registered. |
| Year(s) Of Engagement Activity | 2019 |
| URL | https://warwickbit.wordpress.com/speakers/ |
| Description | The University of Notre Dame Seminar on Behavioural Data Science |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | On January 8, I gave a talk on behavioural data science to the postgraduate students at the University of Notre Dame (USA). The purpose was to showcase the results of the project to student audience. |
| Year(s) Of Engagement Activity | 2021 |
| Description | The University of Warwick Seminar on Behavioural Data Science |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | On January 30, 2021 I gave a talk on anthropomorphic learning to a group of executive postgraduate students at the University of Warwick. The purpose of the talk was to showcase the new methodology developed within the frame of my fellowship. |
| Year(s) Of Engagement Activity | 2021 |
| Description | Turing Urban Analytics Seminar |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Postgraduate students |
| Results and Impact | On January 14, 2021 I gave a talk at the Alan Turing Institute Urban Analytics meeting talking about cities, wellbeing and security. The seminar was attended by approximately 70 people. The majority were postgraduate students. The purpose of the talk was to showcase results of my fellowship project to the Urban Analytics students. |
| Year(s) Of Engagement Activity | 2021 |
| Description | Turing at Birmingham Day |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Other audiences |
| Results and Impact | The University of Birmingham hosted the Alan Turing Institute Director and CEO, Sir Adrian Smith, and members of the Institute's senior management team, including: Dr Donna Brown (Director of Academic Engagement), Professor Mark Briers (Programme Director, Defence and Security Programme), Professor Chris Holmes (Programme Director, Health & Medical Sciences Programme), Dr Lukasz Szpruch (Programme Director, Finance and Economics Programme), Professor Jon Rowe (Programme Director, Data Science for Science Programme), and Dr Theo Damoulas (Deputy Programme Director, Data Centric Engineering Programme). The event also featured a showcase of the University of Birmingham AI projects: Ganna Pogrebna (Turing University Lead for the University of Birmingham), Dr Iain Styles (School of Computer Science, Turing Fellow), Professor Jean-Baptiste Cazier (Institute of Cancer and Genomic Sciences, Turing Fellow), Professor Sylvie Delacroix (Birmingham Law School, Turing Fellow), and Dr Luisa Orsini (School of Biosciences, Turing Fellow) gave an overview of the cutting-edge data science research at the University of Birmingham. One of the speakers was Dr Emmanouil Tranos (University of Bristol, Turing Fellow), who talked about urban analytics research at the Alan Turing Institute, the University of Birmingham and the University of Bristol. Ganna Pogrebna also presented on urban analytics. Feedback has been very positive from both the Institute and the University. For more details and a brief video from the event, see the link below. |
| Year(s) Of Engagement Activity | 2019 |
| URL | https://www.turingatbirmingham.org/post/turing-birmingham-day-report-and-newsletter-october-17th-201... |
| Description | UCAS Invited Talk: Behavioural Data Science |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Around 20 UCAS workers as well as representatives of DSTL attended the talk. The talk was recorded and is currently available on YouTube. The talk let to further discussions of potential joint projects with UCAS as well as DSTL (conversations are still on-going). |
| Year(s) Of Engagement Activity | 2019 |
| URL | https://www.youtube.com/watch?v=v9EXEr0IAyc |
| Description | Warwick Behavioral Insights Team (WBIT) Summit Keynote Address |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Public/other audiences |
| Results and Impact | On June 5, 2020 I gave a talk on behavioural data science and anthropomorphic learning at the Warwick Behavioural Insights Team summit. Over 4000 people watched the even online. |
| Year(s) Of Engagement Activity | 2020 |
| URL | https://youtu.be/X8EGQkXUg78 |