F4SG 2021

2nd International Workshop on Forecasting for Social Good

24th - 25 th Junest, 2021   |   Virtual

F4SG 2021: The 2nd International Workshop on Forecasting for Social Good follows the success of F4SG 2018 and the International Journal of Forecasting's special issue on Forecasting for Social Good.

While there is a growing recognition by agencies, organizations, and governments that data-driven decision making tools, like forecasting models, can offer significant improvements to the societies they are working to improve, there is not a cohesive body of research that offers guidance on how to best implement, understand, use, and evaluate forecasting methods for societal impact in practice. Furthermore, the research on forecasting for social good has been relatively slow and sporadic, both in academic publications and practical applications. The goal of this workshop is thus to improve the research and practice in issues related to forecasting for social good by: facilitating interactions between practitioners, researchers, and policy makers to develop a cohesive and sustainable network of international collaborations with a focus on issues related to forecasting for social good; promoting the development of new methodology and metrics to address the specific challenges related to forecasting for social good; providing professional development to policy makers; gaining a better understanding of the available data, challenges in data acquisition, and the uncertainty present in the data used to produce forecasts; and, addressing the ethical issues related to the use of forecasting methods for problems that impact society.

The F4SG has a special focus on facilitating the professional growth of early career faculty, postdocs, and students who will likely play a leading role in the field of forecasting for social good in the coming years.

CALL FOR SPECIAL SESSIONS

If you would like to organise a special session, please contact: Bahman Rostami-Tabar (rostami-tabarB@cardiff.ac.uk) A special session consists of 3 or 4 talks around a specific, forecasting for social good theme. You are allowed to be one of the speakers in a session you organize. All you would need to do is send us the proposed theme and invite 2-3 other speakers to speak on the related topic. The length of each invited talk should be about 30 minutes.

Special sessions on academic forecasting research and practice oriented applications in Forecasting for Social Good are welcome.

Relevant topics include (but are not limited to):

Health and Healthcare
Wellbeing
Humanitarian and disaster relief operations
Agriculture
Education

Social Services
Poverty
Homelessness
Inequality
Sustainability

Environment
Transportation
Fraud, collusion, and corruption
Government
Public safety, criminal justice, and security

Important Dates:

Special Session Submission deadline:  April 23, 2021 
Registration deadline:  June 10, 2021
Conference:   24 - 25 June, 2021

Publication Opportunities:

Accepted abstracts will be invited to submit an extended full paper of their work for a special section of the International Journal of Forecasting and Supply Chain Forum: An International Journal. This will be an ideal venue for authors to publish an extended full paper on the work they present at F4SG 2021.

KEYNOTE & INVITED SPEAKERS

Keynote Speakers

Image

Spyros Makridakis Professor and Director of the Institute for the Future (IFF)
University of Nicosia

Image

Laura Albert Professor of Industrial & Systems Engineering
University of Wisconsin-Madison

Image

Nicholas Reich Associate Professor of Biostatistics
University of Massachusetts-Amherst

Image

Leonardo Milano Predictive Analytics Team Lead
Centre for Humanitarian Data, United Nations Office for the Coordination of Humanitarian Affairs (OCHA)

Image

Glenn Milano Sr. Advisor for Demand Planning
United States Agency for International Development (USAID), Office of Population and Reproductive Health

PROGRAM

The US COVID-19 Forecast Hub is a collaborative effort of infectious disease modeling teams from across the world who have made forecasts of the COVID-19 pandemic in the United States. Launched in March 2020, the Hub has aggregated over 200m rows of forecast data from over 90 different models. The ensemble forecast generated each week by the Hub is used as the official forecast of the US Centers of Disease Control and Prevention. This talk will describe the process of building and maintaining the Hub, from the data model used to represent forecasts, to the community-building aspects of incentivizing and recruiting dozens to teams, and the statistical challenges in building and evaluating an ensemble forecast in real-time. More information about the COVID-19 Forecast Hub can be found at https://covid19forecasthub.org/.

Uncertainty in Medicine and in Medical Diagnosis

Spyros Makridakis, University of Nicosia

This paper discusses uncertainty in general and more specifically in medicine while focusing on that affecting medical diagnoses, the major source of medical errors and the leading source of malpractice claims. The paper consists of three parts. The first describes uncertainty and the reasons it is underestimated widely in most decision making settings. The second concentrates on the uncertainty of medical diagnoses and the reasons of its critical importance as it greatly affects medical errors. The last part considers possible solutions to correct the problem and reduce its negative consequences, with a critical emphasis on how to communicate diagnostic uncertainty and risks to patients and provide them with sufficient information to enable them to contribute effectively to decisions about their own treatment and consequently about the quality of their lives. In its conclusion, the paper emphasizes the need for an uncertainty revolution in medicine and suggests ways for materializing such revolution.
Public safety systems are government functions that aim to protect the welfare of the public from risks such as emergencies, crimes, and disasters. Public safety leaders and researchers have been studying how to design and operate public sector systems to manage risk for the last half a century. Although researchers have created a body of knowledge for supporting prescriptive and predictive decisions in the public sector, public safety leaders must continually adapt to address new risks in budget-constrained environments. As a result, many research challenges remain.
Public sector applications are complex systems that span people, processes, vehicles, and critical infrastructure, where decisions are not made in isolation. Rather, decisions are interrelated, with every decision potentially affecting every other decision due to congestion, processing delays, capacities, and uncertainty about what can happen next. In this talk, Dr. Laura Albert will discuss her research that studies how to design and operate public sector systems using predictive and prescriptive analytics. She will discuss how she has connected application to theory in public sector applications in the United States ranging from emergency medical services and critical infrastructure protection. She will also discuss policy insights as well as insights obtained from putting the results into practice in real world settings.

Anticipating humanitarian crises to respond earlier, saving and protecting more lives

Leonardo Milano, United Nations Office for the Coordination of Humanitarian Affairs (OCHA)

Although predictive analytics is not a new field, its application in humanitarian response has only just begun. The increasing availability of data from a variety of sources, together with advancements in statistics and machine learning, is generating a growing interest in using models to gain insight and trigger anticipatory action. Using data science to anticipate humanitarian crises represents a great opportunity for organizations to respond earlier, saving and protecting more lives than ever before. The Centre for Humanitarian Data of the United Nations Office for the Coordination of Humanitarian Affairs is focusing its efforts so that the humanitarian system can reliably use models to trigger action.

REGISTRATION

Registration Fees: FREE


ORGANIZERS & SPONSORS

Organizing Committee:

General Chair:   Dr. Bahman Rostami-Tabar (Cardiff University)
Dr. Michael Porter (University of Virginia)
Prof. Zied Babai (Kedge Business School)
Scientific Chair:   Prof. Aris Syntetos (Cardiff University)
Prof. Rob Hyndman (Monash University)
Prof. Nezih Altay (DePaul University)
Dr. Klaus Ackermann (Monash University)
Dr. Bahman Rostami-Tabar (Cardiff University)
Prof. Zied Babai (Kedge Business School)
Dr. Michael Porter (University of Virginia)
Publication Chair:   Dr. Bahman Rostami-Tabar (Cardiff University)
Prof. Zied Babai (Kedge Business School)
Dr. Michael Porter (University of Virginia)
Prof. Pierre Pinson (IJF Editor in Chief, Technical University of Denmark)

Sponsors:


Contact:

rostami-tabarB@cardiff.ac.uk