About the themed issue
Machine learning techniques are increasingly being evaluated in the academic community and at the same time leveraged by practitioners at policy institutions, like central banks or governments. A themed issue in the Journal of Econometrics aims to present frontier research that sits at the intersection of machine learning and economic policy.
There are good reasons for policy makers to embrace these new techniques. Tree-based models or artificial neural networks, often in conjunction with novel and rich data sources, like text or high-frequency indicators, can provide prediction accuracy and information that standard models cannot. For example, machine learning can uncover potentially unknown but important nonlinearities within in the data generating process. Moreover, natural language processing − made possible by advances in machine learning is increasingly being applied to better understand the economic landscape that policymakers must survey.
These upsides of these new techniques come with the downside that it often is not clear what the mechanism through which the machine learning model operates, i.e. the black box critique. Much of the existence of the black box critique is due to how machine learning models evolved with a focus on accuracy. However, this single focus can be particularly problematic in decision making situations, where all stakeholders have an interest in understanding all pieces of information which enter the decision-making process, irrespective of model accuracy. The tools of economics and econometrics can help to address this problem thereby building bridges between disciplines.
This themed issue in the Journal of Econometrics (JoE) is jointly organised by major policy institutions and universities. It aims to cover a diverse set of problems where machine learning approaches and novel data sources are applied to situations, which are relevant to economic policy making. It will cover a range of applications and methodological contributions such as deep learning, text analytics, reinforcement learning, shock or treatment identification, forecasting and nowcasting, as well as different approaches to model interpretability and inference, among others.
It is crucial that the policy dimension of accepted papers is significant and integral to the contribution of each paper. Therefore, it is not sufficient that the policy relevance of these papers is restricted to an empirical illustration. Applications, case studies, or experiments should show in a clear way how the insights derived from them can help economic decision makers. It is also important to note that the usual rigorous editorial standards of the Journal will apply. So, for example, methods must be clearly and rigorously presented and any underlying assumptions and conditions much be explicitly and carefully stated.
Submission: If your paper covers both the methodological and policy angle outlined above, we invite you to submit your paper to the JoE themed issue “Machine Learning for Economic Policy [96] [IG000583]”. The deadline for submission is 31, May 2023. Submissions will be processed as they arrive.
Handling editor (JoE)
- Serena Ng (Colombia University)
Guest associated editors
- Maryam Haghighi (Bank of Canada)
- Andreas Joseph (Bank of England)
- George Kapetanios (King’s College London)
- Christoper Kurz (Federal Reserve Board)
- Michele Lenza (European Central Bank)
- Juri Marcucci (Bank of Italy)
Call for papers