Search results

Machine learning (ML), and deep learning in particular, is gaining traction across a myriad of real-life applications. Portfolio management is no exception. This paper provides a systematic literature review of deep learning applications for portfolio management. The findings are likely to be valuable for industry practitioners and researchers alike, experimenting with novel portfolio management approaches and furthering investment management practice.

This review follows the guidance and methodology of Linnenluecke et al. (2020), Massaro et al. (2016) and Fisch and Block (2018) to first identify relevant literature based on an appropriately developed search phrase, filter the resultant set of publications and present descriptive and analytical findings of the research itself and its metadata.

The authors find a strong dominance of reinforcement learning algorithms applied to the field, given their through-time portfolio management capabilities. Other well-known deep learning models, such as convolutional neural network (CNN) and recurrent neural network (RNN) and its derivatives, have shown to be well-suited for time-series forecasting. Most recently, the number of papers published in the field has been increasing, potentially driven by computational advances, hardware accessibility and data availability. The review shows several promising applications and identifies future research opportunities, including better balance on the risk-reward spectrum, novel ways to reduce data dimensionality and pre-process the inputs, stronger focus on direct weights generation, novel deep learning architectures and consistent data choices.

Several systematic reviews have been conducted with a broader focus of ML applications in finance. However, to the best of the authors’ knowledge, this is the first review to focus on deep learning architectures and their applications in the investment portfolio management problem. The review also presents a novel universal taxonomy of models used.

The purpose of this paper is to provide an example of patient-led co-production.

The New Economics Foundation’s six principles of co-production (nef, 2013) have been used to frame the activities undertaken during the author’s relationship with a community mental health nurse.

This paper describes a co-produced project between a patient and a community mental health nurse to create a range of resources and to deliver training, resulting in mutual benefit for both parties.

This paper invites policy makers to consider the unique role that community mental health nurses can play in supporting patients with long-term challenges that have developed because of an imbalance and an abuse of power within earlier relationships; by adopting a co-production approach, centred on the patient’s interests and skills, a working partnership can be achieved wherein both parties feel that they matter.

Co-production is usually used with groups of stakeholders working together in an equitable way to design or deliver a new service; this paper, however, seeks to demonstrate how the process can be effectively used when the project is patient-led within the context of a therapeutic relationship.

Background: Democratic societies thrive when citizens actively and critically engage with new ideas, developments and claims to truth. Not only can such practices result in more effective choice-making, but they can also lead to widespread support for progressive beliefs, such as social justice. Yet with western societies in the midst of environmental, social and political crises, it seems more pertinent than ever that citizens become “ideas-informed”.

Methods: Drawing on a survey of 1,000 voting age citizens in England, this paper aims to provide insight into the following: (1) the current “state of the nation” in terms of whether, and how, individuals keep themselves up to date with regards to new ideas, developments and claims to truth; (2) the impact of staying up to date on beliefs such as social justice; (3) the factors influencing people’s propensity to stay up to date, their support for value-related statements, as well as the strength of these influencing factors; and (4) clues as to how the extant “state of the nation” might be improved.

Results: Our findings indicate that many people do keep up to date, do so in a variety of ways, and also engage with ideas as mature critical consumers. There is also strong importance attached by most respondents to the values one would hope to see in a progressive and scientifically literate society. Yet, as we illustrate with our structural equation model, there are a number of problematic network and educational related factors which affect: (1) whether and how people stay up to date; and (2) the importance people ascribe to certain social values, irrespective of whether they stay up to date or not.

Conclusions: Suggestions for the types of social intervention that might foster “ideas-informed” democracies (such as improved dialogue) are presented, along with future research in this area.