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.

This chapter examines the trend towards regionalism upon stock market returns for a sample of Asian countries. We find that stock markets are becoming regionally integrated at a faster rate than globally. This finding reflects the growing co-operation between Asian countries. This study focuses upon Indonesia, Malaysia, the Philippines, South Korea, Taiwan and Thailand. These markets suffered severe contagion effects in relation to the Asian financial crisis that occurred during 1997. In addition, this study reports on the significant economic and political events that occurred in Asian economies from 1980. This study concludes that increases in liberalization coupled with stronger ‘regionalism’ in South East Asia contributed to the Asian financial crisis in 1997, in addition to the structural weaknesses in their financial systems. Policy setters may consider reducing the amount of intra-regional dependence in order to reduce the impact of financial crises and improve stability of the financial system.

Terrorism, an important component of Political risk as a possible determinant of ADRs (American Depository Receipts) returns have received little attention in academic literature. To address this issue and examine whether political risk is a major determinant of ADR returns of emerging market countries, this paper empirically examines market valuation of Indian ADRs around acts of terrorism. Using a sample of 52 such events in the sample period Jan 2003‐Dec 2003 we empirically analyze returns of Indian ADRs. The results from our study indicate a marginally negative significant effect, failing to indicate that event of terrorist attacks severely affect the Indian ADRs listed on the US stock market. This may be explained by a combined effect of; (a) the optimism of US investors towards emerging markets, and (b) market participants becoming more resilient and making informed choices around the “general” events of terrorism.

A month or so after the Stresa meeting, the French ISHM chapter, organising a session on ‘Gallic inks’ (!), summoned me to deliver some comments on the 5th European Hybrid Microelectronics Conference. Although it was only a matter of interlude during this technical session, I felt the task quite a difficult one. It became a hazardous project when Brian C. Waterfield kindly asked me to let what is in fact a personal opinion—my personal opinion, standing back from my daily work—appear in Hybrid Circuits. I'll do my best.

This work aims to check the validity of the hypotheses of the agency, signalling, political costs and proprietary costs theories in the disclosure of information online. More specifically, to determine the prevalence of the purposes alleged by those theories, we analyse the effect of industry concentration and other factors on an index of items of information disclosed on corporate web sites, in its entirety as well as its breakdown into information whose elaboration and disclosure is compulsory and information whose elaboration and disclosure is voluntary.

First, a content analysis of the quoted non‐financial Spanish companies' web sites was carried out. To do this, three disclosure indexes were created and applied. Then three causal models were estimated by applying a linear regression, taking several factors into consideration.

The findings emphasise the relevance of the hypotheses of political costs theory as the main explanatory factor for voluntary disclosure of information on the internet by quoted Spanish firms. In particular, the hypothesis that the greater the firm's monopolistic power, the more visible the company is and the more political costs it faces. To reduce these costs, such companies have an interest in disclosing greater amounts of information.

The researchers have analysed only one year of data from one country, but this analysis is significant because the motives which lead a firm to disclose information can be very different depending on its geographic location, especially if the factors which determine disclosure practices are associated with the political costs that the companies face.

This is the first study to examine the effect of industrial concentration on the disclosure of information online.