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 inaugural meeting of the newly established National Party was held in the Queen's Hall, Langham Place, on Thursday, October 25th, under the presidency of Admiral Lord Beresford. There was a large and distinguished audience numbering about 3,000 persons, among those on the platform being Lord Montagu of Beaulieu, Brigadier‐General Page Croft, M.P., Mr. Havelock Wilson, Miss Constance Williams, the Hon. G. J. Jenkins (all of whom addressed the meeting), Earl Bathurst, Sir C. Allom, Major Alan Burgoyne, M.P., Colonel Cassal, Mr. G. K. Chesterton, Sir R. Cooper, M.P., Capt. Viscount Duncannon, M.P., Sir W. Earnshaw Cooper, Mr. H. A. Gwynne, Mr. Rowland Hunt, M.P., Lieut.‐Col. Lord Leconfield, Lord Leith of Fyvie, Admiral Sir H. Markham, The Earl of Northesk, Colonel R. H. Rawson, M.P., Lord Edward St. Maur, Admiral Sir Edward Seymour, Lord Stafford and others.

Most years, several AIB members are elected as AIB Fellows on account of their excellent international business scholarship, and/or past service as AIB President or Executive Secretary. The Fellows are in charge of electing Eminent Scholars as well as the International Executive and International Educator (formerly, Dean) of the Year, who often provide the focus for Plenary Sessions at AIB Conferences. Their history since 1975 covers over half of the span of the AIB and reflects many issues that dominated that period in terms of research themes, progresses and problems, the internationalization of business education and the role of international business in society and around the globe. Like other organizations, the Fellows Group had their ups and downs, successes and failures – and some fun too!

The unsatisfactory state of the law with regard to prosecutions for impoverished milk has been further exemplified in a series of prosecutions at Oldham. Three farmers were summoned for having sold milk “ not of the nature, substance and quality demanded by the purchaser,” and the evidence produced showed that the milk in each case was not only deficient as compared with the standard set by the Board of Agriculture, but even more deficient when compared with mixed samples taken at the farm. The Deputy Town Clerk, who conducted the prosecution, pointed out that the case of Wilkinson v. Clark clearly showed that the Inspectors were justified in going to the farm for a second sample, if the second was comparable with the first, and were entitled to rely on the Public Analyst's certificate for both samples. He argued that, in view of the enhanced price of milk, it was very necessary that the purchaser should be adequately protected and that he should obtain what he paid for — pure unadulterated milk. The defence in the first case was a denial of the milk having been tampered with, it being sold “ as it came from the cow.” Results of experiments at the Yorkshire College for Agricultural Education were quoted to show that wide variations in the quality of the milk might occur for which the farmer ought not to be held responsible. In the present case it was admitted that one of the cows was not milking satisfactorily, and had a “ hard udder.” The milk from this cow when examined closely, was stated in the defendant's evidence to be “ more like water.” This had only been found out on the morning when the first sample had gone into the churn for sale. The Bench, after consultation, expressed themselves satisfied that the milk had not been tampered with, and dismissed the summons.

It is now forty years since there appeared H. R. Plomer's first volume Dictionary of the booksellers and printers who were at work in England, Scotland and Ireland from 1641 to 1667. This has been followed by additional Bibliographical Society publications covering similarly the years up to 1775. From the short sketches given in this series, indicating changes of imprint and type of work undertaken, scholars working with English books issued before the closing years of the eighteenth century have had great assistance in dating the undated and in determining the colour and calibre of any work before it is consulted.

This paper expands the theory of competitive decision making in declining industries. Kelley and Thibaut's theory of interdependence is used to analyze and explain the use of competitive and cooperative strategies among competitors. The analysis suggests that although the use of competitive strategies is more likely, cooperative strategies should produce higher performance. Several barriers to, and facilitators of, the use of cooperative strategies in declining industries are identified, and their prescriptive implications are discussed.

This study reports an examination of the relationships between Porter's (1980) generic strategies, dynamic environments, and performance. In me study, profile deviation is used to test strategy—environment fit. A sample of 173 acute care hospitals was used to test the proposed relationship. Results from the study indicate that adherence to an externally specified ideal strategy profile has a positive effect on firm performance. From a methodological standpoint, results suggest that empirical and theoretical profiles have equal predictive validity, and both have a higher predictive validity, than a random profile. Results also suggest that profiles can not be assumed to be robust to differences in performance measures used.