Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
3.5
2.4
Journals
Mathematics
Special Issues
Applications and Mathematical Foundations of Machine Learning in Investments
share announcement

Applications and Mathematical Foundations of Machine Learning in Investments

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "Financial Mathematics".

Deadline for manuscript submissions: 31 May 2024 | Viewed by 16031

Special Issue Editors

Prof. Dr. Peter Schwendner

E-Mail Website
Guest Editor
School of Management and Law, Center for Asset Management, Zurich University of Applied Sciences, 8400 Winterthur, Switzerland
Interests: investments; explainable AI; transparency of investment processes; ML in finance
Dr. Mark James Thompson

E-Mail Website
Guest Editor
School of Management and Law, Center for Asset Management, Zurich University of Applied Sciences, 8400 Winterthur, Switzerland
Interests: financial options; Bayesian statistics; research design and causality
Dr. Jan-Alexander Posth

E-Mail Website
Guest Editor
School of Management and Law, Center for Asset Management, Zurich University of Applied Sciences, 8400 Winterthur, Switzerland
Interests: GreenTech and AI in finance; sustainable finance & SRI/ESG; risk & risk management
Prof. Dr. Per Bjarte Solibakke

E-Mail Website
Guest Editor
Faculty of Economics and Management, Norwegian University of Science and Technology, 6009 Ålesund, Norway
Interests: corporate finance; econometrics
Dr. Kristina Šutienė

E-Mail Website
Guest Editor
Faculty of Mathematics and Natural Sciences, Kaunas University of Technology, 51368 Kaunas, Lithuania
Interests: applied statistics; quantitative finance; data science; time series and forecasting; machine learning; risk analysis

Special Issue Information

Dear Colleagues,

Machine learning (ML) methods have been applied to all steps of investment processes: to include alternative and often unstructured data for selecting single securities, to make the asset allocation process robust against instable return and covariance estimations, to actively time the market in the tactical allocation step, to estimate and manage risk and to generate transparent backtests with a reduced risk of overfitting. Driven by market competition, the adopted methods are often based on the experience of market practitioners and use innovations from scientific fields beyond finance. This market-driven adoption often leads to heuristic approaches not yet as rigorously tested as those from academic financial econometrics or financial mathematics. Diverging and unstructured data present an additional challenge, especially in the field of sustainable investments.     

With this Special Issue, we would like to invite an academic and practitioner audience to investigate ML and AI applications for investment and portfolio management, and to advance the field through mathematical and econometrical contributions. The diversity of suitable methods offers an opportunity for specialists from several fields to contribute together for applications of high current interest.

The diversity of methods and background of contributors is especially visible within the community of the European COST Action “CA19130 – Fintech and AI in Finance”, who are supporting us. We thank the members of three working groups who aim to advance transparency in Fintech applications, decision-support models and investment products and invite further interested persons to join.

Prof. Dr. Peter Schwendner
Dr. Mark James Thompson
Dr. Jan-Alexander Posth
Prof. Dr. Per Bjarte Solibakke
Dr. Kristina Šutienė
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • risk management
  • credit risk
  • investment decisions
  • portfolio construction
  • asset management
  • machine learning
  • alternative data
  • methodological advancements
  • performance analysis
  • explainable AI
  • synthetic data generation
  • mathematical foundations
  • natural language processing
  • supervised learning
  • unsupervised learning
  • reinforcement learning
  • overfitting

Published Papers (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

20 pages, 4024 KiB  
Article
Improving Stock Market Predictions: An Equity Forecasting Scanner Using Long Short-Term Memory Method with Dynamic Indicators for Malaysia Stock Market
by Chin Soon Ku, Jiale Xiong, Yen-Lin Chen, Shing Dhee Cheah, Hoong Cheng Soong and Lip Yee Por
Mathematics 2023, 11(11), 2470; https://0-doi-org.brum.beds.ac.uk/10.3390/math11112470 - 27 May 2023
Cited by 1 | Viewed by 1755
Abstract
Stock market predictions are a challenging problem due to the dynamic and complex nature of financial data. This study proposes an approach that integrates the domain knowledge of investors with a long-short-term memory (LSTM) algorithm for predicting stock prices. The proposed approach involves [...] Read more.
Stock market predictions are a challenging problem due to the dynamic and complex nature of financial data. This study proposes an approach that integrates the domain knowledge of investors with a long-short-term memory (LSTM) algorithm for predicting stock prices. The proposed approach involves collecting data from investors in the form of technical indicators and using them as input for the LSTM model. The model is then trained and tested using a dataset of 100 stocks. The accuracy of the model is evaluated using various metrics, including the average prediction accuracy, average cumulative return, Sharpe ratio, and maximum drawdown. The results are compared to the performance of other strategies, including the random selection of technical indicators. The simulation results demonstrate that the proposed model outperforms the other strategies in terms of accuracy and performance in a 100-stock investment simulation, highlighting the potential of integrating investor domain knowledge with machine learning algorithms for stock price prediction. Full article
(This article belongs to the Special Issue Applications and Mathematical Foundations of Machine Learning in Investments)
►▼ Show Figures

Figure 1

16 pages, 665 KiB  
Article
Neural Network-Based Modeling for Risk Evaluation and Early Warning for Large-Scale Sports Events
by Chenghao Zhong, Wengao Lou and Chuting Wang
Mathematics 2022, 10(18), 3228; https://0-doi-org.brum.beds.ac.uk/10.3390/math10183228 - 06 Sep 2022
Cited by 6 | Viewed by 1138
Abstract
[Problem] The risks of hosting large-scale sports events are very difficult to evaluate and often directly affected by natural environment risks, events management risks, and social environment risks. Before hosting the events, accurately assessing these risks can effectively minimize the occurrence of risks [...] Read more.
[Problem] The risks of hosting large-scale sports events are very difficult to evaluate and often directly affected by natural environment risks, events management risks, and social environment risks. Before hosting the events, accurately assessing these risks can effectively minimize the occurrence of risks and reduce the subsequent losses. [Aim] In this article, we advocate the use of a back propagation neural network (BPNN) model for risk evaluation and early warning of large-scale sports events. [Methods] We first use expert surveys to assess the risks of 28 large-scale sports events using 12 indicators associated with climate conditions, events management, and natural disasters. We then apply the BPNN model to evaluate the risks of 28 large-scale sports events with sufficient samples by adding white noise with mean zero and small variance to the small actual samples. We provide a general rule to establish a BPNN model with insufficient and small samples. [Results] Our research results show that the recognition accuracy of the established BPNN model is 86.7% for the 15 simulation samples and 100% for the 28 actual samples. Based on this BPNN model, we determined and ranked the risk level of the events and the importance of each indicator. Thus, sample S8 had the highest risk and the second highest was sample S14, and indicator nine was the most important and indicator one the least important. [Conclusions] We can apply the established BPNN model to conveniently evaluate the risk of hosting a large-scale sports event. By analyzing the nonlinear relationship between each indicator and the risk of the sports event, and applying the established BPNN model, we can propose more targeted and effective measures and suggestions for eliminating and decreasing the risks of hosting a large-scale sports event, and ensure large-scale sports events can be successfully hosted. Full article
(This article belongs to the Special Issue Applications and Mathematical Foundations of Machine Learning in Investments)
►▼ Show Figures

Figure 1

20 pages, 2745 KiB  
Article
Using Financial News Sentiment for Stock Price Direction Prediction
by Bledar Fazlija and Pedro Harder
Mathematics 2022, 10(13), 2156; https://0-doi-org.brum.beds.ac.uk/10.3390/math10132156 - 21 Jun 2022
Cited by 14 | Viewed by 6953
Abstract
Using sentiment information in the analysis of financial markets has attracted much attention. Natural language processing methods can be used to extract market sentiment information from texts such as news articles. The objective of this paper is to extract financial market sentiment information [...] Read more.
Using sentiment information in the analysis of financial markets has attracted much attention. Natural language processing methods can be used to extract market sentiment information from texts such as news articles. The objective of this paper is to extract financial market sentiment information from news articles and use the estimated sentiment scores to predict the price direction of the stock market index Standard & Poor’s 500. To achieve the best possible performance in sentiment classification, state-of-the-art bidirectional encoder representations from transformers (BERT) models are used. The pretrained transformer networks are fine-tuned on a labeled financial text dataset and applied to news articles from known providers of financial news content to predict their sentiment scores. The generated sentiment scores for the titles of the given news articles, for the (text) content of said news articles, and for the combined title-content consideration are posited against past time series information of the stock market index. To forecast the price direction of the stock market index, the predicted sentiment scores are used in a simple strategy and as features for a random forest classifier. The results show that sentiment scores based on news content are particularly useful for stock price direction prediction. Full article
(This article belongs to the Special Issue Applications and Mathematical Foundations of Machine Learning in Investments)
►▼ Show Figures

Figure 1

13 pages, 3373 KiB  
Article
A Correlation-Embedded Attention Module to Mitigate Multicollinearity: An Algorithmic Trading Application
by Jireh Yi-Le Chan, Steven Mun Hong Leow, Khean Thye Bea, Wai Khuen Cheng, Seuk Wai Phoong, Zeng-Wei Hong, Jim-Min Lin and Yen-Lin Chen
Mathematics 2022, 10(8), 1231; https://0-doi-org.brum.beds.ac.uk/10.3390/math10081231 - 08 Apr 2022
Cited by 8 | Viewed by 1913
Abstract
Algorithmic trading is a common topic researched in the neural network due to the abundance of data available. It is a phenomenon where an approximately linear relationship exists between two or more independent variables. It is especially prevalent in financial data due to [...] Read more.
Algorithmic trading is a common topic researched in the neural network due to the abundance of data available. It is a phenomenon where an approximately linear relationship exists between two or more independent variables. It is especially prevalent in financial data due to the interrelated nature of the data. The existing feature selection methods are not efficient enough in solving such a problem due to the potential loss of essential and relevant information. These methods are also not able to consider the interaction between features. Therefore, we proposed two improvements to apply to the Long Short-Term Memory neural network (LSTM) in this study. It is the Multicollinearity Reduction Module (MRM) based on correlation-embedded attention to mitigate multicollinearity without removing features. The motivation of the improvements is to allow the model to predict using the relevance and redundancy within the data. The first contribution of the paper is allowing a neural network to mitigate the effects of multicollinearity without removing any variables. The second contribution is improving trading returns when our proposed mechanisms are applied to an LSTM. This study compared the classification performance between LSTM models with and without the correlation-embedded attention module. The experimental result reveals that a neural network that can learn the relevance and redundancy of the financial data to improve the desired classification performance. Furthermore, the trading returns of our proposed module are 46.82% higher without sacrificing training time. Moreover, the MRM is designed to be a standalone module and is interoperable with existing models. Full article
(This article belongs to the Special Issue Applications and Mathematical Foundations of Machine Learning in Investments)
►▼ Show Figures

Figure 1

Review

Jump to: Research

20 pages, 305 KiB  
Review
A Review of Sentiment, Semantic and Event-Extraction-Based Approaches in Stock Forecasting
by Wai Khuen Cheng, Khean Thye Bea, Steven Mun Hong Leow, Jireh Yi-Le Chan, Zeng-Wei Hong and Yen-Lin Chen
Mathematics 2022, 10(14), 2437; https://0-doi-org.brum.beds.ac.uk/10.3390/math10142437 - 13 Jul 2022
Cited by 6 | Viewed by 2875
Abstract
Stock forecasting is a significant and challenging task. The recent development of web technologies has transformed the communication channel to allow the public to share information over the web such as news, social media contents, etc., thus causing exponential growth of web data. [...] Read more.
Stock forecasting is a significant and challenging task. The recent development of web technologies has transformed the communication channel to allow the public to share information over the web such as news, social media contents, etc., thus causing exponential growth of web data. The massively available information might be the key to revealing the financial market’s unexplained variability and facilitating forecasting accuracy. However, this information is usually in unstructured natural language and consists of different inherent meanings. Although a human can easily interpret the inherent messages, it is still complicated to manually process such a massive amount of textual data due to the constraint of time, ability, energy, etc. Due to the different properties of text sources, it is crucial to understand various text processing approaches to optimize forecasting performance. This study attempted to summarize and discuss the current text-based financial forecasting approaches in the aspect of semantic-based, sentiment-based, event-extraction-based, and hybrid approaches. Afterward, the study discussed the strength and weakness of each approach, followed with their comparison and suitable application scenarios. Moreover, this study also highlighted the future research direction in text-based stock forecasting, where the overall discussion is expected to provide insightful analysis for future reference. Full article
(This article belongs to the Special Issue Applications and Mathematical Foundations of Machine Learning in Investments)
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop