Guest Editors:
|
Dr. Edson Gwangwava Department of Accounting and Finance, Chinhoyi University of Technology, Chinhoyi, Zimbabwe. |
|
|
Dr. Mbizi Rangarirai Department of Finance, Zimbabwe Open University, Harare, Zimbabwe. |
|
|
Dr. Haetham.H.Kasim Alkhaffaf College of Administration and Economics, University of Mosul, Mosul, Iraq |
The IJMS (Interdisciplinary Journal of Management Studies) is a peer-reviewed open access journal published by the University of Tehran, Iran since the year 2007. The journal publishes scientific papers reporting original research and/or applications in the field of Management Sciences.
Perspective
Predictive analytics models that employ efficient risk management techniques assist traders in protecting their portfolios from significant losses. The machine learning algorithms are able to learn from past errors and adapt to the shifting market conditions. As a result, over time, their forecasting accuracy gets better. Internal, external, and alternative data are used in predictive analytics risk management to discover, evaluate, and reduce risks. Additionally, predictive models employ past data to spot patterns and trends before extrapolating those findings to forecast future results. Through historical analysis, predictive analytics enables us to comprehend potential future events. Machine learning algorithms find applications in finance such as fraud detection, trading activity automation, and investor financial advising services. Without explicit programming, machine learning is capable of quickly analysing millions of data sets to enhance results. Because machine learning models can capture the nonlinear relationships of scenario variables and risk factors, they provide higher forecasting accuracy. For risk models used for internal decision-making, feature/variable extraction procedures require a substantial amount of time. Statistical algorithms, artificial intelligence, and machine learning techniques are used in predictive analytics to examine data and forecast future financial hazards in financial risk management. Using predictive analytics, possible hazards can be found. The identification, measurement, and management of risks that comprise the financial stability of a company can be accomplished with the help of financial risk analytics. Regardless of where risks originate, businesses can utilise analytical tools and techniques like SWOT analysis to prevent them. The technique of applying machine learning (ML) algorithms to support the analytics process of analysing data and finding insights in order to make decisions that enhance business outcomes is known as machine learning for analytics. Because machine learning prediction is typically more accurate than traditional approaches, it is chosen. Machine learning is able to recognize patterns and relationships that humans are unable to because it is based on algorithms. In predictive financial analytics, artificial intelligence (AI) and machine learning aim to improve prediction accuracy, optimise portfolio management, mitigate risks, discover market trends, and increase operational efficiency.
In order to classify or model themes, management researchers have employed AI approaches to evaluate text data. They have also used machine learning techniques to examine numerical data, most frequently using neural networks and decision trees. From increased forecasting accuracy and risk assessment to better fraud detection and operational efficiency, the integration of AI into financial data analysis and risk management delivers measurable financial benefits. It comprises determining, assessing, and keeping an eye on dangers to the organisation's compliance efforts both now and in the future. Next, internal controls must be put in place and continuously monitored to ensure compliance efficacy. AI improves company risk management by quickly identifying and predicting possible threats from complicated data. By enabling businesses to proactively counter threats, it enhances decision-making and resource allocation. The process of financial risk management entails determining the possible drawbacks of every investment choice and selecting whether to accept the risks or take precautions against them. Since risks can alter over time, financial risk management is an ongoing activity. A variety of fields and viewpoints are encouraged to contribute, including but not limited to: Machine Learning to Improve Predictive Analytics in Financial Risk Management. We welcome researchers and practitioners to present their novel contributions in this regard. Topics of interest include, which are not limited to:
Manuscript Preparation and Submission
All Manuscripts submitting in the SI should conform to the standard editorial and publication policies as mentioned in the journal. The authors should submit the manuscript via online system at https://ijms.ut.ac.ir/. Please select the article type “SI: MLFRM-2025” when submitting the manuscript.
Important Dates