Computing value-at-risk using genetic algorithm

Sharma, Bhanu; Thulasiram, Ruppa K.; Thulasiraman, Parimala

doi:10.1108/jrf-09-2014-0132

Cited by 6 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Big data and the common analytical methods associated with it are exploited to develop measures of potential loss in a portfolio based on genetic algorithms (Sharma et al. ). Further, Sivaramakrishnan and Stubbs () develop a custom risk model based on historical data.…”

Section: Research Directionsmentioning

confidence: 99%

“…Algorithms purporting to predict stock market moves such as ‘I know first’ (2014) use a combination of machine learning via genetic algorithms (survival of the fittest) (Sharma et al. ) and artificial intelligence techniques (specifically neural nets which are widely used in classification) (Parnes ). Roitman () explains that new data are added to the ‘I know first’ database daily to the 15‐year database to run a learning and prediction cycle to identify prices for stock currencies and commodities.…”

Section: Research Directionsmentioning

confidence: 99%

See 1 more Smart Citation

Big Data Opportunities for Accounting and Finance Practice and Research

Cockcroft

Russell

2018

Australian Accounting Review

119

View full text Add to dashboard Cite

We examine the research opportunities for the use of 'big data' in accounting and finance. The purpose of the study is to present a snapshot of big data academic research in information systems, accounting and finance, and to highlight areas for further research in accounting and finance. The research question addressed in this work is: What are the major themes in existing research in big data and where are the resulting gaps in the accounting and finance literature? An analysis is presented of 47 accounting, finance and information systems journals from 2007-2016. We identify and sample the relevant literature to derive a taxonomy of themes. These themes are presented as a conceptual matrix in which the themes from the taxonomy are used as concepts, and the matrix identifies where they appear, and where there are potential areas for further research. Prior research in big data in accounting, finance and information systems falls into six themes. The six under-researched areas of big data in accounting and finance are risk and security, data visualisation and predictive analytics, data management and data quality. Increased research in these areas will lead to improvements in industry practices, and opportunities for cross-disciplinary research.

show abstract

Section: Research Directionsmentioning

confidence: 99%

Section: Research Directionsmentioning

confidence: 99%

Big Data Opportunities for Accounting and Finance Practice and Research

Cockcroft

Russell

2018

Australian Accounting Review

119

View full text Add to dashboard Cite

show abstract

“…Study regarding genetic algorithm applied in Madrid Stock Market suggest that, for reasonable trading costs, the technical trading rule is always superior to a risk-adjusted buy-and-hold strategy [22]. The other study proved that Genetic Algorithm is more conservative as compared to those computed using Monte Carlo simulation [25].…”

Section: Literature Reviewmentioning

confidence: 92%

Robust Hybrid Optimization Method to Reduce Investment Portfolio Risk Using Fusion of Modern Portfolio Theory and Genetic Algorithm

Bakar¹,

Rosbi²

2019

IJEAT

View full text Add to dashboard Cite

Main objective of this study is to develop hybrid optimization method for reducing investment portfolio risk. The methods selected in this study are the combination of Modern Portfolio Theory (MPT) and genetic algorithm optimization approach. Three stocks from Malaysian Stock Exchange are selected in developing the investment portfolio namely Malayan Banking Berhad, Hap Seng Consolidated Berhad and Top Glove Corporation Berhad. Result indicates the modern portfolio theory can give optimal portfolio weightage with maximum return for tolerate level of investment risk. In addition, genetic algorithm enhanced the optimal searching method to find global minimum of investment risk. Result shows the minimum portfolio risk in objective function is 2.122118 with implementation genetic algorithm optimization. The optimal combination of portfolio investment is 32.24 % in asset A (Malayan Banking Berhad), 52.37 % in asset B (Hap Seng Consolidated Berhad), and 15.30 % in asset C (Top Gove Corporation Berhad). The important of this study is it will assist investor in making better decision to optimize their return for given level of investment risk. Furthermore, this hybrid method provides a better accuracy of prediction for return of investment and portfolio risk.

show abstract

“…On the other hand, quantitative tools try to detect risks by analyzing past or present data, including correlation analysis, trend analysis or complex mathematical models, e.g. Monte Carlo analysis and early-warning systems (for more information on all of these tools see, Chapman, 2011;Moeller, 2011;Martinelli and Milosevic, 2016;Pritchard, 2015;McNeil et al, 2015;Sharma et al, 2015;Chen et al, 2016). The result of this process should be a risk-management hierarchy,…”

Section: Financial Risk Managementmentioning

confidence: 99%

Knowledge is power – conceptualizing collaborative financial risk assessment

Brunner-Kirchmair

Wiener

2019

JRF

View full text Add to dashboard Cite

Purpose Inspired by new findings on and perceptions of risk governance, such as the necessity of taking a broader perspective in coping with risks in companies and working together in interactive groups with various stakeholders to deal with complex risks in the modern world, the purpose of this paper is looking for new ways to deal with financial risks. Current methods dealing with those risks are confronted with the problems of being primarily based on past data and experience, neglecting the need for objectivity, focusing on the short-term future and disregarding the interconnectedness of different financial risk categories. Design/methodology/approach A literature review of risk governance, financial risk management and open foresight was executed to conceptualize solutions to the mentioned-above problems. Findings Collaborative financial risk assessment (CFRA) is a promising approach in financial risk governance with respect to overcoming said problems. It is a method of risk identification and assessment, which combines aspects of “open foresight” and the financial risk management and governance literature. CFRA is characterized as bringing together members of different companies in trying to detect weak signals and trends to gain knowledge about the future, which helps companies to reduce financial risks and increase the chance of gaining economic value. By overcoming organizational boundaries, individual companies may gain the knowledge they would probably not have without CFRA and achieve a competitive advantage. Research limitations/implications A conceptual paper like the one at hand wants empirical proof. Therefore, the authors developed a research agenda in the form of five propositions for further research. Originality/value This paper discusses the existing problems of financial risk identification and assessment methods. It contributes to the existing literature by proposing CFRA as a solution to those problems and adding a new perspective to financial risk governance.

show abstract

Computing value-at-risk using genetic algorithm

Cited by 6 publications

References 14 publications

Big Data Opportunities for Accounting and Finance Practice and Research

Big Data Opportunities for Accounting and Finance Practice and Research

Robust Hybrid Optimization Method to Reduce Investment Portfolio Risk Using Fusion of Modern Portfolio Theory and Genetic Algorithm

Knowledge is power – conceptualizing collaborative financial risk assessment

Contact Info

Product

Resources

About