Optimization algorithms and investment portfolio analytics with machine learning techniques under time-varying liquidity constraints

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Mazin A.M. Al Janabi
Keyword(s):  
Machine Learning ◽  
Liquidity Constraints ◽  
Market Risk ◽  
Machine Learning Techniques ◽  
Time Varying ◽  
Risk Modeling ◽  
Investment Portfolio ◽  
Content Type ◽  
Learning Techniques ◽  
Portfolio Managers

Purpose This paper aims to examine from commodity portfolio managers’ perspective the performance of liquidity adjusted risk modeling in assessing the market risk parameters of a large commodity portfolio and in obtaining efficient and coherent portfolios under different market circumstances. Design/methodology/approach The implemented market risk modeling algorithm and investment portfolio analytics using reinforcement machine learning techniques can simultaneously handle risk-return characteristics of commodity investments under regular and crisis market settings besides considering the particular effects of the time-varying liquidity constraints of the multiple-asset commodity portfolios. Findings In particular, the paper implements a robust machine learning method to commodity optimal portfolio selection and within a liquidity-adjusted value-at-risk (LVaR) framework. In addition, the paper explains how the adapted LVaR modeling algorithms can be used by a commodity trading unit in a dynamic asset allocation framework for estimating risk exposure, assessing risk reduction alternates and creating efficient and coherent market portfolios. Originality/value The optimization parameters subject to meaningful operational and financial constraints, investment portfolio analytics and empirical results can have important practical uses and applications for commodity portfolio managers particularly in the wake of the 2007–2009 global financial crisis. In addition, the recommended reinforcement machine learning optimization algorithms can aid in solving some real-world dilemmas under stressed and adverse market conditions (e.g. illiquidity, switching in correlations factors signs, nonlinear and non-normal distribution of assets’ returns) and can have key applications in machine learning, expert systems, smart financial functions, internet of things (IoT) and financial technology (FinTech) in big data ecosystems.

Feasibility study of automatically performing the concrete delivery dispatching through machine learning techniques

2015 ◽  
Vol 22 (5) ◽  
pp. 573-590 ◽  
Author(s):  
Mojtaba Maghrebi ◽  
Claude Sammut ◽  
S. Travis Waller
Keyword(s):  
Machine Learning ◽  
Human Resources ◽  
Design Methodology ◽  
Machine Learning Techniques ◽  
Mixing Process ◽  
Content Type ◽  
Practical Solution ◽  
Learning Techniques ◽  
Ready Mixed Concrete ◽  
Practical Implications

Purpose – The purpose of this paper is to study the implementation of machine learning (ML) techniques in order to automatically measure the feasibility of performing ready mixed concrete (RMC) dispatching jobs. Design/methodology/approach – Six ML techniques were selected and tested on data that was extracted from a developed simulation model and answered by a human expert. Findings – The results show that the performance of most of selected algorithms were the same and achieved an accuracy of around 80 per cent in terms of accuracy for the examined cases. Practical implications – This approach can be applied in practice to match experts’ decisions. Originality/value – In this paper the feasibility of handling complex concrete delivery problems by ML techniques is studied. Currently, most of the concrete mixing process is done by machines. However, RMC dispatching still relies on human resources to complete many tasks. In this paper the authors are addressing to reconstruct experts’ decisions as only practical solution.

scholarly journals Malicious web domain identification using online credibility and performance data by considering the class imbalance issue

2019 ◽  
Vol 119 (3) ◽  
pp. 676-696 ◽  
Author(s):  
Zhongyi Hu ◽  
Raymond Chiong ◽  
Ilung Pranata ◽  
Yukun Bao ◽  
Yuqing Lin
Keyword(s):  
Machine Learning ◽  
Class Imbalance ◽  
Performance Data ◽  
Machine Learning Techniques ◽  
Data Sets ◽  
Real World Data ◽  
Content Type ◽  
Domain Identification ◽  
Learning Techniques ◽  
And Performance

Purpose Malicious web domain identification is of significant importance to the security protection of internet users. With online credibility and performance data, the purpose of this paper to investigate the use of machine learning techniques for malicious web domain identification by considering the class imbalance issue (i.e. there are more benign web domains than malicious ones). Design/methodology/approach The authors propose an integrated resampling approach to handle class imbalance by combining the synthetic minority oversampling technique (SMOTE) and particle swarm optimisation (PSO), a population-based meta-heuristic algorithm. The authors use the SMOTE for oversampling and PSO for undersampling. Findings By applying eight well-known machine learning classifiers, the proposed integrated resampling approach is comprehensively examined using several imbalanced web domain data sets with different imbalance ratios. Compared to five other well-known resampling approaches, experimental results confirm that the proposed approach is highly effective. Practical implications This study not only inspires the practical use of online credibility and performance data for identifying malicious web domains but also provides an effective resampling approach for handling the class imbalance issue in the area of malicious web domain identification. Originality/value Online credibility and performance data are applied to build malicious web domain identification models using machine learning techniques. An integrated resampling approach is proposed to address the class imbalance issue. The performance of the proposed approach is confirmed based on real-world data sets with different imbalance ratios.

scholarly journals Crypto Exchanges and Credit Risk: Modeling and Forecasting the Probability of Closure

2021 ◽  
Vol 14 (11) ◽  
pp. 516
Author(s):  
Dean Fantazzini ◽  
Raffaella Calabrese
Keyword(s):  
Machine Learning ◽  
Credit Risk ◽  
Credit Scoring ◽  
Machine Learning Techniques ◽  
Risk Modeling ◽  
Learning Techniques ◽  
Modeling And Forecasting ◽  
Out Of Sample ◽  
Significant Covariates ◽  
Unique Dataset

While there is increasing interest in crypto assets, the credit risk of these exchanges is still relatively unexplored. To fill this gap, we considered a unique dataset of 144 exchanges, active from the first quarter of 2018 to the first quarter of 2021. We analyzed the determinants surrounding the decision to close an exchange using credit scoring and machine learning techniques. Cybersecurity grades, having a public developer team, the age of the exchange, and the number of available traded cryptocurrencies are the main significant covariates across different model specifications. Both in-sample and out-of-sample analyzes confirm these findings. These results are robust in regard to the inclusion of additional variables, considering the country of registration of these exchanges and whether they are centralized or decentralized.

Toward understanding the topical structure of hospitality literature

2018 ◽  
Vol 30 (11) ◽  
pp. 3386-3411 ◽  
Author(s):  
Eunhye (Olivia) Park ◽  
Bongsug Chae ◽  
Junehee Kwon
Keyword(s):  
Machine Learning ◽  
Topic Modeling ◽  
Research Field ◽  
Intellectual Structure ◽  
Machine Learning Techniques ◽  
Research Topics ◽  
Evolutionary Patterns ◽  
Content Type ◽  
Learning Techniques ◽  
Academic Publications

Purpose This paper aims to identify the intellectual structure of four leading hospitality journals over 40 years by applying mixed-method approach, using both machine learning and traditional statistical analyses. Design/methodology/approach Abstracts from all 4,139 articles published in four top hospitality journals were analyzed using the structured topic modeling and inferential statistics. Topic correlation and community detection were applied to identify strengths of correlations and sub-groups of topics. Trend visualization and regression analysis were used to quantify the effects of the metadata (i.e. year of publication and journal) on topic proportions. Findings The authors found 50 topics and eight subgroups in the hospitality journals. Different evolutionary patterns in topic popularity were demonstrated, thereby providing the insights for popular research topics over time. The significant differences in topical proportions were found across the four leading hospitality journals, suggesting different foci in research topics in each journal. Research limitations/implications Combining machine learning techniques with traditional statistics demonstrated potential for discovering valuable insights from big text data in hospitality and tourism research contexts. The findings of this study may serve as a guide to understand the trends in the research field as well as the progress of specific areas or subfields. Originality/value It is the first attempt to apply topic modeling to academic publications and explore the effects of article metadata with the hospitality literature.

An intrusion detection system for health-care system using machine and deep learning

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Sagar Pande ◽  
Aditya Khamparia ◽  
Deepak Gupta
Keyword(s):  
Machine Learning ◽  
Health Care ◽  
Deep Learning ◽  
Network Security ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Machine Learning Techniques ◽  
Content Type ◽  
Learning Techniques

Purpose One of the important key components of health care–based system is a reliable intrusion detection system. Traditional techniques are not adequate to handle complex data. Also, the diversified intrusion techniques cannot meet current network requirements. Not only the data is getting increased but also the attacks are increasing very rapidly. Deep learning and machine learning techniques are very trending in the area of research in the area of network security. A lot of work has been done in this area by still evolutionary algorithms along with machine learning is very rarely explored. The purpose of this study is to provide novel deep learning framework for the detection of attacks. Design/methodology/approach In this paper, novel deep learning is the framework is proposed for the detection of attacks. Also, a comparison of machine learning and deep learning algorithms is provided. Findings The obtained results are more than 99% for both the data sets. Research limitations/implications The diversified intrusion techniques cannot meet current network requirements. Practical implications The data is getting increased but also the attacks are increasing very rapidly. Social implications Deep learning and machine learning techniques are very trending in the area of research in the area of network security. Originality/value Novel deep learning is the framework is proposed for the detection of attacks.

A segmented machine learning modeling approach of social media for predicting occupancy

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Apostolos Ampountolas ◽  
Mark P. Legg
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Life Cycles ◽  
Machine Learning Techniques ◽  
Learning Approach ◽  
Negative Effects ◽  
Data Set ◽  
Content Type ◽  
Learning Techniques ◽  
The Usa

Purpose This study aims to predict hotel demand through text analysis by investigating keyword series to increase demand predictions’ precision. To do so, this paper presents a framework for modeling hotel demand that incorporates machine learning techniques. Design/methodology/approach The empirical forecasting is conducted by introducing a segmented machine learning approach of leveraging hierarchical clustering tied to machine learning and deep learning techniques. These features allow the model to yield more precise estimates. This study evaluates an extensive range of social media–derived words with the most significant probability of gradually establishing an understanding of an optimal outcome. Analyzes were performed on a major hotel chain in an urban market setting within the USA. Findings The findings indicate that while traditional methods, being the naïve approach and ARIMA models, struggled with forecasting accuracy, segmented boosting methods (XGBoost) leveraging social media predict hotel occupancy with greater precision for all examined time horizons. Additionally, the segmented learning approach improved the forecasts’ stability and robustness while mitigating common overfitting issues within a highly dimensional data set. Research limitations/implications Incorporating social media into a segmented learning framework can augment the current generation of forecasting methods’ accuracy. Moreover, the segmented learning approach mitigates the negative effects of market shifts (e.g. COVID-19) that can reduce in-production forecasts’ life-cycles. The ability to be more robust to market deviations will allow hospitality firms to minimize development time. Originality/value The results are expected to generate insights by providing revenue managers with an instrument for predicting demand.

Image recognition of COVID-19 using DarkCovidNet architecture based on convolutional neural network

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Pankaj Kumar ◽  
Bhavna Bajpai ◽  
Deepak Omprakash Gupta ◽  
Dinesh C. Jain ◽  
S. Vimal
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Computed Tomography ◽  
Convolutional Neural Network ◽  
Design Methodology ◽  
Machine Learning Techniques ◽  
Computed Tomography Scan ◽  
Content Type ◽  
Learning Techniques ◽  
Tomography Scan

Purpose The purpose of this study/paper To focus on finding COVID-19 with the help of DarkCovidNet architecture on patient images. Design/methodology/approach We used machine learning techniques with convolutional neural network. Findings Detecting COVID-19 symptoms from patient CT scan images. Originality/value This paper contains a new architecture for detecting COVID-19 symptoms from patient computed tomography scan images.

Formjacking attack: Are we safe?

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Vijaya Geeta Dharmavaram
Keyword(s):  
Machine Learning ◽  
Credit Card ◽  
Defense Mechanism ◽  
Machine Learning Techniques ◽  
Sensitive Information ◽  
Sensitive Data ◽  
Modus Operandi ◽  
Content Type ◽  
Learning Techniques ◽  
Cyber Criminals

Purpose Today, online shopping and online business has become a new norm especially in the current pandemic scenario. With more businesses running online, cyber criminals are coming up with different tactics to steal identity and sensitive information such as credit card and banking credentials either for personal monetary gain or to sell in the dark Web. One form of such attack that is seen in the recent times is formjacking attack. This paper aims to review the current scenario of formjacking attack and its modus operandi. The paper also provides certain counter measures that can be adopted by the users and website owners. Design/methodology/approach The paper mainly focuses on the modus operandi of formjacking attack to understand the severity of the problem. Based on the way the attack is carried out, some guidelines to be followed are provided. Later, a brief review of machine learning techniques is furnished to understand how it may help as secure defense mechanism. Findings Formjacking attacks are on a rise in the past two years, especially during the holiday season. Cyber criminals have been using smart tactics to carry out these attacks which are very difficult to detect. Machine learning techniques may prove to be effective in combating these attacks. Originality/value Formjacking attack is not just a concern of the customers who may lose their sensitive data, but the onus also lies on the companies itself to ensure they protect their customer’s data from theft. Not much research is found regarding formjacking attack, as it is relatively a new form of attack. The paper reviews this attack and provides some measure that can be followed. It also provides few guidelines which can be used for further research in devising a security tool to mitigate this problem.

Designing predictive maintenance systems using decision tree-based machine learning techniques

2020 ◽  
Vol 37 (4) ◽  
pp. 659-686 ◽  
Author(s):  
Shashidhar Kaparthi ◽  
Daniel Bumblauskas
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Decision Tree ◽  
Service Management ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Content Type ◽  
Learning Techniques ◽  
Maintenance Systems

PurposeThe after-sale service industry is estimated to contribute over 8 percent to the US GDP. For use in this considerably large service management industry, this article provides verification in the application of decision tree-based machine learning algorithms for optimal maintenance decision-making. The motivation for this research arose from discussions held with a large agricultural equipment manufacturing company interested in increasing the uptime of their expensive machinery and in helping their dealer network.Design/methodology/approachWe propose a general strategy for the design of predictive maintenance systems using machine learning techniques. Then, we present a case study where multiple machine learning algorithms are applied to a particular example situation for an illustration of the proposed strategy and evaluation of its performance.FindingsWe found progressive improvements using such machine learning techniques in terms of accuracy in predictions of failure, demonstrating that the proposed strategy is successful.Research limitations/implicationsThis approach is scalable to a wide variety of applications to aid in failure prediction. These approaches are generalizable to many systems irrespective of the underlying physics. Even though we focus on decision tree-based machine learning techniques in this study, the general design strategy proposed can be used with all other supervised learning techniques like neural networks, boosting algorithms, support vector machines, and statistical methods.Practical implicationsThis approach is applicable to many different types of systems that require maintenance and repair decision-making. A case is provided for a cloud data storage provider. The methods described in the case can be used in any number of systems and industrial applications, making this a very scalable case for industry practitioners. This scalability is possible as the machine learning techniques learn the correspondence between machine conditions and outcome state irrespective of the underlying physics governing the systems.Social implicationsSustainable systems and operations require allocating and utilizing resources efficiently and effectively. This approach can help asset managers decide how to sustainably allocate resources by increasing uptime and utilization for expensive equipment.Originality/valueThis is a novel application and case study for decision tree-based machine learning that will aid researchers in developing tools and techniques in this area as well as those working in the artificial intelligence and service management space.

Sign in / Sign up

Export Citation Format

Share Document