Search results

Artificial neural networks (ANNs), which represent computational models simulating the biological neural systems, have become a dominant paradigm for solving complex analytical problems. ANN applications have been employed in various disciplines such as psychology, computer science, mathematics, engineering, medicine, manufacturing, and business studies. Academic research on ANNs is witnessing considerable publication activity, and there exists a need to track the intellectual structure of the existing research for a better comprehension of the domain. The current study uses a bibliometric approach to ANN business literature extracted from the Web of Science database. The study also performs a chronological review using science mapping and examines the evolution trajectory to determine research areas relevant to future research. The authors suggest that researchers focus on ANN deep learning models as the bibliometric results predict an expeditious growth of the research topic in the upcoming years. The findings reveal that business research on ANNs is flourishing and suggest further work on domains, such as back-propagation neural networks, support vector machines, and predictive modeling. By providing a systematic and dynamic understanding of ANN business research, the current study enhances the readers' understanding of existing reviews and complements the domain knowledge.

This paper presents the results of a study comparing the ability of neural network models and multiple discriminant analysis (MDA) models to predict bond rating changes and to exam if segmentation by investment grade improves classification. Data was collected on more than 900 bonds that had their Standard and Poor's Corporation rating changed during the period 1997 to 2002. This was matched this dataset with corresponding firms which had the same initial bond rating but which did not change. The correspondence was based on the firms being in the same industry, having the same rating at the time of the change (the time frame was one month) and the same approximate asset size (within 20%). This relatively stringent set of criteria reduced the data set to 282 pairs of companies. A neural network model and a multiple discriminant analysis were used to predict both a bond change and the general direction of a movement from a particular bond rating to another bond rating. The predictive variables were financial ratios and rates of change for these ratios. In almost all cases, particularly for the larger sample studies, the neural network models were better predictors than the multiple discriminant models. The paper reviews, in detail, performance of the respective models, strengths and limitations of the models – particularly with respect to underlying assumptions- and future research directions.

Budget hotels are becoming an emerging industry for convenience and affordability, where consumer sentiments are of paramount importance. Tourism has become increasingly dependent on social media and online platforms to gather travel-related information, purchase travel products, food, lodging, etc., and share views and experiences. The user-generated data helps companies make informed decisions through predictive and behavioural analytics.

Design/Methodology/Approach: This study uses text mining, deep learning, and machine learning techniques for data collection and sentiment analysis based on 117,151 online reviews of the customers posted on the TripAdvisor website from May 2004 to May 2019 from 197 hotels of five prominent budget hotel groups spread across India using Feedforward Neural Network along with Keras package and Softmax activation function.

Findings: The word-of-mouth turns into electronic word-of-mouth through social networking sites, with easy access to information that enables customers to pick a budget hotel. We identified 20 widely used words that most customers use in their reviews, which can help managers optimise operational efficiency by boosting consumer acceptability, satisfaction, positive experiences, and overcoming negative consumer perceptions.

Practical Implications: The analysis of the review patterns is based on real-time data, which is helpful to understand the customer’s requirements, particularly for budget hotels.

Originality/Value: We analysed TripAdvisor reviews posted over the last 16 years, excluding the Corona period due to industry crises. The findings reverberate in consonance with the performance improvement theory, which states feed-forward a neural network enhances organisational, process, and individual-level performance in the hospitality industry based on customer reviews.

Natural flood disasters frequently happen in Malaysia especially during monsoon season and Kuala Kangsar, Perak, is one of the cities with the frequent record of natural flood disasters. Previous flood disaster faced by this city showed the failure in notifying the citizen with sufficient time for preparation and evacuation. The authority in charge of the flood disaster in Kuala Kangsar depends on the real-time monitoring from the hydrological sensor located at several stations along the main river. The real-time information from hydrological sensor failed to provide early notification and warning to the public. Although many hydrological sensors are available at the stations, only water level sensors and rainfall sensors are used by authority for flood monitoring. This study developed a flood prediction model using artificial intelligence to predict the incoming flood in Kuala Kangsar area based on artificial neural network (ANN). The flood prediction model is expected to predict the incoming flood disaster by using information from the variety of hydrological sensors. The study finds that the proposed ANN model based on nonlinear autoregressive network with exogenous inputs (NARX) has better performance than other models with the correlation coefficient that is equal to 0.98930. The NARX model of flood prediction developed in this study can be referred to as the future flood prediction model in Kuala Kangsar, Perak.

Value at risk (VaR) and expected shortfall (ES) are popular market risk measurements. The former is not coherent but robust, whereas the latter is coherent but less interpretable, only conditionally backtestable and less robust. In this chapter, we compare an innovative artificial neural network (ANN) model with a time series model in the context of forecasting VaR and ES of the univariate time series of four asset classes: US large capitalization equity index, European large cap equity index, US bond index, and US dollar versus euro exchange rate price index for the period of January 4, 1999, to December 31, 2018. In general, the ANN model has more favorable backtesting results as compared to the autoregressive moving average, generalized autoregressive conditional heteroscedasticity (ARMA-GARCH) time series model. In terms of forecasting accuracy, the ANN model has much fewer in-sample and out-of-sample exceptions than those of the ARMA-GARCH model.

African Economies are a mix of emerging and developing economies, characterised by regional imbalances and socio-economic differences. Foreign Direct Investment and Trade has been important for the growth prospects of African Economies. In this paper, we attempt to study the impact of FDI and Trade in a COVID-19 scenario on the African Economies. We also study the lockdown restrictions in different regions of Africa. Applying Neural Network Analysis for the sample of 36 African Economies we identify the significant economic variables for GDP. The analysis based on a feedforward structure suggests that Merchandize Exports (MEXP) and Foreign Direct Investment Stock (FDIS) have very strong causal linkages with the GDP for African Economies sample. On the other hand, Merchandise Imports (MIMP), Services Exports (SEMP), Services Imports (SIMP), and Foreign Direct Investment Inflows (FDII) have a strong and significant relationship with GDP for the African Economies. Tariff Measures (TRFF), Anti-Dumping measures (ADP) and Foreign Direct Investment Outflows (FDIO) have no significant relationship.

The consideration of alternative sources of material for construction is imperative to reduce the environmental impacts as two-fifths of the carbon footprint of materials is attributed to the construction industry. One alternative material with improved biodegradable attributes which can contribute to carbon offset is bamboo. The commercialisation of bamboo in modern infrastructures has significant potential to address few of the Sustainable Development Goals (SDGs) itemised by the United Nations, namely SDG 9 about industry, innovation and infrastructure. Other SDGs covering sustainable cities and communities, responsible consumption and production and climate action are also indirectly addressed when utilising sustainable construction materials. Being a natural material however, the full commercialisation of materials such as bamboo is constrained by a lack of durability. Besides fracture mechanisms arising from load-induced cracks and thermal modification, the durability of bamboo material is greatly impaired by biotic and abiotic factors, which equally affect its natural rate of degradation, hence fracture behaviour. In first instance, this chapter outlines the various factors leading to the durability limitations in bamboo material due to load-induced cracks and natural degradation based on recent findings in this field from the author's own work and from past literature. Secondly, part of this chapter is devoted to a new approach of processing the surge of information about the varied aspects of bamboo durability by considering the powerful technique of artificial intelligence (AI), specifically the artificial neural network (ANN) for prediction modelling. Further use of AI-enabled technologies could have an impactful outcome on the life cycle assessment of bamboo-based structures to address the growing challenges outlined by the United Nations.

The expansion of marketing data is encouraging the growing use of deep learning (DL) in marketing. I summarize the intuition behind deep learning and explain the mechanisms of six popular algorithms: three discriminative (convolutional neural network (CNN), recurrent neural network (RNN), and Transformer), two generative (variational autoencoder (VAE) and generative adversarial networks (GAN)), and one RL (DQN). I discuss what marketing problems DL is useful for and what fueled its growth in recent years. I emphasize the power and flexibility of DL for modeling unstructured data when formal theories and knowledge are absent. I also describe future research directions.

This chapter offers an overview of the applications of artificial intelligence (AI) in the textile industry and in particular, the textile colouration and finishing industry. The advent of new technologies such as AI and the Internet of Things (IoT) has changed many businesses and one area AI is seeing growth in is the textile industry. It is estimated that the AI software market shall reach a new high of over US$60 billion by 2022, and the largest increase is projected to be in the area of machine learning (ML). This is the area of AI where machines process and analyse vast amount of data they collect to perform tasks and processes. In the textile manufacturing industry, AI is applied to various areas such as colour matching, colour recipe formulation, pattern recognition, garment manufacture, process optimisation, quality control and supply chain management for enhanced productivity, product quality and competitiveness, reduced environmental impact and overall improved customer experience. The importance and success of AI is set to grow as ML algorithms become more sophisticated and smarter, and computing power increases.