Search results

This research aims to determine the ideal fare for various aircraft itineraries by modeling prices using a neural network method. Dynamic pricing has been studied from the airline’s point of view, with a focus on demand forecasting and price differentiation. Early demand forecasting on a specific route can assist an airline in strategically planning flights and determining optimal pricing strategies.

A feedforward neural network was employed in the current study. Two hidden layers, consisting of 18 and 12 neurons, were incorporated to enhance the network’s capabilities. The activation function employed for these layers was tanh. Additionally, it was considered that the output layer’s functions were linear. The neural network inputs considered in this study were flight path, month of flight, flight date (week/day), flight time, aircraft type (Boeing, Airbus, other), and flight class (economy, business). The neural network output, on the other hand, was the ticket price. The dataset comprises 16,585 records, specifically flight data for Iranian airlines for 2022.

The findings indicate that the model achieved a high level of accuracy in approximating the actual data. Additionally, it demonstrated the ability to predict the optimal ticket price for various flight routes with minimal error.

Based on the significant alignment observed between the actual data and the tested data utilizing the algorithmic model, airlines can proactively anticipate ticket prices across all routes, optimizing the revenue generated by each flight. The neural network algorithm utilized in this study offers a valuable opportunity for companies to enhance their decision-making processes. By leveraging the algorithm’s features, companies can analyze past data effectively and predict future prices. This enables them to make informed and timely decisions based on reliable information.

The present study represents a pioneering research endeavor that investigates using a neural network algorithm to predict the most suitable pricing for various flight routes. This study aims to provide valuable insights into dynamic pricing for marketing researchers and practitioners.

The purpose of this study is to analyze the dynamic changes of the arms trade network not only from the network structure but also the influence mechanism from the aspects of the economy, politics, security, strategy and transaction costs.

The study employs the Temporal Exponential Random Graph Model and the Separable Temporal Exponential Random Graph Model to analyze the endogenous network structure effect, the attribute effect and the exogenous network effect of 47 major arms trading countries from 2015 to 2020.

The results show that the international arms trade market is unevenly distributed, and there are great differences in military technology. There is a fixed hierarchical structure in the arms trade, but the rise of emerging countries is expected to break this situation. In international arms trade relations, economic forces dominate, followed by political, security and strategic factors.

Economic and political factors play an important role in the arms trade. Therefore, countries should strive to improve their economic strength and military technology. Also, countries should increase political mutual trust and gain a foothold in the industrial chain of arms production to enhance their military power.

The contribution of this paper is to analyze the special trade area of arms trade from a dynamic network perspective by incorporating economic, political, security, strategic and transaction cost factors together into the TERGM and STERGM models.

This study aims to explore how sustainable business models (SBM) can be developed within agri-innovation systems (AIS) and emphasize an integration of the two with a systemic understanding for reducing food loss and value loss in postharvest agri-food supply chain.

This study conducted longitudinal qualitative research in a developing country with food loss challenges in the postharvest supply chain. This study collected data through multiple rounds of fieldwork, interviews and focus groups over four years. Thematic analysis and “sensemaking” were used for inductive data analysis to generate rich contextual knowledge by drawing upon the lived realities of the agri-food supply chain actors.

First, this study finds that the value losses are varied in the supply chain, encompassing production value, intrinsic value, extrinsic value, market value, institutional value and future food value. This happens through two cumulative effects including multiplier losses, where losses in one model cascade into others, amplifying their impact and stacking losses, where the absence of data stacks or infrastructure pools hampers the realisation of food value. Thereafter, this study proposes four strategies for moving from the loss-incurring current business model to a networked SBM for mitigating losses. This emphasises the need to redefine ownership as stewardship, enable formal and informal beneficiary identification, strengthen value addition and build capacities for empowering communities to benefit from networked SBM with AIS initiatives. Finally, this study puts forth ten propositions for future research in aligning AIS with networked SBM.

This study contributes to understanding the interplay between AIS and SBM; emphasising the integration of the two to effectively address food loss challenges in the early stages of agri-food supply chains. The identified strategies and research propositions provide implications for researchers and practitioners seeking to accelerate sustainable practices for reducing food loss and waste in agri-food supply chains.

Because the dynamic characteristics of the stock market are nonlinear, it is unclear whether stock prices can be predicted. This paper aims to explore the predictability of the stock price index from a long-memory perspective. The authors propose hybrid models to predict the next-day closing price index and explore the policy effects behind stock prices. The paper aims to discuss the aforementioned ideas.

The authors found a long memory in the stock price index series using modified R/S and GPH tests, and propose an improved bi-directional gated recurrent units (BiGRU) hybrid network framework to predict the next-day stock price index. The proposed framework integrates (1) A de-noising module—Singular Spectrum Analysis (SSA) algorithm, (2) a predictive module—BiGRU model, and (3) an optimization module—Grid Search Cross-validation (GSCV) algorithm.

Three critical findings are long memory, fit effectiveness and model optimization. There is long memory (predictability) in the stock price index series. The proposed framework yields predictions of optimum fit. Data de-noising and parameter optimization can improve the model fit.

The empirical data are obtained from the financial data of listed companies in the Wind Financial Terminal. The model can accurately predict stock price index series, guide investors to make reasonable investment decisions, and provide a basis for establishing individual industry stock investment strategies.

If the index series in the stock market exhibits long-memory characteristics, the policy implication is that fractal markets, even in the nonlinear case, allow for a corresponding distribution pattern in the value of portfolio assets. The risk of stock price volatility in various sectors has expanded due to the effects of the COVID-19 pandemic and the R-U conflict on the stock market. Predicting future trends by forecasting stock prices is critical for minimizing financial risk. The ability to mitigate the epidemic’s impact and stop losses promptly is relevant to market regulators, companies and other relevant stakeholders.

Although long memory exists, the stock price index series can be predicted. However, price fluctuations are unstable and chaotic, and traditional mathematical and statistical methods cannot provide precise predictions. The network framework proposed in this paper has robust horizontal connections between units, strong memory capability and stronger generalization ability than traditional network structures. The authors demonstrate significant performance improvements of SSA-BiGRU-GSCV over comparison models on Chinese stocks.

Historical bazaars, a huge treasure of Iranian culture, art and economy, are places for social capital development. Un-supervised management in past decades has led to the demolition and change of historical bazaars and negligence of its different aspects. The present research aims to investigate the resilience of historical bazaars preserving their identity and different developments.

The artificial neural network (ANN) has been applied to investigate the resilience of historical bazaars. This model consists of three main networks for evaluating the resilience of historical networks in terms of adaptability, variability and reactivity.

The ANN proposed to evaluate the resilience of historic bazaars based on the mentioned factors is efficient. By calculating mean squared error (MSE), the model accuracy for evaluating adaptability, variability and reactivity were obtained at 7.62e-25, 2.91e-24 and 1.51e-24. The correlation coefficient was obtained at a significance level of 99%. This indicates the considerable effectiveness of the artificial intelligence model in modeling and predicting the qualitative properties of historical bazaars resilience.

This paper clarifies indexes and components of resilience in terms of adaptability, variability and reactivity. Then, the ANN model is obtained with the least error and very high accuracy that predict the resilience of historical bazaars.

Forecasting population movement trends is crucial for implementing effective policies to regulate labor force growth and understand demographic changes. Combining migration theory expertise and neural network technology can bring a fresh perspective to international migration forecasting research.

This study proposes a conditional generative adversarial neural network model incorporating the migration knowledge – conditional generative adversarial network (MK-CGAN). By using the migration knowledge to design the parameters, MK-CGAN can effectively address the limited data problem, thereby enhancing the accuracy of migration forecasts.

The model was tested by forecasting migration flows between different countries and had good generalizability and validity. The results are robust as the proposed solutions can achieve lesser mean absolute error, mean squared error, root mean square error, mean absolute percentage error and R² values, reaching 0.9855 compared to long short-term memory (LSTM), gated recurrent unit, generative adversarial network (GAN) and the traditional gravity model.

This study is significant because it demonstrates a highly effective technique for predicting international migration using conditional GANs. By incorporating migration knowledge into our models, we can achieve prediction accuracy, gaining valuable insights into the differences between various model characteristics. We used SHapley Additive exPlanations to enhance our understanding of these differences and provide clear and concise explanations for our model predictions. The results demonstrated the theoretical significance and practical value of the MK-CGAN model in predicting international migration.

The study aimed to analyze the influence of network embeddedness on the innovation performance of high-tech enterprises in Guangdong Province.

A conceptual model of the influence of network embeddedness on the innovation performance of high-tech enterprises in Guangdong province is established, which takes the business model as the mediating variable and political association as the moderating variable. Multivariate statistical analysis and the MacKinnon confidence interval method were used to analyze 418 questionnaires.

The results show that both relational embeddedness and structural embeddedness have significant positive effects on the innovation performance of high-tech enterprises in Guangdong Province. The business model has a partial mediating effect between relationship embeddedness, structure embeddedness, and innovation performance of high-tech enterprises in Guangdong Province, respectively. Political relevance has a significant negative moderating effect on the relationship between the relationship embeddedness and innovation performance of high-tech enterprises in Guangdong Province, but the moderating effect on structural embeddedness and innovation performance of high-tech enterprises in Guangdong province has not been verified.

The study of this paper also has some shortcomings: very few data research samples exist; the external factors affecting the performance of high-tech enterprises in Guangdong Province need to be further refined. The research scale needs further improvement.

In this paper, embedding theory, transaction cost theory, resource dependence theory, rent-seeking theory, new institution theory and uncertainty management theory were integrated by system attempt to reveal the mediating and moderating roles of business model and political relevance, respectively, between network embeddedness behavior and entrepreneurial innovation performance of high-tech enterprises. The research conclusions expand the relevant research in the field of entrepreneurial innovation. At the same time, the research results provide theoretical support and reference for the innovative growth of high-tech enterprises and government behavior decision-making in Guangdong province.

Network embeddedness will have a profound impact on the entrepreneurial innovation performance of high-tech enterprises. Existing research has overlooked discussing this issue from the perspective of internal and external influencing factors within the enterprise. Therefore, this study addresses this issue by (1) introducing the business model as the mediating variable from an internal perspective of the enterprise, (2) introducing political association as the moderating variable from an external perspective of the enterprise and (3) 418 original questionnaires of high-tech enterprises in Guangdong Province were used to test the effect of the study variables.

A circular economy (CE) is an economic system that tries to eliminate waste and continually use resources. Due to growing environmental concerns, supply chain (SC) design should be based on the CE considerations. In addition, responding and satisfying customers are the challenges managers constantly encounter. This study aims to improve the design of an agile closed-loop supply chain (CLSC) from the CE point of view.

In this research, a new multi-stage, multi-product and multi-period design of a CLSC network under uncertainty is proposed that aligns with the goals of CE and SC participants. Recycling of goods is an important part of the CLSC. Therefore, a multi-objective mixed-integer linear programming model (MILP) is proposed to formulate the problem. Besides, a robust counterpart of multi-objective MILP is offered based on robust optimization to cope with the uncertainty of parameters. Finally, the proposed model is solved using the e-constraint method.

The proposed model aims to provide the strategic choice of economic order to the suppliers and third-party logistic companies. The present study, which is carried out using a numerical example and sensitivity analysis, provides a robust model and solution methodology that are effective and applicable in CE-related problems.

This study shows how all upstream and downstream units of the SC network must work integrated to meet customer needs considering the CE context.

The main goal of the CE is to optimize resources, reduce the use of raw materials, and revitalize waste by recycling. In this study, a comprehensive model that can consider both SC design and CE necessities is developed that considers all SC participants.

The below-average innovative capacity of the tourism sector raises the question on the potentials of digital business ecosystems (DBEs) to overcome these shortages at a destination level – especially within a smart city environment. Using the example of the German Capital Berlin, this article aims to discuss both the possibilities and inhibitors of innovative knowledge-creation by building scenarios on one specific design option: the integration of digital deep learning (DL) functionalities and traditional organizational learning (OL) processes.

Using the qualitative GABEK-method, major characteristics of a DBE as resource-, platform- and innovation systems are analyzed toward their interactions with the construction of basic action models (as the basic building blocks of knowledge).

Against the background of the research findings, two scenarios are discussed for future evolution of the Berlin DBE, one building on cultural emulation as a trigger for optimized DL functionalities and one following the idea of cultural engineering supported by DL functionalities. Both scenarios focus specifically on the identified systemic inhibitors of innovative capabilities.

While this study highlights the potential of the GABEK method to analyze mental models, separation of explicit and latent models still remains challenging – so does the reconstruction of higher order mental models which require a combined take on interview techniques in the future.

The resulting scenarios innovatively combine concepts from OL theory with the concept of DBE, thus indicating possible pathways into a tourism future where the limitations of human learning capacities could be compensated through the targeted support of general artificial intelligence (AI).

The energy efficiency of buildings has been emphasized along with the continual development in the building and construction sector that consumes a significant amount of energy. To this end, the purpose of this research paper is to forecast energy consumption to improve energy resource planning and management.

This study proposes the application of the convolutional neural network (CNN) for estimating the electricity consumption in the Grey Nuns building in Canada. The performance of the proposed model is compared against that of long short-term memory (LSTM) and multilayer perceptron (MLP) neural networks. The models are trained and tested using monthly electricity consumption records (i.e. from May 2009 to December 2021) available from Concordia’s facility department. Statistical measures (e.g. determination coefficient [R²], root mean squared error [RMSE], mean absolute error [MAE] and mean absolute percentage error [MAPE]) are used to evaluate the outcomes of models.

The results reveal that the CNN model outperforms the other model predictions for 6 and 12 months ahead. It enhances the performance metrics reported by the LSTM and MLP models concerning the R², RMSE, MAE and MAPE by more than 4%, 6%, 42% and 46%, respectively. Therefore, the proposed model uses the available data to predict the electricity consumption for 6 and 12 months ahead. In June and December 2022, the overall electricity consumption is estimated to be 195,312 kWh and 254,737 kWh, respectively.

This study discusses the development of an effective time-series model that can forecast future electricity consumption in a Canadian heritage building. Deep learning techniques are being used for the first time to anticipate the electricity consumption of the Grey Nuns building in Canada. Additionally, it evaluates the effectiveness of deep learning and machine learning methods for predicting electricity consumption using established performance indicators. Recognizing electricity consumption in buildings is beneficial for utility providers, facility managers and end users by improving energy and environmental efficiency.