With the rapid development of artificial intelligence and deep learning, image-text matching has gradually become an important research topic in cross-modal fields. Achieving correct image-text... Show More

With the rapid development of artificial intelligence and deep learning, image-text matching has gradually become an important research topic in cross-modal fields. Achieving correct image-text matching requires a strong understanding of the correspondence between visual and textual information. In recent years, deep learning-based image-text matching methods have achieved significant success. However, image-text matching requires a deep understanding of intra-modal information and the exploration of fine-grained alignment between image regions and textual words. How to integrate these two aspects into a single model remains a challenge. Additionally, reducing the internal complexity of the model and effectively constructing and utilizing prior knowledge are also areas worth exploring, therefore addressing the issues of excessive computational complexity in existing fine-grained matching methods and the lack of multi-perspective matching.

This study investigates the effect of digital finance on Chinese OFDI using Probit and Logit models on A-share-listed Chinese enterprises and representative OFDI data from 2011 to 2020. It shows... Show More

This study investigates the effect of digital finance on Chinese OFDI using Probit and Logit models on A-share-listed Chinese enterprises and representative OFDI data from 2011 to 2020. It shows that digital finance has a heterogeneous impact on Chinese OFDI both in probability and scale depending on the enterprise digitalization level. That is, digital finance has a positive (negative) effect on the OFDI of high (low) digital enterprises. Mechanism analysis reveals that the digital divide, which causes credit resources to be squeezed and increased financing constraints for these enterprises, is the main cause of the negative impact of digital finance on the OFDI of low-digital enterprises while the negative impact of digital finance on the OFDI of low-digital enterprises is limited to greenfield investments and highly competitive industries. The findings highlight the importance of encouraging enterprise digital transformation when developing digital finance policies to effectively leverage the potential of digital finance to drive Chinese firms' OFDI.

Innovation management involves planning, organizing, and controlling innovation within an organization, while venture capital evaluation assesses investment opportunities in startups and early-stage... Show More

Innovation management involves planning, organizing, and controlling innovation within an organization, while venture capital evaluation assesses investment opportunities in startups and early-stage companies. Both fields require effective decision-making and data analysis. This study aims to enhance innovation management and venture capital evaluation by combining CNN and GRU using deep learning. The approach consists of two steps. First, the authors build a deep learning model that fuses CNN and GRU to analyze diverse data sources like text, finance, market trends, and social media sentiment. Second, they optimize the model using the gorilla troop optimization (GTO) algorithm, inspired by gorilla behavior. GTO efficiently explores the solution space to find optimal or near-optimal solutions. The authors compare the fused CNN-GRU model with traditional methods and evaluate the GTO algorithm's performance. The results demonstrate improvements in innovation management and venture capital evaluation.

When compared to traditional indicators, text information can capture market sentiment, investor confidence, and public opinion more effectively. Meanwhile, the mixed-frequency dynamic factor model... Show More

When compared to traditional indicators, text information can capture market sentiment, investor confidence, and public opinion more effectively. Meanwhile, the mixed-frequency dynamic factor model (MF-DFM) can capture current changes. In this study, the authors constructed a financial cycle measurement and nowcasting framework by incorporating text information into factors derived from MF-DFM. The findings reveal that, first, the financial cycle indicator (FCI) provides a more detailed and forward-looking perspective on major events. Second, it can serve as an effective “early warning system” by cross-referencing economic indicators. Third, financial cycles exhibit five short cycles, with contraction periods being longer than expansion phases and expansion amplitudes surpassing contractions. Lastly, the analysis suggests a potential turning point in the second half of 2023. This research represents a valuable attempt to integrate big data for more sensitive, timely, and accurate monitoring of financial dynamics.

In this study, the authors explore how financial institutions make decisions about stock trading strategies in a rapidly changing and complex environment. These decisions are made with limited... Show More

In this study, the authors explore how financial institutions make decisions about stock trading strategies in a rapidly changing and complex environment. These decisions are made with limited, often inconsistent information and depend on the current and future strategies of both the institution itself and its competitors. They develop a dynamic game model that factors in this imperfect information and the evolving nature of decision-making. To model reward transitions, they utilize a combination of t-Copula simulation of a non-stationary Markov chain, probabilistic fuzzy regression, and chaos optimization algorithms. They then apply deep q-network, a method from deep reinforcement learning, to ensure the effectiveness of the chosen strategy during ongoing decision-making. The approach is significant for both researchers across fields and practical professionals in the finance industry.

This study proposes a deep learning-based analytical model to conduct an in-depth study of the relationship between consumer trust, perceived benefits, and purchase intention. This model combines... Show More

This study proposes a deep learning-based analytical model to conduct an in-depth study of the relationship between consumer trust, perceived benefits, and purchase intention. This model combines natural language processing and sentiment analysis, using the BERT-LSTNet-Softmax model to extract textual features in reviews and perform temporal predictions of consumer sentiment and purchase intention. Experimental results show that this model achieves excellent performance in the e-commerce field and provides a powerful tool for in-depth understanding of consumer purchasing decisions. This research promotes the application of deep learning technology in the field of e-commerce, helps to improve the accuracy of consumer purchase intentions, and provides more support for the development of the e-commerce market and consumer decision-making.

A trademark is an essential symbol of a company, consisting of a semantically rich image under ordinary circumstances. The popularity of a company can be measured by the frequency of its trademark... Show More

A trademark is an essential symbol of a company, consisting of a semantically rich image under ordinary circumstances. The popularity of a company can be measured by the frequency of its trademark being used. Therefore, efficiently retrieving trademark images would directly contribute to the detection of popular companies. However, most mainstream retrieval methods are not especially pertinent to trademark image retrieval. To solve this problem, a combination of the ResNet50 network and Autoencoder with local sensitive hashing (LSH) is used to conduct full cross-checking, which significantly improves the effectiveness of trademark image retrieval. Meanwhile, image super-resolution-based sparse coding is also proposed to achieve high-precision trademark image retrieval and its effect is particularly significant for challenging trademark images. Finally, the authors conduct extensive experiments on a high-quality database to demonstrate the substantial effectiveness of the proposed methods.

Thanks to the rapid growth of cross-border e-commerce platforms, numerous cross-border items are now available to customers. Several serious issues with cross-border e-commerce platforms related to... Show More

Thanks to the rapid growth of cross-border e-commerce platforms, numerous cross-border items are now available to customers. Several serious issues with cross-border e-commerce platforms related to item promotion and consumer product screening have arisen. Particular importance should be placed on studying and implementing personalized recommendation systems based on international e-commerce. In light of the quick expansion of commodities, when making individualized suggestions, traditional recommendation algorithms have had to deal with issues such as scant data, a chilly start to the market, and trouble identifying user preferences. To automatically mine the implicit and latent relationships between users and objects in recommendation systems, this study employs deep learning with nonlinear learning capabilities, which resolves the challenges of user interest mining. The weaknesses of the existing global recommendation research are emphasized, the study of conventional recommendation algorithms mixed with deep learning technology is deep factorization machine (DeepFM) and neural matrix factorization (NeuMF) models. Both models excel in recommending implicit feedback data. The DeepFM model yields the lowest loss function values, while the NeuMF model outperforms the competing models in terms of HR@20 (a commonly used indicator to measure the recall rate) and loss functions. In summary, this research addresses critical issues in cross-border e-commerce by developing personalized recommendation systems and integrating deep learning with traditional recommendation algorithms to enhance global recommendations.

This project addresses demand forecasting and inventory optimization in supply chain management. Traditional methods have limitations with complex demand patterns and large-scale data. Deep learning... Show More

This project addresses demand forecasting and inventory optimization in supply chain management. Traditional methods have limitations with complex demand patterns and large-scale data. Deep learning techniques are employed to enhance accuracy and efficiency. The project utilizes BO-CNN-LSTM, leveraging Bayesian optimization for hyperparameter tuning, Convolutional Neural Networks (CNNs) for spatiotemporal feature extraction, and Long Short-Term Memory Networks (LSTMs) for modeling sequential data. Experimental results validate the effectiveness of the approach, outperforming traditional methods. Practical implementation in supply chain management improves operational efficiency and cost control.

With the growing urgency of global climate change, carbon neutrality, as a strategy to reduce greenhouse gas emissions into the atmosphere, is increasingly seen as a critical solution. However... Show More

With the growing urgency of global climate change, carbon neutrality, as a strategy to reduce greenhouse gas emissions into the atmosphere, is increasingly seen as a critical solution. However, current forecasting models still face significant challenges and limitations in accurately and effectively predicting carbon emissions and their associated effects. These challenges largely stem from the complexity of carbon emission data and the interplay of anthropogenic and natural factors. To overcome these obstacles, the authors introduce an advanced forecasting model, the SSA-Attention-BIGRU network. This model ingeniously integrates an external attention mechanism, bidirectional GRU, and SSA components, allowing it to synthesize various key factors and enhance prediction accuracy when forecasting carbon neutrality trends. Through experiments on multiple datasets, the results demonstrate that, compared to other popular methods, the SSA-Attention-BIGRU network significantly excels in prediction accuracy, robustness, and reliability.

VQA (visual question and answer) is the task of enabling a computer to generate accurate textual answers based on given images and related questions. It integrates computer vision and natural... Show More

VQA (visual question and answer) is the task of enabling a computer to generate accurate textual answers based on given images and related questions. It integrates computer vision and natural language processing and requires a model that is able to understand not only the image content but also the question in order to generate appropriate linguistic answers. However, current limitations in cross-modal understanding often result in models that struggle to accurately capture the complex relationships between images and questions, leading to inaccurate or ambiguous answers. This research aims to address this challenge through a multifaceted approach that combines the strengths of vision and language processing. By introducing the innovative LIUS framework, a specialized vision module was built to process image information and fuse features using multiple scales. The insights gained from this module are integrated with a “reasoning module” (LLM) to generate answers.

The fairness of vocational contest scoring is key to generating reliable competency assessments. This study examined the performance impact of the motivation of English-as-a-foreign-language... Show More

The fairness of vocational contest scoring is key to generating reliable competency assessments. This study examined the performance impact of the motivation of English-as-a-foreign-language learners in contests with vocabulary knowledge antecedents in the contexts of artificial intelligence (AI) and blockchain (BC). The sample comprised 185 participants of an oral English contest at higher vocational institution in China. AI-powered scoring of learners' contest performance and a survey were used to collect data. The findings revealed that learners' intrinsic drive was the main positive factor, outweighing their extrinsic motivation, and that AI and BC increased the trustworthiness and integrity of contest records, thus providing new opportunities to build learner trust and form psychological incentives. This study enriches foreign language motivation theory in the context of contest research and highlights the importance of using AI and BC to enhance the scoring accuracy and credibility of contests as authoritative evaluation instruments in vocational education.

With the penetration of deep learning technology into forecasting and decision support systems, enterprises have an increasingly urgent need for accurate forecasting of time series data. Especially... Show More

With the penetration of deep learning technology into forecasting and decision support systems, enterprises have an increasingly urgent need for accurate forecasting of time series data. Especially in fields such as finance, retail, and production, immediate and accurate predictions of market trends are the key to maintaining a competitive advantage. This study aims to address the limitations of traditional time series forecasting methods, such as the difficulty in adapting to the nonlinearity and non-stationarity of the data, through an innovative deep learning framework. The authors propose a Prophet model that combines deep learning with LSTNet and statistics. In this way, they combine the ability of LSTNet to handle complex time dependencies and the flexibility of the Prophet model to handle trends and periodicity. The particle swarm optimization algorithm (PSO) is responsible for tuning this hybrid model, aiming to improve the accuracy of predictions. Such a strategy not only helps capture long-term dependencies in time series, but also models seasonality and holiday effects well.

This study aims to enhance the efficacy of personalized learning paths by amalgamating transformer models, generative adversarial networks (GANs), and reinforcement learning techniques. To refine... Show More

This study aims to enhance the efficacy of personalized learning paths by amalgamating transformer models, generative adversarial networks (GANs), and reinforcement learning techniques. To refine personalized learning trajectories, the authors integrated the transformer model for enhanced information assimilation and learning path planning. Through generative adversarial networks, the authors simulated the fusion and interaction of multi-modal information, refining the training of virtual teaching assistants. Lastly, reinforcement learning was employed to optimize the interaction strategies of these assistants, aligning them better with student needs. In the experimental phase, the authors benchmarked their approach against six state-of-the-art models to assess its effectiveness. The experimental outcomes highlight significant enhancements achieved by the authors' virtual teaching assistant compared to traditional methods. Precision improved to 95% and recall to 96%, and an F1 score exceeding 95% was attained.

Conventional automobile manufacturing plants involve intricate assembly, testing, and debugging processes heavily reliant on manual operations. This study aims to explore the application of... Show More

Conventional automobile manufacturing plants involve intricate assembly, testing, and debugging processes heavily reliant on manual operations. This study aims to explore the application of industrial internet of things (IIoT) and deep learning algorithms to achieve process automation in manufacturing. Firstly, utilizing IIoT technology, OPC UA, and point cloud fitting techniques, a comprehensive modeling of most equipment and materials within the factory is conducted, constructing a digital twin (DT) model as a virtual representation of actual equipment. Subsequently, the study innovatively introduces the deep Q network algorithm, facilitating the automatic transition of the production process and improving production efficiency. Through comparison with ten baseline models, the proposed model demonstrates an improvement in production efficiency of at least four percentage points compared to other models. Experimental validation confirms the effectiveness of the proposed model in the smart factory for electric vehicle manufacturing.

This article presents a study using ResNet-50, GRU, and transfer learning to construct a marketing decision-making model and predict consumer behavior. Deep learning algorithms address the scale and... Show More

This article presents a study using ResNet-50, GRU, and transfer learning to construct a marketing decision-making model and predict consumer behavior. Deep learning algorithms address the scale and complexity of consumer data in the information age. Traditional methods may not capture patterns effectively, while deep learning excels at extracting features from large datasets. The research aims to leverage deep learning to build a marketing decision-making model and predict consumer behavior. ResNet-50 analyzes consumer data, extracting visual features for marketing decisions. GRU model temporal dynamics, capturing elements like purchase sequences. Transfer learning improves performance with limited data by using pre-trained models. By comparing the model predictions with ground truth data, the performance of the models can be assessed and their effectiveness in capturing consumer behavior and making accurate predictions can be measured. This research contributes to marketing decision-making. Deep learning helps understand consumer behavior, formulate personalized strategies, and improve promotion and sales. It introduces new approaches to academic marketing research, fostering collaboration between academia and industry.

In today's digital age, the e-commerce industry continues to grow and flourish. The widespread application of computer vision technology has brought revolutionary changes to e-commerce platforms.... Show More

In today's digital age, the e-commerce industry continues to grow and flourish. The widespread application of computer vision technology has brought revolutionary changes to e-commerce platforms. Extracting image features from e-commerce platforms using deep learning techniques is of paramount importance for predicting product sales. Deep learning-based computer vision models can automatically learn image features without the need for manual feature extractors. By employing deep learning techniques, key features such as color, shape, and texture can be effectively extracted from product images, providing more representative and diverse data for sales prediction models. This study proposes the use of ResNet-101 as an image feature extractor, enabling the automatic learning of rich visual features to provide high-quality image representations for subsequent analysis. Furthermore, a bidirectional attention mechanism is introduced to dynamically capture correlations between different modalities, facilitating the fusion of multimodal features.

To elevate the intelligence of customer service dialogue systems, this article proposes an intelligent customer service system comprising chat dialogue subsystems, task-oriented multi-turn dialogue... Show More

To elevate the intelligence of customer service dialogue systems, this article proposes an intelligent customer service system comprising chat dialogue subsystems, task-oriented multi-turn dialogue subsystems, single-turn dialogue subsystems, and an integration model. Firstly, to enhance diversity of responses and improve user experience, particularly in casual chat scenarios, this article presents a Seq2Seq-based approach for multi-answer responses, allowing for more expressive emotional expression in responses. Secondly, to address situations where customers cannot articulate their needs in a single sentence during multi-turn dialogues, this article designs a task-oriented multi-turn dialogue module. It employs intent recognition and slot filling to maintain contextual information throughout the conversation, aiding customers in problem resolution. Lastly, to overcome the current limitation of intelligent customer service models providing relatively one-dimensional answers in specific domains.

In today's global society, carbon neutrality has become a focal point of concern. Greenhouse gas emissions and rising atmospheric temperatures are triggering various extreme weather events, sea... Show More

In today's global society, carbon neutrality has become a focal point of concern. Greenhouse gas emissions and rising atmospheric temperatures are triggering various extreme weather events, sea level rise, and ecological imbalances. These changes not only affect the stability and sustainable development of human society but also pose a serious threat to the Earth's ecosystems and biodiversity. Faced with this global challenge, finding effective solutions has become urgent. This article aims to propose a comprehensive artificial intelligence design approach to address issues related to carbon neutrality. This method integrates technologies from fields such as computer vision, natural language processing, and deep learning to achieve a comprehensive understanding of environmental conservation and innovative solutions. Specifically, the authors first use a visual module to extract features from images, which helps capture important information in the images. Next, we employ the ALBEF model for cross-modal alignment, enabling better collaboration between images and textual information.

As global financial markets continue to evolve and change, financial risk monitoring and early warning have become increasingly important. However, the complexity and diversity of financial markets... Show More

As global financial markets continue to evolve and change, financial risk monitoring and early warning have become increasingly important. However, the complexity and diversity of financial markets have led to the emergence of multidimensional and multimodal data. Traditional risk monitoring methods face difficulties in handling such diverse data and adapting to the monitoring and early warning needs of emerging risk types. To address these issues, this article proposes a financial risk intelligent monitoring and early warning model that integrates deep learning to better cope with uncertainty and risk in the financial market. Firstly, the authors introduce an LSTM model in the initial approach, trained on historical financial market data, to capture long-term dependencies and trends in the data, enabling effective monitoring of financial risk. They also optimize the model architecture to improve its performance and prediction accuracy. Secondly, the authors further introduce a transformer model with self-attention mechanism to better handle sequential data.

This research delves into the integration of the CDIO framework and gamified learning into a web crawling system, aiming to elevate the innovation and practical skills of corporate trainees. The... Show More

This research delves into the integration of the CDIO framework and gamified learning into a web crawling system, aiming to elevate the innovation and practical skills of corporate trainees. The study examines the effects on learning achievement, immersion, and behavioral intentions among corporate trainees. Results indicate that those utilizing the gamified web crawling learning system exhibit enhanced learning achievement. HMSAM analysis unveils notable standardized path coefficients, wherein perceived ease of use positively influences perceived usefulness, curiosity, joy, and control. Perceived usefulness and joy significantly impact behavioral intention to use, prompting corporate trainees to express a continued willingness to use the system. These findings deepen our comprehension of CDIO and gamified learning applications in corporate education and training, emphasizing the importance of aligning educational tools with the interests and preferences of corporate trainees.

This article aims to study the role of digital finance in rural revitalization by utilizing the data for 30 provinces in China Mainland from 2012 to 2019, via the fixed effect model and differential... Show More

This article aims to study the role of digital finance in rural revitalization by utilizing the data for 30 provinces in China Mainland from 2012 to 2019, via the fixed effect model and differential GMM model. The empirical results show that the level of rural revitalization varies among different regions in China. In addition, the development of digital inclusive finance is essential in promoting rural revitalization, which is credible while we conduct several robustness tests such as changing the measurement of digital finance and including the dynamic progress by utilizing the GMM estimation. The impact of digital inclusive finance on rural revitalization is not constant among different regions, the positive impact of digital finance on rural revitalization is stronger in eastern region than that in central and western regions.

In the context of current smart city development, the efficiency of urban management has become crucial. Target detection technology plays a vital role in addressing the complexity of urban... Show More

In the context of current smart city development, the efficiency of urban management has become crucial. Target detection technology plays a vital role in addressing the complexity of urban environments. The authors propose a new method called YOLOv8_k, employing transfer learning as its foundation. This method leverages pre-trained model parameters from related tasks to incorporate prior knowledge into the target detection model, adapting better to the complexity of smart city management scenarios. Experimental results demonstrate the outstanding performance of YOLOv8_k. In specific experimental results, YOLOv8_k shows significant improvements across multiple evaluation metrics. The average precision in target detection tasks experiences a notable increase. Furthermore, in large-scale urban datasets, compared to traditional methods, YOLOv8_k exhibits higher responsiveness in handling large volumes of real-time data, further demonstrating its superiority in practical applications.

The results indicate a dynamic pattern of interconnectedness throughout history. Based on the findings, the transmission of volatility exhibited a higher magnitude during the period of COVID-19. The... Show More

The results indicate a dynamic pattern of interconnectedness throughout history. Based on the findings, the transmission of volatility exhibited a higher magnitude during the period of COVID-19. The issue of high transmission volatility due to limited diversification options concerns investors, green stakeholders, and policymakers alike. This article proposes various potential areas for future research. The ICEA index can potentially assist businesses operating in environmentally sensitive sectors make well-informed policy decisions. It includes sectors such as environmental green bonds, and commodities. Consideration should be given to implementing blockchain technology, as it can consume less power in this particular scenario. By employing a time-frequency paradigm, this study is able to incorporate the investment horizon, a crucial factor to be taken into account when making financial judgments. The advancement of this research could be facilitated by directing our attention toward the implications of our findings on portfolios and developing appropriate measures for their evaluation.

Effectively fusing information between the visual and language modalities remains a significant challenge. To achieve deep integration of natural language and visual information, this research... Show More

Effectively fusing information between the visual and language modalities remains a significant challenge. To achieve deep integration of natural language and visual information, this research introduces a multimodal fusion neural network model, which combines visual information (RGB images and depth maps) with language information (natural language navigation instructions). Firstly, the authors used faster R-CNN and ResNet50 to extract image features and attention mechanism to further extract effective information. Secondly, GRU model is used to extract language features. Finally, another GRU model is used to fuse the visual- language features, and then the history information is retained to give the next action instruction to the robot. Experimental results demonstrate that the proposed method effectively addresses the localization and decision-making challenges for robotic vacuum cleaners.

With the rapid development of artificial intelligence technology, algorithmic management is increasingly prevalent in enterprises. Despite the considerable scholarly attention given to the impact of... Show More

With the rapid development of artificial intelligence technology, algorithmic management is increasingly prevalent in enterprises. Despite the considerable scholarly attention given to the impact of algorithmic management, a research gap remains regarding its influence on employee creativity. To address this gap, the authors developed a theoretical model using ability-motivation-opportunity (AMO) theory. This model aims to investigate the direct impacts of algorithmic management (opportunity) on employee creativity (performance) while also considering the mediating roles played by knowledge combination capability (ability) and achievement goal (motivation). Using a sample of 327 paired leader-employee data from an information technology service company, the findings reveal that algorithmic management has a negative effect on employee creativity. Furthermore, the results demonstrate that algorithmic management negatively influences employee creativity through its impact on knowledge combination capability and achievement goal.

Driven by the wave of digitalization, the booming development of the e-commerce industry urgently requires in-depth analysis of user shopping behavior to improve service experience. In view of the... Show More

Driven by the wave of digitalization, the booming development of the e-commerce industry urgently requires in-depth analysis of user shopping behavior to improve service experience. In view of the limitations of traditional models in dealing with complex shopping scenarios, this study innovatively proposes a deep learning model: the VATA model (a combination of variational autoencoder, transformer, and attention mechanism). Through this model, the authors strive to classify and analyze user shopping behavior more accurately and intelligently. Variational autoencoder (VAE) can learn the potential representation of user personalized historical data, capture the implicit characteristics of shopping behavior, and improve the ability to deal with actual shopping situations. Transformer models can more comprehensively capture the dependencies between shopping behaviors and understand shopping. The overall structure of behavior plays an important role.

This study explores the potential application of deep learning techniques in stock market prediction and investment decision-making. The authors used multi-temporary stock data (MTS) for effective... Show More

This study explores the potential application of deep learning techniques in stock market prediction and investment decision-making. The authors used multi-temporary stock data (MTS) for effective multi-scale feature extraction in reverse cross attention (RCA), combined with improved whale optimization algorithm (IWOA) to select the optimal parameters for the bidirectional long short-term memory network (BiLSTM) and constructed an innovative RCA-BiLSTM stock intelligent trend prediction model. At the same time, a complete RCA-BiLSTM-DQN stock intelligent prediction and investment model was established by combining the deep Q network (DQN) investment strategy. The research results indicate that the model has excellent sequence modeling and decision learning capabilities, which can capture the nonlinear characteristics and complex correlations of the market and provide more accurate prediction results. It can continuously improve the robustness and stability of the model through adaptive learning and automatic optimization.

In the face of intensifying global climate change, carbon neutrality has emerged as a pivotal strategy to curb greenhouse gas emissions and confront the complexities associated with climate... Show More

In the face of intensifying global climate change, carbon neutrality has emerged as a pivotal strategy to curb greenhouse gas emissions and confront the complexities associated with climate challenges. However, achieving carbon neutrality poses a formidable challenge: the identification and mitigation of anomalies within the carbon sequestration process. These anomalies can result in unintended carbon dioxide leakage, emissions, or system failures, thus jeopardizing the feasibility and resilience of carbon neutrality initiatives. This research introduces the ResNet-BIGRU-TPA network, an innovative model that integrates deep learning techniques with time series attention mechanisms. The primary focus centers on addressing the intricate task of anomaly detection within the realm of carbon offsetting, specifically aiming to enhance precision in identifying a wide array of complex anomalous events. Through rigorous experimental validation across four diverse datasets, the model has exhibited exceptional performance.

Visual search technology, because of its convenience and high efficiency, is widely used by major tourism e-commerce platforms in product search functions. This study introduces an innovative visual... Show More

Visual search technology, because of its convenience and high efficiency, is widely used by major tourism e-commerce platforms in product search functions. This study introduces an innovative visual search engine model, namely CLIP-ItP, aiming to thoroughly explore the application potential of visual search in tourism e-commerce. The model is an extension of the CLIP (contrastive language-image pre-training) framework and is developed through three pivotal stages. Firstly, by training an image feature extractor and a linear model, the visual search engine labels images, establishing an experimental visual search engine. Secondly, CLIP-ItP jointly trains multiple text and image encoders, facilitating the integration of multimodal data, including product image labels, categories, names, and attributes. Finally, leveraging user-uploaded images and jointly selected product attributes, CLIP-ItP provides personalized top-k product recommendations.

Disruption events highlight the importance of supply chain resilience (SCR) and leave managers wondering what characteristics can help firms survive and recover. This study employs the... Show More

Disruption events highlight the importance of supply chain resilience (SCR) and leave managers wondering what characteristics can help firms survive and recover. This study employs the knowledge-based theory to investigate factors contributing to SCR. Using data collected from 220 manufacturing firms in China, this study empirically examines the proposed research model. Results indicate KM processes (i.e., creation, sharing, utilization) significantly influence SCR, with collaborative innovation capability (CIC) mediating the relationship between KM and SCR. Interestingly, social media use positively moderates the relationship between knowledge sharing/utilization and CIC, while this effect is absent for the relationship between knowledge creation and CIC. These findings enrich the existing literature on knowledge management and supply chain management, offering managerial insights for effective knowledge strategies and resilience improvement.

With the rapid advancement of financial technology, an increasing number of related advertisements have received widespread attention. User engagement detection during the advertisement viewing... Show More

With the rapid advancement of financial technology, an increasing number of related advertisements have received widespread attention. User engagement detection during the advertisement viewing process directly reflects the effectiveness of the advertising video. Therefore, detecting user engagement during the advertisement viewing process has become a crucial issue. However, traditional engagement detection methods often require significant computational resources, significantly reducing their practicality. To address this issue, the authors propose a method to effectively detect user engagement by fully integrating multiple relatively practical models. Specifically, the authors extract key frame images from user face video and perform super-resolution reconstruction of them. Then image pyramid matching is used to achieve user engagement detection. Finally, the authors establish a reasonable database and conduct sufficient experiments based on it. Experimental results demonstrate that this proposed method has realistic engagement detection accuracy, and the design of multiple steps is also valid.

With the continuous evolution of digital marketing, the generation of advertising images has become crucial in capturing user interest and enhancing advertising effectiveness. However, existing... Show More

With the continuous evolution of digital marketing, the generation of advertising images has become crucial in capturing user interest and enhancing advertising effectiveness. However, existing methods face limitations in meeting the diverse and creative demands of advertising content, necessitating innovative algorithms to improve advertising generation outcomes. In addressing these challenges, this study proposes a deep learning algorithm framework that cleverly integrates a generative adversarial network and an VGG-based visual transformer model to enhance the effectiveness of advertising image generation. Systematic experimentation shows that the model proposed in this article achieves an AUC metric value of more than 0.7 on several datasets. The results of the experiments demonstrate that the novel algorithm significantly improves the attractiveness of advertising content, particularly showcasing substantial benefits in website operations during online evaluation experiments.

In today's digital economy, digital marketing has become a crucial means for businesses to drive growth and enhance brand exposure. However, with increasing competition, predicting and optimizing... Show More

In today's digital economy, digital marketing has become a crucial means for businesses to drive growth and enhance brand exposure. However, with increasing competition, predicting and optimizing advertising effectiveness has become a pivotal component in formulating digital marketing strategies. In order to better understand ad creatives and deeply explore the information within them, this study focuses on integrating visual transformer (VIT) and graph neural network (GNN) methods. Additionally, the study leverages generative adversarial networks (GAN) to enhance the quality of visual features, aiming to achieve visual analysis, exploration, and prediction of advertising effectiveness in digital marketing. This approach begins by employing VIT, an emerging visual transformer technology, to transform image information into high-dimensional feature representations.

Faced with challenges in sales predicting research, this article combines the capabilities of deep learning algorithms in handling complex tasks and unstructured data. Through analyzing consumer... Show More

Faced with challenges in sales predicting research, this article combines the capabilities of deep learning algorithms in handling complex tasks and unstructured data. Through analyzing consumer behavior, it selects factors influencing sales, including images, prices and discounts, and historical sales, as input variables for the model. Three different types of neural network models-fully connected neural networks, convolutional neural networks, and recurrent neural networks-are employed to process structured data, image data, and sales sequence data, respectively. This forms a deep neural network for feature representation. Subsequently, based on the outputs of these three types of deep neural networks, a fully connected neural network is employed to train the sales prediction model. Ultimately, experimental results demonstrate that the proposed sales prediction method outperforms exponential regression and shallow neural networks in terms of accuracy.

The significance of financial risk lies in its impact on economic stability and individual/institutional financial security. Effective risk management is crucial for market confidence and crisis... Show More

The significance of financial risk lies in its impact on economic stability and individual/institutional financial security. Effective risk management is crucial for market confidence and crisis prevention. Current methods for multivariate time series anomaly detection have limitations in adaptability and generalization. To address this, we propose an innovative approach integrating contrastive learning and Generative Adversarial Networks (GANs). We use geometric distribution masking for data augmentation to enhance dataset diversity. Within the GAN framework, we train a Transformer-based autoencoder to capture normal point distributions. We include contrastive loss in the discriminator to ensure robust generalization. Rigorous experiments on four real-world datasets show that our method effectively mitigates overfitting and outperforms state-of-the-art approaches. This enhances anomaly identification in risk management, paving the way for deep learning in finance, and offering insights for future research and practical use.

In pursuit of promoting sales, certain e-commerce vendors post scarce inventory messages on product pages to signal impending stockouts. To explore how disclosure information strategy regarding... Show More

In pursuit of promoting sales, certain e-commerce vendors post scarce inventory messages on product pages to signal impending stockouts. To explore how disclosure information strategy regarding scarce inventory influences online sales, this study utilizes Chinese e-commerce data collected from February 1st to April 30th, 2023 and constructs an empirical model that delves into the relationship between the disclosure of scarce inventory information and online sales based on the signal theory. The empirical findings reveal a positive impact of scarce inventory information disclosure on online sales, with this impact being more pronounced under the moderating role of the commodity discount rate. These results hold substantial theoretical implications and offer valuable insights for practical applications in the e-commerce domain.

The digital transformation of enterprises has amplified the complexity of financial risks, underscoring the significance of optimizing financial risk warning models to ensure sustainable... Show More

The digital transformation of enterprises has amplified the complexity of financial risks, underscoring the significance of optimizing financial risk warning models to ensure sustainable development. This study integrates several deep learning techniques, including Back Propagation Neural Network (BPNN), Bi-Long Short-Term Memory (Bi-LSTM), and transfer learning, to enhance the risk warning system and improve the accuracy and efficiency of financial risk prediction models. The results demonstrate that the proposed algorithm surpasses the baseline models in various metrics. For instance, on the Altman's Z-Score dataset, there is an improvement of 1.4% in accuracy, a reduction of over 48.8% in FLOP, and an enhancement of 43.5% in MAPE. These outcomes underscore the significant advancements in risk identification, decision support, and proactive risk management facilitated by the proposed model. As a result, enterprises can derive benefits from more precise and reliable financial risk warning tools, and effectively address the challenges brought about by digital transformation.

While the internet provides abundant information, it often leads to information overload of users when purchasing goods. Tripadvisor.com, despite having a date sorting function, struggles to... Show More

While the internet provides abundant information, it often leads to information overload of users when purchasing goods. Tripadvisor.com, despite having a date sorting function, struggles to effectively filter relevant comments to users and neglects that consumer preferences may change over time. Therefore, this study aims to develop a website with visual charts showing changes in sentiment over time in reviews. The goal is to determine if this website improves user efficiency compared to the original website, reducing search time and aiding decision-making. The chart generation process involves four stages: collecting and preprocessing comments, constructing a hotel feature dictionary, classifying sentences and computing sentiment scores, and embedding charts on the website. 36 Tripadvisor.com users participate in experiments to evaluate the impact of old and new interfaces on answer quantity and search time. The NASA.tlx scale is used to assess the mental load experienced with both interfaces.

The aim of this research is to explore the mediating and moderating effects of various HR functions and regulatory environments on the relationship between AI integration and data-driven decision... Show More

The aim of this research is to explore the mediating and moderating effects of various HR functions and regulatory environments on the relationship between AI integration and data-driven decision making in HRM. The study was conducted in a corporate sector in Malaysia, focusing on businesses actively integrating AI into their HRM functions. A total of 376 individuals successfully submitted the questionnaire, representing an 83.5% response rate. The direct and indirect effects of Workforce Planning (WP), Learning and Development (LD), Employee Engagement and Retention (EER), Performance Management (PM), Talent Acquisition (TA), and Data-Driven Decision Making (DDM) were examined through the partial least squares structural equation modeling approach (PLS-SEM). The results demonstrate that AI-enriched HR functions, including workforce planning, learning and development, employee engagement & retention, performance management, and talent acquisition, play a critical role in driving DDM.

In today's globalized and technologically advanced business landscape, supply chain collaboration is crucial for enterprises seeking to gain a competitive edge, enhance operational efficiency, and... Show More

In today's globalized and technologically advanced business landscape, supply chain collaboration is crucial for enterprises seeking to gain a competitive edge, enhance operational efficiency, and adapt to market dynamics. Traditional methods often fall short in managing the complexities and rapid changes within supply chains. This study introduces an innovative deep learning model, combining BERT, GAT, and RL, to address these challenges effectively. The model demonstrates its prowess in processing supply chain data, accurately predicting market trends, and optimizing decision-making processes. By leveraging deep learning, this research not only expands theoretical applications in supply chain management but also provides practical tools to boost operational efficiency, highlighting the immense potential and practical value of deep learning technology in modern supply chain management.

Consumer credit assessment has always been a crucial concern in the financial industry. It involves evaluating an individual's credit history and their ability to repay loans, playing a pivotal role... Show More

Consumer credit assessment has always been a crucial concern in the financial industry. It involves evaluating an individual's credit history and their ability to repay loans, playing a pivotal role in the risk management and lending decisions made by credit institutions. In the present landscape, traditional credit assessment methods confront various shortcomings. Firstly, they typically only consider static features and are unable to capture the dynamic changes in an individual's credit profile over time. Secondly, traditional methods struggle with processing complex time series data, failing to fully exploit the importance of time-related information. To address these challenges, we propose an innovative solution – the XGBoost-LSTM model optimized with the AdaBound algorithm. This hybrid model combines two powerful machine learning techniques, XGBoost and LSTM, to leverage both static and dynamic features effectively.

With the rapid evolution of financial technology, the recommendation system for financial products, as a crucial technology to enhance user experience and reduce information search costs, is... Show More

With the rapid evolution of financial technology, the recommendation system for financial products, as a crucial technology to enhance user experience and reduce information search costs, is increasingly becoming the focus of the financial services sector. As market competition intensifies, the diversity of user demands, coupled with the continuous expansion of financial product types, has exposed limitations in traditional recommendation systems regarding accuracy and personalized services. Therefore, this study aims to explore the application of deep learning technology in the field of financial product recommendations, aiming to construct a more intelligent and precise financial product recommendation system. The metrics we focus on include precision, recall, and F1-score, comprehensively evaluating the effectiveness of the proposed methods. In terms of methodology, we first employ a Transformer model, leveraging its powerful self-attention mechanism to capture the complex relationships between user behavior sequences and financial product information.

As competition in the realm of e-commerce escalates, the provision of personalized and precise shopping recommendations emerges as a pivotal strategy for e-commerce platforms striving to engage... Show More

As competition in the realm of e-commerce escalates, the provision of personalized and precise shopping recommendations emerges as a pivotal strategy for e-commerce platforms striving to engage users effectively. Traditional recommendation systems often grapple with challenges such as the inability to capture intricate relationships, limited personalization, and issues concerning diversity. In response to these challenges, this study introduces cutting-edge deep learning techniques, namely Transformer models, Generative Adversarial Networks (GANs), and reinforcement learning, with the aim of bolstering the recommendation accuracy and user experience within e-commerce shopping systems.Initially, we harness Transformer models, capitalizing on their exceptional performance in processing sequential data to adeptly extract and learn representations of both product and user features. This facilitates a more profound understanding of the correlations between products and user shopping behaviors, thus empowering the system to offer more tailored recommendations.

With the expansion of the logistics network, enterprise logistics distribution faces increasing challenges, including high transportation costs, low distribution efficiency, and unstable... Show More

With the expansion of the logistics network, enterprise logistics distribution faces increasing challenges, including high transportation costs, low distribution efficiency, and unstable distribution networks. To address these issues, this study focuses on optimizing enterprise logistics distribution using a double-layer (DL) model. In this paper, we propose a DL model for optimizing enterprise logistics distribution. The DL model is designed to find the optimal solution using the particle swarm optimization (PSO) algorithm. By leveraging location data from the region, the DL model evaluates and compares alternative distribution centers to determine the most efficient distribution strategy. The results demonstrate that the DL site selection model developed in this study effectively addresses the tasks of logistics center location and distribution optimization among alternative distribution centers. Comparison tests reveal that the distribution path proposed by the DL model is more accessible and cost-effective compared to alternative approaches.

This study employs a novel Markov jump system model to address complexities and uncertainties in modern logistics management, particularly in supply chain logistics information networks. It... Show More

This study employs a novel Markov jump system model to address complexities and uncertainties in modern logistics management, particularly in supply chain logistics information networks. It introduces dynamic memory to tackle issues in traditional static networks, enabling modeling and control of this intricate system. By assessing decision node importance, a novel strategy optimization method is devised. Through information exchange and decision adjustments among cooperating nodes, the overall decision system performance is enhanced, resulting in a comprehensive logistics information coordination mechanism for production supply chains based on the Markov jump system. The research demonstrates that this approach considers node interactions and information exchange, using dynamic memory to improve system adaptability and robustness, ultimately enhancing overall decision performance and stability. This has practical value for decision support and system optimization in production supply chain logistics information networks, offering fresh insights into Markov jump system control.

The existing big data analytics measures were developed without considering the cultural dimensions of developing countries. This research aims to develop and validate measures for big data Vs and... Show More

The existing big data analytics measures were developed without considering the cultural dimensions of developing countries. This research aims to develop and validate measures for big data Vs and cultural big data analytics and study their impacts on the developing countries' big data value proposition. Following MacKenzie's and Shiau and Huang's scale development procedures, data was collected twice from individuals in a developing country to refine the scale and reexamine its properties. PLS methods were used to study the impacts of big data Vs and cultural big data analytics on the value proposition. The findings revealed that big data analytics snobbism and conformism positively impact big data value proposition. Similarly, big data volume, velocity, and variety positively impact the value proposition. Paradoxically, big data veracity and variability do not significantly affect the value proposition. Surprisingly, big data analytics fatalism negatively impacts the value proposition. Theoretical and practical contributions were offered.

This paper introduces the ISSA-BiLSTM-TPA model to improve financial investment decision-making. Traditional deep learning models face limitations in handling the complexity and uncertainty of... Show More

This paper introduces the ISSA-BiLSTM-TPA model to improve financial investment decision-making. Traditional deep learning models face limitations in handling the complexity and uncertainty of financial markets. Our approach incorporates attention mechanisms, Bidirectional Long Short-Term Memory (BiLSTM), and Temporal Pattern Attention (TPA) to enhance accuracy in modeling and forecasting financial time series. The attention mechanism focuses on crucial information, BiLSTM captures bidirectional dependencies, and TPA identifies optimal solutions. Experimental results show higher prediction accuracy compared to traditional models, offering more reliable decision support for financial practitioners. Continuous optimization aims to provide innovative decision-making tools for the finance industry, advancing deep learning technology in finance.

Predicting financial market volatility is essential for investors and risk management. This study proposes a dynamic prediction model for financial asset volatility, with a Bi-directional Recurrent... Show More

Predicting financial market volatility is essential for investors and risk management. This study proposes a dynamic prediction model for financial asset volatility, with a Bi-directional Recurrent Neural Network (Bi-RNN) utilized to cleverly address market complexity. Our framework integrates Bi-RNN and gated recurrent units (GRU) to perform global optimization via particle swarm optimization algorithm (PSO). Bi-RNN combines historical data and future expectations, while GRU effectively solves long-term dependency issues through a gating mechanism, which enhances model generalization. Experimental results show that the model exhibits significant performance advantages on different financial datasets, along with strong learning and generalization capabilities superior to traditional methods. This research provides advanced and practical solutions for financial asset fluctuation prediction and is of positive significance for the greater accuracy of investment decisions and risk mitigation.