Search results

Deep learning (DL) is a new and relatively unexplored field that finds immense applications in many industries, especially ones that must make detailed observations, inferences and predictions based on extensive and scattered datasets. The purpose of this paper is to answer the following questions: (1) To what extent has DL penetrated the research being done in finance? (2) What areas of financial research have applications of DL, and what quality of work has been done in the niches? (3) What areas still need to be explored and have scope for future research?

This paper employs bibliometric analysis, a potent yet simple methodology with numerous applications in literature reviews. This paper focuses on citation analysis, author impacts, relevant and vital journals, co-citation analysis, bibliometric coupling and co-occurrence analysis. The authors collected 693 articles published in 2000–2022 from journals indexed in the Scopus database. Multiple software (VOSviewer, RStudio (biblioshiny) and Excel) were employed to analyze the data.

The findings reveal significant and renowned authors' impact in the field. The analysis indicated that the application of DL in finance has been on an upward track since 2017. The authors find four broad research areas (neural networks and stock market simulations; portfolio optimization and risk management; time series analysis and forecasting; high-frequency trading) with different degrees of intertwining and emerging research topics with the application of DL in finance. This article contributes to the literature by providing a systematic overview of the DL developments, trajectories, objectives and potential future research topics in finance.

The findings of this paper act as a guide for literature review for anyone interested in doing research in the intersection of finance and DL. The article also explores multiple areas of research that have yet to be studied to a great extent and have abundant scope.

Very few studies have explored the applications of machine learning (ML), namely, DL in finance, which is a much more specialized subset of ML. The authors look at the problem from the aspect of different techniques in DL that have been used in finance. This is the first qualitative (content analysis) and quantitative (bibliometric analysis) assessment of current research on DL in finance.

This study aims to compare machine learning models, datasets and splitting training-testing using data mining methods to detect financial statement fraud.

This study uses a quantitative approach from secondary data on the financial reports of companies listed on the Indonesia Stock Exchange in the last ten years, from 2010 to 2019. Research variables use financial and non-financial variables. Indicators of financial statement fraud are determined based on notes or sanctions from regulators and financial statement restatements with special supervision.

The findings show that the Extremely Randomized Trees (ERT) model performs better than other machine learning models. The best original-sampling dataset compared to other dataset treatments. Training testing splitting 80:10 is the best compared to other training-testing splitting treatments. So the ERT model with an original-sampling dataset and 80:10 training-testing splitting are the most appropriate for detecting future financial statement fraud.

This study can be used by regulators, investors, stakeholders and financial crime experts to add insight into better methods of detecting financial statement fraud.

This study proposes a machine learning model that has not been discussed in previous studies and performs comparisons to obtain the best financial statement fraud detection results. Practitioners and academics can use findings for further research development.

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.

This study focuses on the classification of targets with varying shapes using radar cross section (RCS), which is influenced by the target’s shape. This study aims to develop a robust classification method by considering an incident angle with minor random fluctuations and using a physical optics simulation to generate data sets.

The approach involves several supervised machine learning and classification methods, including traditional algorithms and a deep neural network classifier. It uses histogram-based definitions of the RCS for feature extraction, with an emphasis on resilience against noise in the RCS data. Data enrichment techniques are incorporated, including the use of noise-impacted histogram data sets.

The classification algorithms are extensively evaluated, highlighting their efficacy in feature extraction from RCS histograms. Among the studied algorithms, the K-nearest neighbour is found to be the most accurate of the traditional methods, but it is surpassed in accuracy by a deep learning network classifier. The results demonstrate the robustness of the feature extraction from the RCS histograms, motivated by mm-wave radar applications.

This study presents a novel approach to target classification that extends beyond traditional methods by integrating deep neural networks and focusing on histogram-based methodologies. It also incorporates data enrichment techniques to enhance the analysis, providing a comprehensive perspective for target detection using RCS.

With the rapid growth of the domestic lending industry, assessing whether the borrower of each loan is at risk of default is a pressing issue for financial institutions. Although there are some models that can handle such problems well, there are still some shortcomings in some aspects. The purpose of this paper is to improve the accuracy of credit assessment models.

In this paper, three different stages are used to improve the classification performance of LSTM, so that financial institutions can more accurately identify borrowers at risk of default. The first approach is to use the K-Means-SMOTE algorithm to eliminate the imbalance within the class. In the second step, ResNet is used for feature extraction, and then two-layer LSTM is used for learning to strengthen the ability of neural networks to mine and utilize deep information. Finally, the model performance is improved by using the IDWPSO algorithm for optimization when debugging the neural network.

On two unbalanced datasets (category ratios of 700:1 and 3:1 respectively), the multi-stage improved model was compared with ten other models using accuracy, precision, specificity, recall, G-measure, F-measure and the nonparametric Wilcoxon test. It was demonstrated that the multi-stage improved model showed a more significant advantage in evaluating the imbalanced credit dataset.

In this paper, the parameters of the ResNet-LSTM hybrid neural network, which can fully mine and utilize the deep information, are tuned by an innovative intelligent optimization algorithm to strengthen the classification performance of the model.

This paper aims to propose a new deep learning technique to detect the type of material to improve automated construction quality monitoring.

A new data augmentation approach that has improved the model robustness against different illumination conditions and overfitting is proposed. This study uses data augmentation at test time and adds outlier samples to training set to prevent over-fitted network training. For data augmentation at test time, five segments are extracted from each sample image and fed to the network. For these images, the network outputting average values is used as the final prediction. Then, the proposed approach is evaluated on multiple deep networks used as material classifiers. The fully connected layers are removed from the end of the networks, and only convolutional layers are retained.

The proposed method is evaluated on recognizing 11 types of building materials which include 1,231 images taken from several construction sites. Each image resolution is 4,000 × 3,000. The images are captured with different illumination and camera positions. Different illumination conditions lead to trained networks that are more robust against various environmental conditions. Using VGG16 model, an accuracy of 97.35% is achieved outperforming existing approaches.

It is believed that the proposed method presents a new and robust tool for detecting and classifying different material types. The automated detection of material will aid to monitor the quality and see whether the right type of material has been used in the project based on contract specifications. In addition, the proposed model can be used as a guideline for performing quality control (QC) in construction projects based on project quality plan. It can also be used as an input for automated progress monitoring because the material type detection will provide a critical input for object detection.

Several studies have been conducted to perform quality management, but there are some issues that need to be addressed. In most previous studies, a very limited number of material types were examined. In addition, although some studies have reported high accuracy to detect material types (Bunrit et al., 2020), their accuracy is dramatically reduced when they are used to detect materials with similar texture and color. In this research, the authors propose a new method to solve the mentioned shortcomings.

Coal is a critical global energy source, and fluctuations in its price significantly impact related enterprises' profitability. This study aims to develop a robust model for predicting the coal price index to enhance coal purchase strategies for coal-consuming enterprises and provide crucial information for global carbon emission reduction.

The proposed coal price forecasting system combines data decomposition, semi-supervised feature engineering, ensemble learning and deep learning. It addresses the challenge of merging low-resolution and high-resolution data by adaptively combining both types of data and filling in missing gaps through interpolation for internal missing data and self-supervision for initiate/terminal missing data. The system employs self-supervised learning to complete the filling of complex missing data.

The ensemble model, which combines long short-term memory, XGBoost and support vector regression, demonstrated the best prediction performance among the tested models. It exhibited superior accuracy and stability across multiple indices in two datasets, namely the Bohai-Rim steam-coal price index and coal daily settlement price.

The proposed coal price forecasting system stands out as it integrates data decomposition, semi-supervised feature engineering, ensemble learning and deep learning. Moreover, the system pioneers the use of self-supervised learning for filling in complex missing data, contributing to its originality and effectiveness.

Taking into consideration the current human need for agricultural produce such as rice that requires water for growth, the optimal consumption of this valuable liquid is important. Unfortunately, the traditional use of water by humans for agricultural purposes contradicts the concept of optimal consumption. Therefore, designing and implementing a mechanized irrigation system is of the highest importance. This system includes hardware equipment such as liquid altimeter sensors, valves and pumps which have a failure phenomenon as an integral part, causing faults in the system. Naturally, these faults occur at probable time intervals, and the probability function with exponential distribution is used to simulate this interval. Thus, before the implementation of such high-cost systems, its evaluation is essential during the design phase.

The proposed approach included two main steps: offline and online. The offline phase included the simulation of the studied system (i.e. the irrigation system of paddy fields) and the acquisition of a data set for training machine learning algorithms such as decision trees to detect, locate (classification) and evaluate faults. In the online phase, C5.0 decision trees trained in the offline phase were used on a stream of data generated by the system.

The proposed approach is a comprehensive online component-oriented method, which is a combination of supervised machine learning methods to investigate system faults. Each of these methods is considered a component determined by the dimensions and complexity of the case study (to discover, classify and evaluate fault tolerance). These components are placed together in the form of a process framework so that the appropriate method for each component is obtained based on comparison with other machine learning methods. As a result, depending on the conditions under study, the most efficient method is selected in the components. Before the system implementation phase, its reliability is checked by evaluating the predicted faults (in the system design phase). Therefore, this approach avoids the construction of a high-risk system. Compared to existing methods, the proposed approach is more comprehensive and has greater flexibility.

By expanding the dimensions of the problem, the model verification space grows exponentially using automata.

Unlike the existing methods that only examine one or two aspects of fault analysis such as fault detection, classification and fault-tolerance evaluation, this paper proposes a comprehensive process-oriented approach that investigates all three aspects of fault analysis concurrently.

In this study, the central objective is to foresee stock market signals with the use of a proper structure to achieve the highest accuracy possible. For this purpose, three hybrid models have been developed for the stock markets which are a combination of support vector machine (SVM) with meta-heuristic algorithms of particle swarm optimization (PSO), imperialist competition algorithm (ICA) and genetic algorithm (GA).All the analyses are technical and are based on the Japanese candlestick model.

Further as per the results achieved, the most suitable algorithm is chosen to anticipate sell and buy signals. Moreover, the authors have compared the results of the designed model validations in this study with basic models in three articles conducted in the past years. Therefore, SVM is examined by PSO. It is used as a classification agent to search the problem-solving space precisely and at a faster pace. With regards to the second model, SVM and ICA are tested to stock market timing, in a way that ICA is used as an optimization agent for the SVM parameters. At last, in the third model, SVM and GA are studied, where GA acts as an optimizer and feature selection agent.

As per the results, it is observed that all new models can predict accurately for only 6 days; however, in comparison with the confusion matrix results, it is observed that the SVM-GA and SVM-ICA models have correctly predicted more sell signals, and the SCM-PSO model has correctly predicted more buy signals. However, SVM-ICA has shown better performance than other models considering executing the implemented models.

In this study, the data for stock market of the years 2013–2021 were analyzed; the long length of timeframe makes the input data analysis challenging as they must be moderated with respect to the conditions where they have been changed.

In this study, two methods have been developed in a candlestick model; they are raw-based and signal-based approaches in which the hit rate is determined by the percentage of correct evaluations of the stock market for a 16-day period.

This study explores the pioneering approach of utilising machine learning (ML) models and integrating social media data for predicting tourist arrivals in Sri Lanka.

Two sets of experiments are performed in this research. First, the predictive accuracy of three ML models, support vector regression (SVR), random forest (RF) and artificial neural network (ANN), is compared against the seasonal autoregressive integrated moving average (SARIMA) model using historical tourist arrivals as features. Subsequently, the impact of incorporating social media data from TripAdvisor and Google Trends as additional features is investigated.

The findings reveal that the ML models generally outperform the SARIMA model, particularly from 2019 to 2021, when several unexpected events occurred in Sri Lanka. When integrating social media data, the RF model performs significantly better during most years, whereas the SVR model does not exhibit significant improvement. Although adding social media data to the ANN model does not yield superior forecasts, it exhibits proficiency in capturing data trends.

The findings offer substantial implications for the industry's growth and resilience, allowing stakeholders to make accurate data-driven decisions to navigate the unpredictable dynamics of Sri Lanka's tourism sector.

This study presents the first exploration of ML models and the integration of social media data for forecasting Sri Lankan tourist arrivals, contributing to the advancement of research in this domain.