Search results

Accounting information systems are mainly rule-based, and data are usually available and well-structured. However, many accounting systems are yet to catch up with current technological developments. Thus, artificial intelligence (AI) in financial accounting is often applied only in pilot projects. Using AI-based forecasts in accounting enables proactive management and detailed analysis. However, thus far, there is little knowledge about which prediction models have already been evaluated for accounting problems. Given this lack of research, our study aims to summarize existing findings on how AI is used for forecasting purposes in financial accounting. Therefore, the authors aim to provide a comprehensive overview and agenda for future researchers to gain more generalizable knowledge.

The authors identify existing research on AI-based forecasting in financial accounting by conducting a systematic literature review. For this purpose, the authors used Scopus and Web of Science as scientific databases. The data collection resulted in a final sample size of 47 studies. These studies were analyzed regarding their forecasting purpose, sample size, period and applied machine learning algorithms.

The authors identified three application areas and presented details regarding the accuracy and AI methods used. Our findings show that sociotechnical and generalizable knowledge is still missing. Therefore, the authors also develop an open research agenda that future researchers can address to enable the more frequent and efficient use of AI-based forecasts in financial accounting.

Owing to the rapid development of AI algorithms, our results can only provide an overview of the current state of research. Therefore, it is likely that new AI algorithms will be applied, which have not yet been covered in existing research. However, interested researchers can use our findings and future research agenda to develop this field further.

Given the high relevance of AI in financial accounting, our results have several implications and potential benefits for practitioners. First, the authors provide an overview of AI algorithms used in different accounting use cases. Based on this overview, companies can evaluate the AI algorithms that are most suitable for their practical needs. Second, practitioners can use our results as a benchmark of what prediction accuracy is achievable and should strive for. Finally, our study identified several blind spots in the research, such as ensuring employee acceptance of machine learning algorithms in companies. However, companies should consider this to implement AI in financial accounting successfully.

To the best of our knowledge, no study has yet been conducted that provided a comprehensive overview of AI-based forecasting in financial accounting. Given the high potential of AI in accounting, the authors aimed to bridge this research gap. Moreover, our cross-application view provides general insights into the superiority of specific algorithms.

The Chinese housing market has witnessed rapid growth during the past decade and the significance of housing price forecasting has undoubtedly elevated, becoming an important issue to investors and policymakers. This study aims to examine neural networks (NNs) for office property price index forecasting from 10 major Chinese cities for July 2005–April 2021.

The authors aim at building simple and accurate NNs to contribute to pure technical forecasts of the Chinese office property market. To facilitate the analysis, the authors explore different model settings over algorithms, delays, hidden neurons and data-spitting ratios.

The authors reach a simple NN with three delays and three hidden neurons, which leads to stable performance of about 1.45% average relative root mean square error across the 10 cities for the training, validation and testing phases.

The results could be used on a standalone basis or combined with fundamental forecasts to form perspectives of office property price trends and conduct policy analysis.

This study aims to examine the effects of cross-flow and multiple jet impingement on conductive panel cooling performance when subjected to uniform magnetic field effects. The cooling system has double rotating cylinders.

Cross-flow ratios (CFR) ranging from 0.1 to 1, magnetic field strength (Ha) ranging from 0 to 50 and cylinder rotation speed (Rew) ranging from −5,000 to 5,000 are the relevant parameters that are included in the numerical analysis. Finite element method is used as solution technique. Radial basis networks are used for the prediction of average Nusselt number (Nu), average surface temperature of the panel and temperature uniformity effects when varying the impacts of cross-flow, magnetic field and rotations of the double cylinder in the cooling channel.

The effect of CFR on cooling efficiency and temperature uniformity is favorable. By raising the CFR to the highest value under the magnetic field, the average Nu can rise by up to 18.6%, while the temperature drop and temperature difference are obtained as 1.87°C and 3.72°C. Without cylinders, magnetic field improves the cooling performance, while average Nu increases to 4.5% and 8.8% at CR = 0.1 and CR = 1, respectively. When the magnetic field is the strongest with cylinders in channel at CFR = 1, temperature difference (ΔT) is obtained as 2.5 °C. The rotational impacts on thermal performance are more significant when the cross-flow effects are weak (CFR = 0.1) compared to when they are substantial (CFR = 1). Cases without a cylinder have the worst performance for both weak and severe cross-flow effects, whereas using two rotating cylinders increases cooling performance and temperature uniformity for the conductive panel. The average surface temperature lowers by 1.2°C at CFR = 0.1 and 0.5°C at CFR = 1 when the worst and best situations are compared.

The outcomes are relevant in the design and optimization-based studies for electric cooling, photo-voltaic cooling and battery thermal management.

This study aimed to improve the financing credit evaluation for small and medium-sized real estate enterprises (SMREEs). A financing credit evaluation model was proposed, and a blockchain-driven financing credit evaluation framework was designed to improve the transparency, credibility and applicability of the financing credit evaluation process.

The design science research methodology was adopted to identify the main steps in constructing the financing credit model and blockchain-driven framework. The fuzzy analytic hierarchy process (FAHP)–entropy weighting method (EWM)–set pair analysis (SPA) method was used to design a financing credit evaluation model. Moreover, the proposed framework was validated using data acquired from actual cases.

The results indicate that: (1) the proposed blockchain-driven financing credit evaluation framework can effectively realize a transparent evaluation process compared to the traditional financing credit evaluation system. (2) The proposed model has high effectiveness and can achieve efficient credit ranking, reflect SMREEs' credit status and help improve credit rating.

This study proposes a financing credit evaluation model of SMREEs based on the FAHP–EWM–SPA method. All credit rating data and evaluation process data are immediately stored in the proposed blockchain framework, and the immutable and traceable nature of blockchain enhances trust between nodes, improving the reliability of the financing credit evaluation process and results. In addition, this study partially fulfills the lack of investigations on blockchain adoption for SMREEs' financing credit.

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.

Quadrotors have been applied in various fields. However, because the quadrotor is subject to multiple disturbances, consisting of external disturbances, actuator faults and parameter uncertainties, it is difficult to control the unmanned aerial vehicle (UAV) to achieve high-precision tracking performance. This paper aims to design a safety controller that uses observer and neural network method to improve the tracking performance of UAV under multiple disturbances. The experiments prove that this method is effective.

First, to actively estimate and compensate the synthetic uncertainties of the system, a finite-time extended state observer is investigated, and the disturbances are transformed into the extended state of the system for estimation. Second, an adaptive neural network controller that does not accurately require the dynamic model knowledge is designed based on the estimated value, where the weights of the neural network can be dynamically adjusted by the adaptive law. Furthermore, the finite-time bounded convergence of the proposed observer and the stability of the system are proved through homogeneous theory and Lyapunov method.

The figure-“8” climbing flight simulation and real flight experiments illustrate that the proposed safety control strategy has good tracking performance.

This paper proposes the safety control structure of the UAV, which combines the extended state observer with the neural network method. Numerical simulation results and actual flight experiments demonstrate the effectiveness of the proposed control strategy.

For policymakers and participants of financial markets, predictions of trading volumes of financial indices are important issues. This study aims to address such a prediction problem based on the CSI300 nearby futures by using high-frequency data recorded each minute from the launch date of the futures to roughly two years after constituent stocks of the futures all becoming shortable, a time period witnessing significantly increased trading activities.

In order to answer questions as follows, this study adopts the neural network for modeling the irregular trading volume series of the CSI300 nearby futures: are the research able to utilize the lags of the trading volume series to make predictions; if this is the case, how far can the predictions go and how accurate can the predictions be; can this research use predictive information from trading volumes of the CSI300 spot and first distant futures for improving prediction accuracy and what is the corresponding magnitude; how sophisticated is the model; and how robust are its predictions?

The results of this study show that a simple neural network model could be constructed with 10 hidden neurons to robustly predict the trading volume of the CSI300 nearby futures using 1–20 min ahead trading volume data. The model leads to the root mean square error of about 955 contracts. Utilizing additional predictive information from trading volumes of the CSI300 spot and first distant futures could further benefit prediction accuracy and the magnitude of improvements is about 1–2%. This benefit is particularly significant when the trading volume of the CSI300 nearby futures is close to be zero. Another benefit, at the cost of the model becoming slightly more sophisticated with more hidden neurons, is that predictions could be generated through 1–30 min ahead trading volume data.

The results of this study could be used for multiple purposes, including designing financial index trading systems and platforms, monitoring systematic financial risks and building financial index price forecasting.

This study aims to review recent advances towards the implementation of ANN and NLP applications during the budgeting phase of the construction process. During this phase, construction companies must assess the scope of each task and map the client’s expectations to an internal database of tasks, resources and costs. Quantity surveyors carry out this assessment manually with little to no computer aid, within very austere time constraints, even though these results determine the company’s bid quality and are contractually binding.

This paper seeks to compile applications of machine learning (ML) and natural language processing in the architectural engineering and construction sector to find which methodologies can assist this assessment. The paper carries out a systematic literature review, following the preferred reporting items for systematic reviews and meta-analyses guidelines, to survey the main scientific contributions within the topic of text classification (TC) for budgeting in construction.

This work concludes that it is necessary to develop data sets that represent the variety of tasks in construction, achieve higher accuracy algorithms, widen the scope of their application and reduce the need for expert validation of the results. Although full automation is not within reach in the short term, TC algorithms can provide helpful support tools.

Given the increasing interest in ML for construction and recent developments, the findings disclosed in this paper contribute to the body of knowledge, provide a more automated perspective on budgeting in construction and break ground for further implementation of text-based ML in budgeting for construction.

The objective of this paper is to evaluate whether the data from consignors, logistics service providers (LSPs) and consignees contribute to the prediction of air transport shipment delays in a machine learning application.

The research database contained 2,244 air freight intercontinental shipments to 4 automotive production plants in Latin America. Different algorithm classes were tested in the knowledge discovery in databases (KDD) process: support vector machine (SVM), random forest (RF), artificial neural networks (ANN) and k-nearest neighbors (KNN).

Shipper, consignee and LSP data attribute selection achieved 86% accuracy through the RF algorithm in a cross-validation scenario after a combined class balancing procedure.

These findings expand the current literature on machine learning applied to air freight delay management, which has mostly focused on weather, airport structure, flight schedule, ground delay and congestion as explanatory attributes.