International Journal of Business Intelligence and Data Mining (10 papers in press)

Regular Issues

• Financial risk monitoring and warning method of listed enterprises based on data mining  
  by Xinyan Zhang 
  Abstract: To address the issues of low accuracy in traditional methods for enterprise financial data mining, significant discrepancies between financial risk monitoring results and reality, and low accuracy in risk warning, a data mining-based financial risk monitoring and warning method for listed companies was designed. Firstly, grey relational clustering is used to mine financial data of listed companies. Then, factor analysis and fuzzy recognition matrix are combined to identify financial risks of listed companies. Finally, XGboost algorithm is used to divide financial risks of listed companies. Support vector machine is used to build a financial risk warning decision function for listed companies, achieving financial risk monitoring and warning for listed companies. The experimental results show that the financial risk monitoring results of this method are consistent with the true values, and the data mining accuracy can reach up to 98.23%, with a risk warning accuracy of over 95%. It has a good effect on enterprise financial risk monitoring and warning, and has high application value.
  Keywords: data mining; listed companies; financial risk; monitoring and warning; grey relational clustering; support vector machine.
  DOI: 10.1504/IJBIDM.2025.10066153
   
  

Special Issue on: Methods and Applications of Data Mining in Business Domains II

• Online teaching data distribution method based on learning behaviour big data mining  
  by Jing Chang 
  Abstract: To overcome the problems of low accuracy and recall of traditional online teaching data distribution methods, this paper proposes an online teaching data distribution method based on learning behaviour big data mining. Firstly, collect online teaching data and pre-process the distribution data; then, generate online teaching data distribution rules through triangular fuzzy clustering; finally, based on the learning behaviour big data mining method, the data is divided into fuzzy metrics, membership functions are established to update distribution rules, and big data mining is used to design data distribution schemes. The experimental results show that the distribution accuracy of our method can reach 99.89%, and the parameter recall rate can reach 97.89%. The actual results are in line with the expected results and have a good distribution effect.
  Keywords: learning behaviour; big data mining; online teaching; data distribution.
  DOI: 10.1504/IJBIDM.2025.10065173
   
  
• Enterprise financial risk early warning method based on PCA and SVM algorithms  
  by Yanyan Cao, Gechun Pei 
  Abstract: Aiming at the problems of low relevance and high false alarm rate of enterprise financial risk early warning, an enterprise financial risk early warning method based on PCA and SVM algorithm is proposed. Firstly, the sensitivity optimisation principal component analysis method is introduced, and the representative index is selected according to the threshold value to establish the index system. Then, support vector machine is introduced to store the data in the sample space, and the indicators are divided into positive and negative indicators. Finally, combined with FCM clustering algorithm, the early-warning decision function is constructed to realise the early-warning of enterprise financial risk. The experimental results show that the correlation of this method is higher than 0.915, the false alarm rate is lower than 2%, and the Matthews correlation coefficient is up to 1.00.
  Keywords: principal component analysis; PCA; support vector machine; SVM; corporate financial risks; risk warning; FCM clustering algorithm.
  DOI: 10.1504/IJBIDM.2025.10065576
   
  
• An English learning behaviour data mining based on improved ensemble learning algorithm  
  by Lin Fan, Pengqi Cao, Yunxia Du 
  Abstract: In order to enhance the learning effectiveness of English learners, this paper proposes an English learning behaviour data mining method based on improved ensemble learning algorithm. A web crawler is used to collect behavioural information of learners during the process of learning English, and learner profiles are constructed. The data is pre-processed, and collaborative filtering algorithms are employed to extract features of English learning behaviours. By treating English learning behaviour features as input vectors and data mining results as output vectors, an improved stacking ensemble learning model based on chain rules is constructed. This model is utilised to obtain data mining results for English learning behaviour. The experimental results show that the normalised difference accuracy of the proposed method is always above 90%, and the mAP value is always above 93%, indicating that the proposed method has high accuracy and good mining effect in English learning behaviour data mining.
  Keywords: ensemble learning; English learning; learning behaviour; data mining; chain rules; stacking ensemble learning model.
  DOI: 10.1504/IJBIDM.2025.10065187
   
  
• Web server log data pre-processing for mining zakat user profile using association rules  
  by Mohamad Farhan Mohamad Moshin, Wan Hussain Wan Ishak, Yuhanis Yusof, Jastini Mohd Jamil, Alwi Ahmad 
  Abstract: The internet’s transformative impact on businesses and marketing strategies underscores the pivotal role of websites in establishing credibility and disseminating information to customers. To measure website effectiveness, tracking visitor behaviour is essential. This study focuses on web log data from Lembaga Zakat Negeri Kedah (LZNK), a Malaysian government institution managing zakat which utilises web analytics and mining to gain insights into website usage. The objectives of this paper are two-fold: firstly, to detail the pre-processing of weblog data to ensure reliability for data mining. Secondly is to employ association rule mining to extract user patterns from pre-processed weblog data. To achieve this, the web logs were obtained from the LZNK’s website spanning from 2016 to November 2020 with a focus on user access in 2020. The findings reveal critical aspects of user behaviour including the most visited pages, popular page combinations, user interests, relationships between pages, and the impact of the entry page. Implementing these insights can enhance the LZNK website’s usability, user satisfaction, and highlighting the importance of adapting to evolving user preferences and technological advancements.
  Keywords: association rule; data pre-processing; user profile; web log; web mining.
  DOI: 10.1504/IJBIDM.2025.10065199
   
  
• Assessing ensemble techniques for imbalanced classification  
  by Eric P. Jiang 
  Abstract: Class imbalance represents a pervasive and challenging problem in machine learning and manifests in a wide range of real-world applications, where the distribution of data across different classes is highly skewed. Conventional machine learning algorithms tend to favour majority classes, often resulting in a failure to capture data patterns of minority classes. This bias can lead to undesirable outcomes in practice. This paper addresses the problem of class imbalance by conducting a comprehensive comparative study of various hybrid ensemble approaches that demonstrate promise in mitigating this learning issue. The study encompasses extensive experiments conducted on a diverse collection of datasets gathered from multiple application domains and characterised by a wide range of class imbalance ratios. To facilitate a comprehensive performance assessment of these methods in dealing with imbalanced data, we have deployed a combination of relevant and commonly used performance metrics and additionally, we have leveraged multiple non-parametric statistical tests to evaluate, analyse and compare the results obtained from the selected methods. By doing so, we aim to offer practical insights into which particular methods are better suited for specific contexts, thus aiding practitioners in selecting the appropriate approaches to address class imbalance in their machine learning tasks.
  Keywords: learning from imbalanced data; data rebalancing; ensemble learning; performance evaluation and comparison.
  DOI: 10.1504/IJBIDM.2025.10065924
   
  
• Comprehensive evaluation method of enterprise financial risk based on fuzzy grey correlation analysis  
  by Xuena Lin, Guijun Shang 
  Abstract: In this paper, a comprehensive evaluation method of enterprise financial risk based on fuzzy grey correlation analysis is proposed. Firstly, the comprehensive evaluation index system of enterprise financial risk is constructed, and the comprehensive evaluation index of risk is differentiated according to the judgment matrix. Then, based on fuzzy grey relational analysis, a judgment matrix is constructed to determine the weight of financial risk indicators. Finally, optimise the comprehensive evaluation sub-node to realise the comprehensive evaluation of enterprise financial risk. The experimental results show that the graphic area enclosed by PR curve, X-axis and Y-axis is close to 1, the financial health index is above 80%, and the false alarm rate is below 15%, which has good evaluation performance.
  Keywords: fuzzy grey correlation analysis; enterprise financial risk; comprehensive evaluation; evaluation index system; financial health index.
  DOI: 10.1504/IJBIDM.2025.10066018
   
  
• Online allocation of network learning resources based on parallel cluster mining  
  by Zhaofeng Li, Ping Hu, Pei Zhang, Liwei Zhang 
  Abstract: In order to solve the problem of low accuracy and consideration of online allocation of existing network learning resources, this paper proposes a network learning resource online allocation method based on parallel clustering mining. Firstly, analyse the development stages of online learning resources and collect data on educational resources; secondly, construct a network learning resource model and utilise parallel clustering to explore the clustering features of network learning resources; finally, using the mined resource features, design network learning resource labels to achieve online allocation of network learning resources. The experimental results show that the accuracy of network learning resource allocation in this method is 98.2%, the accuracy of network learning resource allocation is 98.1%, and the reliability of allocation reaches 96.2%.
  Keywords: parallel clustering mining; online allocation of learning resources; resource tags; education resource data.
  DOI: 10.1504/IJBIDM.2025.10066019
   
  
• Study on complement of knowledge map of educational resources based on semi-supervised learning  
  by Wei Liu 
  Abstract: In order to improve the effectiveness of completing educational resource knowledge graphs, a complement method of knowledge map of educational resources based on semi-supervised learning is studied. The relationship path features of the education resource knowledge graph are extracted using a path sorting algorithm. Within the interactive connection graph attention network of the semi-supervised deep learning algorithm, the embedding vectors of the knowledge graph are inputted to obtain the encoded representation of contextual features for the embedding vector entities, and the encoded feature matrix is constructed. The semantic matching model tensor decomposition is used to encode the feature matrix and calculate the scores for each triple. The triple with the highest score is selected as the completion result of the knowledge graph. The experimental results show that this method achieves high values in average reciprocal rank, Hits@10, Hits@3, and Hits@1, indicating a good completion effect of the knowledge graph.
  Keywords: semi-supervised learning; educational resources; knowledge map; complement method; relationship path; attention network.
  DOI: 10.1504/IJBIDM.2025.10066020
   
  
• Adaptive recommendation method for teaching resources based on knowledge graph and user similarity  
  by Meng Li 
  Abstract: To provide users with personalised and accurate teaching resource recommendation results, a new teaching resource adaptive recommendation method is proposed by effectively integrating knowledge graph with user similarity. This method first constructs a knowledge graph of teaching resources, representing the relationship between resources as a graph structure. Then, by analysing user learning history, ratings, and preferences, calculate user similarity and identify other users with higher similarity to the current user. Next, based on the resource ratings between similar users and current users, combined with the resource association relationship in the knowledge graph, the resource ratings are calculated using methods such as weighted summation. Finally, teaching resources are sorted based on resource ratings and recommended to current users. The experimental results show that the maximum root mean square error of this method is only 0.26, the highest recall rate is 95.6% and the MRR value is relatively high.
  Keywords: knowledge graph; user similarity; ICA algorithm; improve collaborative filtering algorithms; preference learning algorithm.
  DOI: 10.1504/IJBIDM.2025.10066021