Data Mining Results Research Articles

Comparison of Social Media BOT Functions Using the K-Nearest Neighbor Method Against User Satisfaction

Social media is currently an alternative medium in conveying messages in the form of news and can be used as a tool to exchange news from different places. Many people use social media to express opinions, express feelings, as well as experiences and things that can be of concern. In this study, the data processing used was the K-Nearest Neighbor Algorithm with the classification method as a media for comparing the functions of the two bots, namely the WhatsApp and Telegram bots. Using SPSS (Statistical Product and Serive Solutions) and Rapidminer as a place to perform calculations and analysis. Based on the results of testing data mining with Rapid Miner, the calculation results are obtained which will be used as information to support user satisfaction in using Social Media Bots. User satisfaction is found in WhatsApp Bot users 72.22% and Telegram Bot users 28.57%. Calculations are carried out with a data mining process obtained from the K-Nearest Neighbor algorithm to make it easier to find Bot user satisfaction on both WhatsApp and Telegram social media. The WhatsApp bot is the best choice and has several useful functions as a digital communication media tool on the Internet of Things.

Application of Neural Network Method to Determine Public Satisfaction Level on Pertalite Fuel

This research aims to analyze public interest in Pertalite fuel using the Data Mining method, specifically using the Neural Network method. The stages in this research include Data Analysis, Data Preprocessing, Designing Classification Models in Data Mining, Classification Results in Data Mining, Designing Evaluation Models in Data Mining, and Evaluation Results on Data Mining. The classification results show that of the total of 105 community data analyzed, 97 community data showed interest in Pertalite fuel, while only 8 community data showed no interest. The accuracy results obtained were 100%, indicating that the Neural Network method is very suitable and effective in classifying people's interest in Pertalite fuel. The Data Analysis process was carried out to understand and analyze the characteristics of data regarding public interest in Pertalite fuel. Data preprocessing is carried out to clean, transform and integrate data so that it is ready for the classification process. Next, the Designing Classification Models in Data Mining process is carried out to design a classification model using the Neural Network method. Classification Results in Data Mining produces information that the majority of people have an interest in Pertalite fuel. Designing Evaluation Models in Data Mining is carried out to design classification evaluation models, which then produce Evaluation Results on Data Mining which show an accuracy level of 100%. Thus, this research shows that the Neural Network method is very effective in classifying people's interest in Pertalite fuel.

Establishment and evaluation of a premenstrual syndrome rat model induced by progesterone-withdrawal and emotional-stimulation

Premenstrual syndrome(PMS) lacks a highly consistent and feasible animal model that aligns with diagnostic and therapeutic standards in both traditional Chinese medicine(TCM) and western medicine, resulting in a lack of reliable experimental carriers for studying its pathogenesis and pharmacological effects. This study aims to systematically analyze the biological implications of PMS from the perspective of the "disease-syndrome-symptom" correlation and establish preparation and evaluation methods for an improved animal model of this disease. Firstly, clinical symptom gene sets related to the Qi stagnation syndromes due to liver depression and blood stasis in PMS in both modern medicine and TCM diagnostic standards were collected through GeneCards, DisGeNET, Mala-Cards, and the System of Foundational Diagnostic Association(SoFDA) database, as well as published literature. Based on the interaction information between genes, a "disease-syndrome-symptom" correlation network of PMS was established. Based on data mining results, an improved rat model of PMS was prepared by combining chronic restraint stress with the classical progesterone-withdrawal mo-del to simulate emotional depression caused by external environmental stimuli during the clinical onset process, inducing pathological damage from both physiological and emotional dimensions. The evaluation of the improved model before and after modification included open field experiment scores, organ indices, ovarian pathological changes, serum levels of estradiol(E_2), follicle-stimulating hormone/luteinizing hormone(FSH/LH), 5-hydroxytryptamine(5-HT), dopamine(DA), norepinephrine(NE), as well as coagulation parameters and hemorheology indexes. By calculating the degree, betweenness, and closeness centrality of nodes in the "disease-syndrome-symptom" correlation network, 163 core genes with topological importance were identified. Further biological function mining results indicated that core genes in PMS mainly participated in the regulation of the "nervous-endocrine-immune" system and pathways related to circulatory disorders. Mapping analysis of clinical phenotype symptom gene sets suggested significant correlations between core genes in PMS and depressive symptoms and pain symptoms caused by blood stasis. Compared with the simple progesterone withdrawal model, rats subjected to combined injections and restraint stress showed more significant abnormalities in open field experiment scores, ovarian tissue pathology, serum neurotransmitter levels of 5-HT and DA, as well as serum hormone levels of E_2 and FSH/LH. The modified modeling conditions exacerbated the pathological changes in blood rheology, coagulation function, and red blood cell morphology in model rats, confirming that the improved rat model could characterize the "nervous-endocrine-immune" system disorder and circulatory system disorders in the occurrence and progression of PMS, consistent with the clinical diagnostic and therapeutic standards of both TCM and western medicine. The establishment of the improved rat model of PMS can provide a reliable experimental carrier for elucidating the pathogenesis of PMS and discovering and evaluating therapeutic drugs. It also provides references for objectively reflecting the clinical characteristics of PMS in TCM and western medicine and precision treatment.

Optimization of parallel SVM algorithm for big data

Parallel Support Vector Machine (SVM) based on big data has achieved some results in data mining, but due to the complexity of the data itself and a large amount of noisy data, its execution efficiency and classification accuracy in the big data environment are very low. In order to eliminate noise, a noise reduction method based on Noise Cleaning (NC) strategy was proposed, and redundant training samples in big data environments were deleted; Introduce an improved Artificial Fish Swarm Algorithm (IAFSA) to obtain the final Parallel SVM algorithm using mutual information and artificial fish swarm algorithm based on MapReduce (MIAFSA-PSVM) classification model. The results indicate that when compared to CMI-PSVM, the execution time of MIAFSA-PSVM algorithm is higher on the NDC dataset with the largest data size, The SVM parameter optimization algorithm based on MapReduce and cuckoo search (CSSVM-MR) and the particle swarm optimization based parallel support vector machine ensemble algorithm (PSO-PSVM) decreased by 40.1%, 79.3%, and 51.7%, respectively. This indicates that GIESVM-MR and MIAFSA-PSVM have strong adaptability to big data environments and high classification accuracy.

Abstract 4908: Comprehensive tool for pan-cancer consensus data mining of drugs, targets and biomarkers

Abstract The rapid increase in collateral omics and phenotypic data has enabled data-driven studies for the discovery of drug targets and biomarkers. For this purpose, we have developed a convenient tool, Q-omics software, for general researchers and cancer scientists to carry out customized data mining without bioinformatics background. Q-omics provides a comprehensive interface and smart functions for facilitating pan cancer-wide association studies on mutations, RNA expression, protein abundance, shRNA/CRISPR efficacy, drugs, tumor-infiltrating cells, patient survival, clinical info. etc. Furthermore, consensus scores on associated data pairs from heterogeneous samples, help to predict the reproducibility of data mining results. Q-omics (download: http://qomics.io) improves the utility of cancer omics big data for non-computational scientists at all levels of cancer research. Citation Format: Sukjoon Yoon. Comprehensive tool for pan-cancer consensus data mining of drugs, targets and biomarkers [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4908.

Step-rate-test as one of the strategies for managing formation water injection. Design and monitoring

The construction of a produced water management (PWM) system relies on a Step-rate-test strategy that integrates a novel technology for treating the bottomhole formation zone and adjacent fractures resulting from prior hydraulic fracturing. Step-rate-test technology is considered more environmentally friendly than hydraulic fracturing for several reasons. It doesn't require crosslinkers or proppants, and there is no discharge of liquids or other reagents onto the terrain or into water basins. This article discusses technical approaches to solving field service problems in injection wells. One of the strategies for managing produced water injection is Step-rate-test, which is considered the best choice in these operations. This strategy can also be used to solve the problem of disposing of excess fluid or waste after hydraulic fracturing. Advances in modelling, operation, monitoring, and evaluation provide the basis for minimising costs and preserving the environment. The connection between the object of work and the engineering works is established through quality targets and pumping requirements. Field example, such as Tevlinsko-Russkinskoye and Yuzhno-Yagunskoye, and results of data mining of them, demonstrate the significant impact of data differences on site selection. Field data indicates that injectivity decreases in matrix injection structures despite the injection of prepared fluid. It is acceptable to inject the fluid without prior preparation, provided that there is no well pad pump station, pipe end phase divider or similar equipment. The majority of rock structures become fractured during fluid injection, which affects the selection of technical equipment for the process. This article evaluates the propagation of fractures during the injection of prepared and unprepared fluids and their impact on well performance.

Research on assessment of air traffic control operation quality based on track data

AbstractEvaluating the quality of air traffic control operations is crucial for enhancing airspace management. Thus, this paper proposes a data mining approach for conducting a comprehensive assessment of control operation quality (COQ) in increasingly complex operation environments. First, the authors establish a COQ evaluation index system that combines both subjective and objective measures. Key index parameters are determined using wavelet filtering and interval estimation techniques on the basis of data mining results. Second, the authors apply an entropy‐weighted cloud model to label data samples and classify COQ into ‘excellent’, ‘good’, and ‘fair’ levels. Finally, the authors establish an support vector machine‐based COQ assessment model using XGBoost feature combinations to verify the practical feasibility and scientific validity of their approach.

Integration of single-cell and bulk RNA sequencing data reveals that CYTOR is a potential prognostic and immunotherapeutic response marker for skin cutaneous melanoma.

Skin cutaneous melanoma (SKCM) is a highly malignant tumor that is prone to immune escape and distant metastasis. Immunotherapy is considered to be the best treatment for patients with SKCM. However, not all patients benefit from it. We observed a significant differential expression of the lncRNA CYTOR in patients with SKCM based on single-cell and bulk RNA sequencing data mining results. The results showed that compared to normal tissue lncRNA CYTOR expression was significantly upregulated in SKCM tissue. Subsequently, we validated this finding in clinical samples, and we also found that the expression of lncRNA CYTOR in SKCM was higher as it progressed. lncRNA CYTOR was differentially expressed in patients who responded to immunotherapy, suggesting that it may serve as a biomarker to predict the efficacy of SKCM immunotherapy. In-depth analysis revealed that lncRNA CYTOR expression was strongly correlated with immune cell infiltration, immune response, and immune checkpoint expression. Meanwhile, our experiments revealed that CYTOR affects SKCM cell invasion and clone formation and is associated with the activation of the EMT pathway. In summary, our findings illustrate, for the first time, the value of CYTOR as a potential prognostic and immunotherapeutic response marker in SKCM.

Alice and the Caterpillar: A more descriptive null model for assessing data mining results

Alice and the Caterpillar: A more descriptive null model for assessing data mining results

Theme Song Partai sebagai Komunikasi Politik: Analisis pada Lagu "PAN PAN PAN"

Partai Amanat Nasional (PAN) released a video for a song entitled "PAN..PAN..PAN" via the PAN TV YouTube account. The PAN song is a promotion and outreach within the framework of the 2024 General Election. The song, which was first released on YouTube PAN TV, has become a viral and trending topic on social media, even getting various comments from netizens and the public. Against the background of the phenomena and problems regarding the PAN song, the study aims to analyze the PAN song using a political communication approach and study. This study specifically aims to reveal more deeply about the following two entities, namely: (1) Forms of Political Communication in PAN Songs; (2) Political Communication Messages in PAN Songs. The analysis of this PAN song is based on the theory of the Bandwagon Effect and The Communicative Function Model. This study was conducted using a qualitative descriptive analysis method. Based on the results of analysis and data mining, two main findings were obtained in this study, namely: (1) The form of political communication in PAN songs includes political communication techniques in the form of the bandwagon effect which has three main effects on audiences, namely conformity, interpersonal influence and seeking status; (2) Political communication messages in the PAN song technically use the communicative function campaign model which consists of four stages, namely surfacing, primary, nomination and election.

Classification Interest Customer XL Internet Card Using Naive Bayes Algorithm At PT XML Tronik

In the world of trade, competition within a company has become commonplace and makes business people always think about breakthroughs that can ensure the continuity of their business . Basically companies have valuable assets but are rarely used as a reference, these assets are in the form of databases with large numbers. PT.XML Tronik is a company that has been in the technology sector for a long time, one of which is selling GSM Card Providers in Indonesia. The classification method used is the Naïve Bayes Algorithm, where Naïve Bayes is used to classify statistical and probability methods . Method This research uses several stages starting from data collection , analysis sales , data processing using naïve Bayes method and proceed with measurements level accuracy use WEKA application . From the results of data mining using the Naïve Bayes Algorithm, this researcher found patterns of interest in buying XL Card customers at PT.XML Tronik . Based on the results of the analysis carried out, using 20% of the test data with negative and positive labels. So that it can produce a sign ending with an accuracy level of 84.6667% with a precision of 97% and a recall of 83%.

SbMBR Tree—A Spatiotemporal Data Indexing and Compression Algorithm for Data Analysis and Mining

In the field of data analysis and mining, adopting efficient data indexing and compression techniques to spatiotemporal data can significantly reduce computational and storage overhead for the abilities to control the volume of data and exploit the spatiotemporal characteristics. However, traditional lossy compression techniques are hardly suitable due to their inherently random nature. They often impose unpredictable damage to scientific data, which affects the results of data mining and analysis tasks that require certain precision. In this paper, we propose a similarity-based minimum bounding rectangle (SbMBR) tree, a tree-based indexing and compression method, to address the aforementioned problem. Our method can hierarchically select appropriate minimum bounding rectangles according to the given maximum acceptable errors and use the average value contained in each selected MBR to replace the original data to achieve data compression with multi-layer loss control. This paper also provides the corresponding tree construction algorithm and range query processing algorithm for the indexing structure mentioned above. To evaluate the data quality preservation in cross-domain data analysis and mining scenarios, we use mutual information as the estimation metric. Experimental results emphasize the superiority of our method over some of the typical indexing and compression algorithms.

Effects of FDI, External Trade, and Human Capital of the ICT Industry on Sustainable Development in Taiwan

Understanding how international trade, FDI and human capital (FDI-HC and ET-HC) in the ICT industry affect Taiwan’s stable economic growth between 2001 and 2020 is the main objective of this study. The empirical analysis method used in this study is mainly divided into two steps: First, it uses variables with reliability and authenticity as keywords for primary, data mining, and semantic network analysis (SNA). Second, it investigates the long- and short-term interactions between the variables using the vector error correction model (VECM). The results of data mining and SNA using FDI and ET as keywords reveal that terms connected to HC have high levels of centrality, clustering, and frequency. This finding implies that the variables FDI-HC and ET-HC are reliable and can be utilized as interaction variables. Moreover, FDI–HC and ET–HC exert positive short- and long-term influences on GDP, and ET–HC exerts strong mid- to long-term impacts on GDP, FDI–HC, and ET.

Методологические аспекты организации грузоперевозок железнодорожным транспортом в проектах развития Восточного полигона с учетом рисков инфраструктурных ограничений

Purpose: To develop a methodology for the organization of freight transportation in the project of comprehensive modernization of the Baikal-Amur Mainline (BAM) and Trans-Siberian Railway (Transsib) (Eastern polygon). Methods: The study is based on operational data of freight traffic on the railway infrastructure of the Eastern polygon of JSC "Russian Railways", their systematization and analysis. The method of in-depth analysis of structured data on the dependence of the performance indicators of the projected railway infrastructure and the passage of projected freight volumes, taking into account empty wagons, is used. Results: The methodology of regulation of the organization of freight rail transportation has been updated. The key problems, risks and restrictions of freight transportation in the Eastern polygon development project are classified. The results of statistical processing and data mining are presented, specifying the parameters of the forecast model for the growth of freight volumes and the increase in the capacity of the Eastern polygon. An algorithm has been developed for analyzing freight rail transportation in the projects of the development of the Eastern polygon, taking into account the risks of infrastructure restrictions. Practical significance: An assessment of the degree to which risks of infrastructure restrictions impact the effectiveness of the organizing freight traffic in the railway infrastructure development project is given.

Management path optimization of accordion music course education based on big data technology analysis

Abstract With the continuous development of information technology, especially the rapid development of big data technology, the coverage and effectiveness of information application and dissemination have increased substantially. With the current innovation and development of music management education mode, the traditional accordion course management mode also changed, this paper makes full use of big data technology to optimize the accordion course education management path, mainly through the construction of an accordion score database and retrieval system, the closer the data mining algorithm calculation result is to 1, it means that the data mining result is more similar to the actual result. The experimental analysis result is equal to 1, which indicates that the data mining result of this study is similar to the actual result, which is conducive to the intelligent management under the analysis of big data technology for music course education, improving students’ learning interest and passion, improving the teaching quality of learning, and facilitating the teaching management work of university leaders. And it can be further based on the big data era, grasp the trend of the big data era, and understand the level, learning needs, and personal characteristics of students, analysis can be seen that accordion course education management based on big data can make different learning plans for different levels of students, which is conducive to improving management quality and efficiency at the data level.

Study on the explicitation of implicit knowledge and the construction of knowledge graph on moxibustion in medical case records of ZHOU Mei-sheng's Jiusheng

To explore the methods of the explicitation of implicit knowledge and the construction of knowledge graph on moxibustion in medical case records of ZHOU Mei-sheng's Jiusheng. The medical case records data of Jiusheng was collected, the frequency statistic was analyzed based on Python3.8.6, complex network analysis was performed using Gephi9.2 software, community analysis was performed by the ancient and modern medical case cloud platform V2.3.5, and analysis and verification of correlation graph and weight graph were proceed by Neo4j3.5.25 image database. The disease systems with frequency≥10 % were surgery, ophthalmology and otorhinolaryngology, locomotor, digestive and respiratory systems. The diseases under the disease system were mainly carbuncle, arthritis, lumbar disc herniation and headache. The commonly used moxibustion methods were fumigating moxibustion, blowing moxibustion, direct moxibustion and warming acupuncture. The core prescription of points obtained by complex network analysis included Yatong point, Zhiyang(GV 9), Sanyinjiao(SP 6), Dazhui(GV 14), Zusanli(ST 36), Lingtai(GV 10), Xinshu(BL 15), Zhijian point and Hegu(LI 4), which were basically consistent with high-frequency points. A total of 6 communities were obtained by community analysis, corresponding to different diseases. Through the analysis of correlation graph, 13 pairs of strong association rule points were obtained. The correlation between Zhiyang(GV 9)-Dazhui(GV 14) and Yatong point-Lingtai(GV 10) was the strongest. The acupoints with high correlation with Yatong point were Zhiyang(GV 9), Lingtai(GV 10), Dazhui(GV 14), Zusanli(ST 36) and Sanyinjiao(SP 6). In the weight graph of the high-frequency disease system, the relationship of the first weight of the surgery system disease was fumigating moxibustion-carbuncle-Yatong point, and the relationship of the first weight of the ophthalmology and otorhinolaryngology system disease was blowing moxibustion-laryngitis-Hegu (LI 4). The results of correlation graph and weight graph are consistent with the results of data mining, which can be used as an effective way to study the knowledge base of moxibustion diagnosis and treatment in the future.

Study on the explicitation of implicit knowledge and the construction of knowledge graph on moxibustion in medical case records of ZHOU Mei-sheng's Jiusheng

To explore the methods of the explicitation of implicit knowledge and the construction of knowledge graph on moxibustion in medical case records of ZHOU Mei-sheng's Jiusheng. The medical case records data of Jiusheng was collected, the frequency statistic was analyzed based on Python3.8.6, complex network analysis was performed using Gephi9.2 software, community analysis was performed by the ancient and modern medical case cloud platform V2.3.5, and analysis and verification of correlation graph and weight graph were proceed by Neo4j3.5.25 image database. The disease systems with frequency≥10 % were surgery, ophthalmology and otorhinolaryngology, locomotor, digestive and respiratory systems. The diseases under the disease system were mainly carbuncle, arthritis, lumbar disc herniation and headache. The commonly used moxibustion methods were fumigating moxibustion, blowing moxibustion, direct moxibustion and warming acupuncture. The core prescription of points obtained by complex network analysis included Yatong point, Zhiyang(GV 9), Sanyinjiao(SP 6), Dazhui(GV 14), Zusanli(ST 36), Lingtai(GV 10), Xinshu(BL 15), Zhijian point and Hegu(LI 4), which were basically consistent with high-frequency points. A total of 6 communities were obtained by community analysis, corresponding to different diseases. Through the analysis of correlation graph, 13 pairs of strong association rule points were obtained. The correlation between Zhiyang(GV 9)-Dazhui(GV 14) and Yatong point-Lingtai(GV 10) was the strongest. The acupoints with high correlation with Yatong point were Zhiyang(GV 9), Lingtai(GV 10), Dazhui(GV 14), Zusanli(ST 36) and Sanyinjiao(SP 6). In the weight graph of the high-frequency disease system, the relationship of the first weight of the surgery system disease was fumigating moxibustion-carbuncle-Yatong point, and the relationship of the first weight of the ophthalmology and otorhinolaryngology system disease was blowing moxibustion-laryngitis-Hegu (LI 4). The results of correlation graph and weight graph are consistent with the results of data mining, which can be used as an effective way to study the knowledge base of moxibustion diagnosis and treatment in the future.探究周楣声《灸绳》医案灸法隐性知识显性化及其知识图谱构建的方法。收集《灸绳》医案数据，基于Python3.8.6进行频数统计分析，利用Gephi9.2软件进行复杂网络分析，登录古今医案云平台V2.3.5进行社团分析，并运用Neo4j3.5.25图数据库进行关联图谱和权值图谱的分析及验证。出现频率≥10%的疾病系统分别为外科、五官、运动、消化和呼吸系统。疾病系统下属疾病以痈、关节炎、腰椎间盘突出症、头痛为主。治疗常用灸法为熏灸、吹灸、直接灸和温针灸。复杂网络分析所得腧穴核心组方为压痛穴、至阳、三阴交、大椎、足三里、灵台、心俞、指尖、合谷，基本与高频腧穴相一致。社团分析共得到6个社团，分别与不同疾病相对应。关联图谱分析得到强关联规则穴对13条，至阳-大椎、压痛穴-灵台的关联性最强，与压痛穴关联性较高的腧穴为至阳、灵台、大椎、足三里、三阴交。高频疾病系统权值图谱中，外科系统疾病权值排名第一的关系为熏灸-痈-压痛穴，五官系统疾病权值排名第一的关系为吹灸-喉炎-合谷。关联图谱及权值图谱所得结论与数据挖掘结果相一致，可作为未来研究灸法诊疗知识库的有效途径。.

Pemberdayaan Guru Melalui Peningkatan Inovasi Belajar Mengajar

Community empowerment in Pambon Hamlet through the results of observations and data mining that we conducted for the community for thirty-four days shows various phenomena that occur. There are several aspects that we explored, ranging from the aspects of education, health, economy to social and community in Pambon Hamlet. Seeing the human resources (HR) that are developing in the world of education, we hold a Scientific Discussion: Increasing Teaching and Learning Innovations. This activity is expected to be able to increase the innovation and creativity of teachers in the teaching and learning process through scientific discussions related to teaching and learning innovations with Khoirun Nasikh, M.H.I. as the source.

Risk Analysis and Establishment of Supervision System of Internet Finance Based on Big Data Era

The benefits of Internet finance, such as its speed, transparency, and efficiency, have caused conventional financial institutions to rethink their business models and have led to its tremendous growth in recent years. However, as Internet finance continues to grow, new possibilities and threats are continuously developing. One of the most pressing concerns in the use of Internet technology for financial growth is how to properly identify and evaluate risks involved for Internet finance, as well as how to accurately anticipate such risks. Internet finance risk elements are examined thoroughly in this research, and a feasible solution to reduce Internet financial hazards is proposed. This paper completes the following work: (1) according to the collected sample data, the BP network is used as a big data mining analysis method to establish a financial risk assessment model. (2) The data is processed accordingly, and then based on the MATLAB program platform, the BP network numerical calculation is built to train the theoretical model, and the actual output and predicted output are obtained. (3) With the analysis results of data mining, this work has established a risk prevention and control supervision system. (4) This work has carried out various experiments on the designed method, and the results have verified the superiority of the method.

Default Feature Selection in Credit Risk Modeling: Evidence From Chinese Small Enterprises

This paper aims to design a novel AFCM-SMOTENC-APRIORI model to mine the default feature attributes of small enterprises. It can overcome the problem that the data characteristics of “small defaulting small enterprises and large non-defaulting small enterprises” make it difficult to mine the defaulting feature attributes of existing small enterprises. We used 1,231 small enterprise credit data from a city commercial bank in China to make an empirical analysis. We found that 23 feature attributes are strongly associated with default and 87% of the association rules are the same between the extended data and the original data mining. It shows that the data mining results with SMOTE-NC are highly consistent with the results of the original data mining, and the model is robust and reliable. It can be used as a reference for the credit risk identification of small enterprises in commercial banks.