Mining Framework Research Articles

AFL++: A Vulnerability Discovery and Reproduction Framework

Directed greybox fuzzing can mainly be used for vulnerability mining and vulnerability replication. However, there are still some issues with existing directional fuzzing tools. One is that after providing problematic changes or patches, it is not possible to quickly target and discover the problem. Secondly, it is difficult to break through the magic byte path, making it difficult to mine deep vulnerabilities. This article proposes a new vulnerability mining and repair framework: American Fuzz Lop Plus (AFL++). Firstly, we utilize alias analysis to enhance inter-procedural control flow graphs and redefine the distance calculation formula to obtain more accurate distances. Secondly, the Newton interpolation method is used for the energy initialization of each seed to prevent test cases from being filtered out due to low energy. A heuristic energy scheduling algorithm is proposed to judiciously schedule the energy of seeds. During the path exploration phase, by adjusting the seed energy, shorter-distance seeds quickly reach the target; with increasing time, seeds tend to explore deeper paths. We then represent the symbolic distance by the number of instructions passed to reach the target and investigate the shortest path search strategy to achieve path pruning, alleviating the problem of path explosion. Finally, based on the above methods, we implement the AFL++ prototype system, integrating directed greybox fuzzing with symbolic execution technology for vulnerability discovery. By interleaving directed symbolic execution and directed greybox fuzzing, the efficiency of vulnerability discovery and reproduction is effectively enhanced.

A Sequential Pattern Mining Method for the Individualized Detection of Online Banking Fraudulent Transactions

Financial institutions are facing a growing number of challenges as a result of the growth in fraudulent activities in online banking, which calls for the implementation of systems that are more advanced in their identification of fraud.Traditional rule-based techniques have difficulties when it comes to handling rule modifications and do not provide sufficient detail to particular users. This study presents the User-Specific Sequence Pattern Mining Framework for Online Banking Fraud Detection (USPM-FrauD) as a solution to the challenges that have been highlighted. The framework was developed in order to detect fraudulent activity in online banking.This system makes use of sequence pattern mining algorithms in order to examine the transaction logs of every user and find variations that may be indicative of fraudulent conduct. By concentrating on individualised transaction patterns, the USPM-FrauD model provides a method that is both more efficient and more specifically targeted to the identification of fraudulent activity in online banking. When compared to rule-based and Markov chain models, the experimental findings reveal that the USPM-FrauD model has greater performance. This demonstrates that the model has the potential to be practically implemented in online banking systems that are used in the real world. In order to battle the ever-changing world of online banking fraud, financial institutions now have access to a more complex and user-specific tool thanks to the USPM-FrauD framework, which marks a substantial improvement in fraud detection approaches.

Explainable data stream mining: Why the new models are better

Explainable Machine Learning brings expandability, interpretability, and accountability to Data Mining Algorithms. Existing explanation frameworks focus on explaining the decision process of a single model in a static dataset. However, in data stream mining changes in data distribution over time, called concept drift, may require updating the learning models to reflect the current data environment. It is therefore important to go beyond static models and understand what has changed among the learning models before and after a concept drift. We propose a Data Stream Explanability framework (DSE) that works together with a typical data stream mining framework where support vector machine models are used. DSE aims to help non-expert users understand model dynamics in a concept drifting data stream. DSE visualizes differences between SVM models before and after concept drift, to produce explanations on why the new model fits the data better. A survey was carried out between expert and non-expert users on the effectiveness of the framework. Although results showed non-expert users on average responded with less understanding of the issue compared to expert users, the difference is not statistically significant. This indicates that DSE successfully brings the explanability of model change to non-expert users.

Fuzzy Regional Co-Location Pattern Mining Based on Efficient Density Peak Clustering and Maximal Fuzzy Grid Cliques

Due to the heterogeneity of data distribution in real life and the spatial autocorrelation among spatial instances, traditional spatial co-location pattern mining methods tend to ignore valuable information specific to local regions. To address the limitation, regional co-location pattern mining has been proposed to find patterns that may be hidden within local regions. In this paper, a fuzzy regional co-location pattern mining framework based on efficient density peak clustering and maximal fuzzy grid cliques is presented. By incorporating a grid-splitting method and fuzzy theory, an efficient density peak clustering algorithm is proposed to divide the global area into distinct local regions. Furthermore, we propose a method to materialize the neighbor relationships between instances based on the maximal fuzzy grid cliques, and parallelize the clustering process to improve the algorithm efficiency. Experimental results show that the proposed algorithm can not only reduce the time consumption by about 40%, but also mine meaningful patterns with tighter instance distributions.

Learning Embedding for Signed Network in Social Media With Global Information

Signed networks contain nodes connected by positive and negative signed links. Signed network representation learning concentrates on learning the low-dimensional representations of these nodes, which facilitates downstream tasks such as link prediction using general data mining framework. However, most signed network embedding (SiNE) approaches neglect global information in the networks, limiting the capacity to learn genuine signed graph topology. To overcome this limitation, a deep graph neural network (GNN) framework SiG to learn SiNE with global information is proposed. To be more explicit, a hierarchical pooling mechanism is developed to encode the high-level features of the networks. Moreover, a graph convolution layer is introduced to aggregate both positive and negative information from neighbor nodes, and the concatenation of two parts generates the final embedding of nodes. Extensive experiments on four large real-world signed network datasets demonstrate the effectiveness and excellence of the proposed method.

Introducing exceptional growth mining-Analyzing the impact of soil characteristics on on-farm crop growth and yield variability.

Sustainable intensification of agriculture requires understanding of the effect of soil characteristics and nutrient supply on crop growth. As farms are increasing in size by acquiring small fields from various farmers, the soil characteristics and nutrient supply might be very different from field to field, while at the same time specific soil properties might limit the nutrient uptake. As a result, there might be a large number of heterogeneous reasons why crop growth varies significantly. New data analysis techniques can help to explain variability in crop growth among fields. This paper introduces Exceptional Growth Mining (EGM) as a first contribution. EGM instantiates the data mining framework Exceptional Model Mining (EMM) such that subgroups of fields can be found that grow exceptionally in terms of three growth parameters (high/low maximum growth, steep/flat linear growth and early/late midpoint of maximum growth). As second contribution, we apply EGM to a case study by analyzing the dataset of a potato farm in the south of the Netherlands. EGM consists of (i) estimating growth curves by applying nonlinear mixed models, (ii) investigating the correlation between the estimated growth parameters, and (iii) applying EMM on these growth curve parameters using a growth curve-specific quality measure. By applying EGM on the data of the potato farm, we obtain the following results: 1) the estimated growth curves represent the variability in potato tuber growth very well (R2 of 0.92), 2) the steepness of the growth curve has a strong correlation with the maximum growth and the midpoint of maximum growth, and the correlation between the midpoint of maximum growth and maximum growth is weak, 3) the subgroup analyses indicate that: high values of K correspond to high maxima; low values of K correspond to low maxima, steep growth curves', and a late midpoint of halfway growth; Mg influences the midpoint of the growth curve; values of B are higher on dry soils with high tuber growth, while low values of B are found on wet soils with high tuber growth; high values of Zn, Mn, and Fe are found in subgroups with low tuber weight, probably related to the soil's low pH. In summary, this paper introduces EGM to obtain understanding in crop response to soil properties and nutrient supply. In addition, EGM provides a way to analyze only small parts of a large dataset, such that the impact of soil factors on growth can be analyzed on a more detailed level than existing methods.

Mining the Micro-Trajectory of Two-Wheeled Non-Motorized Vehicles Based on the Improved YOLOx

Two-wheeled non-motorized vehicles (TNVs) have become the primary mode of transportation for short-distance travel among residents in many underdeveloped cities in China due to their convenience and low cost. However, this trend also brings corresponding risks of traffic accidents. Therefore, it is necessary to analyze the driving behavior characteristics of TNVs through their trajectory data in order to provide guidance for traffic safety. Nevertheless, the compact size, agile steering, and high maneuverability of these TNVs pose substantial challenges in acquiring high-precision trajectories. These characteristics complicate the tracking and analysis processes essential for understanding their movement patterns. To tackle this challenge, we propose an enhanced You Only Look Once Version X (YOLOx) model, which incorporates a median pooling-Convolutional Block Attention Mechanism (M-CBAM). This model is specifically designed for the detection of TNVs, and aims to improve accuracy and efficiency in trajectory tracking. Furthermore, based on this enhanced YOLOx model, we have developed a micro-trajectory data mining framework specifically for TNVs. Initially, the paper establishes an aerial dataset dedicated to the detection of TNVs, which then serves as a foundational resource for training the detection model. Subsequently, an augmentation of the Convolutional Block Attention Mechanism (CBAM) is introduced, integrating median pooling to amplify the model’s feature extraction capabilities. Subsequently, additional detection heads are integrated into the YOLOx model to elevate the detection rate of small-scale targets, particularly focusing on TNVs. Concurrently, the Deep Sort algorithm is utilized for the precise tracking of vehicle targets. The process culminates with the reconstruction of trajectories, which is achieved through a combination of video stabilization, coordinate mapping, and filtering denoising techniques. The experimental results derived from our self-constructed dataset reveal that the enhanced YOLOx model demonstrates superior detection performance in comparison to other analogous methods. The comprehensive framework accomplishes an average trajectory recall rate of 85% across three test videos. This significant achievement provides a reliable method for data acquisition, which is essential for investigating the micro-level operational mechanisms of TNVs. The results of this study can further contribute to the understanding and improvement of traffic safety on mixed-use roads.

Statistical Analysis and Accuracy Assessment of Improved Machine Learning Based Opinion Mining Framework

Sentiment analysis, also known as opinion mining, plays a crucial role in understanding and extracting valuable insights from textual data in various domains, including social media, customer feedback, and product reviews. This research presents an in-depth examination of an improved machine learning-based sentiment analysis framework, focusing on its statistical analysis and accuracy assessment. The research begins by introducing the framework's architecture, which incorporates advanced machine learning algorithms and natural language processing techniques. These enhancements aim to provide a more nuanced and context-aware sentiment analysis, addressing the limitations of traditional approaches. To evaluate the performance of the proposed framework, a comprehensive statistical analysis is conducted. Various statistical metrics, such as precision, recall, F1-score, and accuracy, are employed to assess its effectiveness in classifying text sentiments accurately. Additionally, the study explores the impact of different feature engineering and pre-processing techniques on model performance. The results of this study demonstrate the significant improvements achieved by the enhanced sentiment analysis framework in terms of accuracy and reliability. The statistical analysis confirms its superior performance in capturing subtle sentiment nuances, making it a valuable tool for applications requiring precise sentiment understanding. In conclusion, this research contributes to the field of sentiment analysis by presenting an improved machine learning-based framework and conducting a rigorous statistical assessment of its accuracy. The findings provide valuable insights for researchers and practitioners seeking to enhance sentiment analysis techniques and apply them effectively in various domains..

UI Action Logger to Investigate Potential Robotic Process Automation Routines.

Robotic Process Automation (RPA) is a cost-effective technology that emulates human tasks, reduces errors and enhances business performance. However, identifying ideal processes for RPA implementation can be challenging. Process Mining is a strategy that leverages User Interface (UI) logs to delve into processes and generate "process maps." These logs record user actions during processes, necessitating the use of a tool such as UI Action Logger to capture and transmit them to a cloud-based application for logging. Subsequently, Process Mining frameworks like ProM utilize these logs to construct process models, aiding in the identification of repetitive processes suitable for RPA automation. This innovative study shifts the focus of process mining from event logs to UI logs, simplifying the detection of potential routines. Enriched UI logs are valuable for creating RPA bots, conducting in-depth process analysis, task mining, and training RPA bots through machine learning, and selecting processes for automation. In summary, UI Action Logger offers distinctive features, capturing user interactions at a coarse level conducive to RPA implementation.

Automated data mining framework for building energy conservation aided by generative pre-trained transformers (GPT)

Data mining technologies have showed promising capabilities in extracting building operation patterns from massive amounts of building operational data for energy conservation. However, the number of the extracted operation patterns is always large. It is time-consuming and tedious for users to find valuable operation patterns among them. To overcome this barrier, this study proposes an automated data mining framework based on maximal frequent itemset mining and generative pre-trained transformers (GPT). An improved maximal frequent itemset mining-based data mining method is developed to extract non-redundant operation patterns from numerous building operational data for reducing the number of the extracted operation patterns. A template-based prompt generation method is proposed to transform the extracted operation patterns into prompts. The prompts are inputted into GPT to determine whether there are energy waste patterns hidden in the extracted operation patterns. It liberates humans from the tedious work on analyzing the extracted operation patterns. The framework is applied to analyze the one-year operational data from a real-world building chiller plant system for verifying its performance. Most of the energy waste patterns in this system are detected successfully, such as valve faults, low chilled water outlet temperature, small chilled and cooling water temperature differences, and improper coordinated control among devices. The detection accuracy of GPT is 89.17 % for energy waste patterns and 99.48 % for normal operation patterns. The response time and cost of GPT are 6747.60 s and $17.68, respectively.

Data Preprocessing for Cross-System Analysis: The DaProXSA Approach

The domain of Social Collaboration Analytics (SCA) is gathering momentum due to the increasing importance of Enterprise Collaboration Systems (ECS) that are used to build performant digital workplaces. ECS collect and store large amounts of digital trace data, which reflect the collaborative work of employees. Collaborative work activity is usually supported by multiple systems, which complicates the analysis of the digital traces. The cross-system analysis of collaborative work is challenging because of the nature of the log files that are stored in heterogeneous formats and at different levels of log granularity. These challenges cannot easily be overcome with the help of existing approaches for data preprocessing. In this paper, approaches and frameworks for data mining, data preprocessing and SCA are adapted to design a special method for Social Process Mining (SPM). The DaProXSA approach was developed to obtain interpretable, high-quality event logs of multiple ECS and builds on existing literature as well as on findings from an analysis of leading ECS. DaProXSA contributes to the aim of discovering and interpreting patterns and processes that occur in computer-mediated collaborative work.

Progressive Frame-Proposal Mining for Weakly Supervised Video Object Detection.

In this paper, we focus on the weakly supervised video object detection problem, where each training video is only tagged with object labels, without any bounding box annotations of objects. To effectively train object detectors from such weakly-annotated videos, we propose a Progressive Frame-Proposal Mining (PFPM) framework by exploiting discriminative proposals in a coarse-to-fine manner. First, we design a flexible Multi-Level Selection (MLS) scheme, with explicit guidance of video tags. By selecting object-relevant frames and mining important proposals from these frames, the proposed MLS can effectively reduce frame redundancy as well as improve proposal effectiveness to boost weakly-supervised detectors. Moreover, we develop a novel Holistic-View Refinement (HVR) scheme, which can globally evaluate importance of proposals among frames, and thus correctly refine pseudo ground truth boxes for training video detectors in a self-supervised manner. Finally, we evaluate the proposed PFPM on a large-scale benchmark for video object detection, on ImageNet VID, under the setting of weak annotations. The experimental results demonstrate that our PFPM significantly outperforms the state-of-the-art weakly-supervised detectors.

Social media insights into spatio-temporal emotional responses to COVID-19 crisis

The Coronavirus pandemic has presented multifaceted challenges in urban emotional well-being and mental health management. Our study presents a spatio-temporal sentiment mining (STSM) framework to address these challenges, focusing on the space-time geography and environmental psychology. This framework analyzes the distribution and trends of 6 categories of public sentiments in Shanghai during the COVID-19 crisis, considering the potential urban spatial influencing factors. The research specifically draws on social media data temporally coinciding with the spread of COVID-19 and the pre-trained language model RoBERTa-wwm-ext to classify public sentiment, in order to characterize the distribution and trends of dominant urban sentiment under the influence of epidemic at different phases. The interactions between urban geospatial features and sentiments are further modelled and explained using LightGBM algorithm and SHapley Additive exPlanations (SHAP) technique. The experimental findings reveal the subtle yet dynamic impact of the urban environment on the long-term spatial variation and trends of public sentiment under the epidemic, with green spaces and socio-economic status emerging as significant factors. Regions with higher permanent population consumption demonstrated more positive sentiments, underscoring the significance of socio-economic factors in urban planning and public health policy. This research offers the most extensive analysis to date on the influence of urban characteristics on public sentiment during Shanghai's epidemic life cycle also lays the groundwork for applying the STSM framework in future crises beyond COVID-19.

Visualizing Large-Scale Spatial Time Series with GeoChron.

In geo-related fields such as urban informatics, atmospheric science, and geography, large-scale spatial time (ST) series (i.e., geo-referred time series) are collected for monitoring and understanding important spatiotemporal phenomena. ST series visualization is an effective means of understanding the data and reviewing spatiotemporal phenomena, which is a prerequisite for in-depth data analysis. However, visualizing these series is challenging due to their large scales, inherent dynamics, and spatiotemporal nature. In this study, we introduce the notion of patterns of evolution in ST series. Each evolution pattern is characterized by 1) a set of ST series that are close in space and 2) a time period when the trends of these ST series are correlated. We then leverage Storyline techniques by considering an analogy between evolution patterns and sessions, and finally design a novel visualization called GeoChron, which is capable of visualizing large-scale ST series in an evolution pattern-aware and narrative-preserving manner. GeoChron includes a mining framework to extract evolution patterns and two-level visualizations to enhance its visual scalability. We evaluate GeoChron with two case studies, an informal user study, an ablation study, parameter analysis, and running time analysis.

Computational analysis of dystopian elements in the partition fiction: A machine learning approach to the indian English novels

Despite the growth of digital humanities, the specific application of computational methods to analyse literary themes and elements remains underexplored. This study aims to use machine learning algorithms for text classification on seven novels about the partition of India. The article has a dual objective: firstly, to develop and implement an innovative opinion mining framework that leverages machine learning techniques to identify and classify dystopian elements in Partition novels; and secondly, to evaluate and compare the efficacy of the model in accurately classifying dystopian sentiments within selected literary texts. The proposed framework includes six phases of data collection, test-pre-processing, text extraction, text exploration, modelling or classification using machine leaning, and performance evaluation. Machine learning approaches such as Logistic Regression, Naïve Bayes, Support Vector Machine, and k-Nearest Neighbor are adopted to classify the text based on compiled dictionary. First, the study revealed that the main components and characteristics of dystopian elements found in selected narratives are ‘fear’, ‘suffer’, ‘oppression’ and ‘violence’. Second, the analysis showed that SVM with CountVectorizer, using imbalanced dataset and random oversampling dataset, outperforms other classifiers in classifying dystopian types in the selected novels. The results also suggest that CountVectorizer works better for the dataset compared to TF-IDF.

Clustering-Based Frequent Pattern Mining Framework for Solving Cold-Start Problem in Recommender Systems

Clustering-Based Frequent Pattern Mining Framework for Solving Cold-Start Problem in Recommender Systems

FePARM: The Frequency-Patterned Associative Rule Mining Framework on Consumer Purchasing-Pattern for Online Shops

1Malasowe, Bridget Ogheneovo,, 2Okpako, Abugor Ejaita, 3 , 4Ejeh, Patrick Ogholuwarami, 5Ojugo, Arnold Adimabua & 6 1Department of Computer Science, University of Delta, Agbor, Nigeria 2Department of Cyber Security, University of Delta, Agbor, Nigeria 3Department of Cyber Security, Faculty of Computing, Delta State University of Science and Technology, Ozoro. Nigeria. 4Department of Computer Science, Dennis Osadebay University, Anwai-Asaba, Nigeria 5 Department of Computer Science, Federal University of Petroleum Resources Effurun, Nigeria 6 Department of Computer Science, Federal University of Petroleum Resources Effurun, Nigeria E-mails: 1bridget.malasowe@unidel.edu.ng; 2ejaita.okpako@unidel.edu.ng; 3okpormd@dsust.edu.ng, 4 patrick.ejeh@dou.edu.ng; 5ojugo.arnold@fupre.edu.ng, 6ako.rita@fupre.edu.ng ABSTRACT Transaction data often is a true presentation of consumers’ buying behavior, stored as a set of relational records, which properly harnessed via mining – can help businesses improve their sales volume as a decision support system. Managing such a system can pose many issues to biz such as feature evolution, concept evolution, concept drift, and infinite data length – and often makes it impractical to effectively store such big-data. To curb this, previous studies have assumed data to be stationary in using associative rule mining. This has deprived such systems of the flexibility and adaptiveness required to handle the dynamics of concept drift that characterizes transaction datasets. Our study thus proposes a basket frequent pattern growth trained associative rule mining model to handle large data. The dataset was retrieved from the Delta-Mall Asaba and consists of 556,000 transaction consumer records. The model consists of six-layers, and yields the best result with a 0.1 value for both the confidence and support level(s) at a 94% accuracy, sensitivity of 87%, and a specificity of 32% with a 20-second convergence and processing time. Keywords: Big-Data Analysis, Feature Evolution, Inventory Model, Market Basket Analysis, Businesses, Transactional Data Streams, Concept Drift CISDI Journal Reference Format Malasowe, B.O., Okpako, A.E., Okpor, M.D., Ejeh, P.O., Ojugo, A.A. & Ako, R.E. (2024): FePARM: The Frequency-Patterned Associative Rule Mining Framework on Consumer Purchasing-Pattern for Online Shops. Computing, Information Systems, Development Informatics & Allied Research Journal. Vol 15 No 2, Pp 15-28. dx.doi.org/10.22624/AIMS/CISDI/V15N2P2-1. Available online at www.isteams.net/cisdijournal

FePARM: The Frequency-Patterned Associative Rule Mining Framework on Consumer Purchasing-Pattern for Online Shops

Transaction data often is a true presentation of consumers’ buying behavior, stored as a set of relational records, which properly harnessed via mining – can help businesses improve their sales volume as a decision support system. Managing such a system can pose many issues to biz such as feature evolution, concept evolution, concept drift, and infinite data length – and often makes it impractical to effectively store such big-data. To curb this, previous studies have assumed data to be stationary in using associative rule mining. This has deprived such systems of the flexibility and adaptiveness required to handle the dynamics of concept drift that characterizes transaction datasets. Our study thus proposes a basket frequent pattern growth trained associative rule mining model to handle large data. The dataset was retrieved from the Delta-Mall Asaba and consists of 556,000 transaction consumer records. The model consists of six-layers, and yields the best result with a 0.1 value for both the confidence and support level(s) at a 94% accuracy, sensitivity of 87%, and a specificity of 32% with a 20-second convergence and processing time. Keywords: Big-Data Analysis, Feature Evolution, Inventory Model, Market Basket Analysis, Businesses, Transactional Data Streams, Concept Drift CISDI Journal Reference Format Malasowe, B.O., Okpako, E.A., Ashioba, N.O., Ejeh, P.O., Ojugo, A.A. & Ako, R.E. (2024): FePARM: The Frequency-Patterned Associative Rule Mining Framework on Consumer Purchasing-Pattern for Online Shops. Computing, Information Systems, Development Informatics & Allied Research Journal. Vol 15 No 2, Pp 1-14. dx.doi.org/10.22624/AIMS/CISDI/V15N2P2. Available online at www.isteams.net/cisdijournal

Pedagogical Integration of Core Literacy in College Physical Education and Health Courses Based on Data Mining Techniques

Abstract At universities and colleges today, physical education is overly regimented and ignores students’ basic health literacy. This study aims to investigate this phenomenon by examining the state of physical education instruction in colleges and universities nowadays using data mining techniques. In order to retrieve information on the essential literacies of health and physical education courses at colleges and universities, the study first builds a data mining framework using data clustering analysis, association rule extraction, and decision tree algorithms. The teaching-coordination-level model of the core literacies of physical education and health courses is established utilizing the entropy power approach, and the development history of physical education is examined. To determine the best teaching technique for integrating the core literacies of physical education and health courses, an experiment was conducted using College A as an example. The findings indicate that following the trial, students in the experimental class had substantial improvements in their physical and health literacy scores, with the exception of physical fitness (P>0.05). In the previous 10 years, the mean value of the coupling coordination was between 0.6683. The integration of the essential literacies of physical education and health courses accounted for more than 90% of the total credit hours earned in the best colleges and universities. In addition to enhancing physical education abilities, the integration of health and physical education curricula with core literacy in colleges and universities supports the general development of students’ health literacy.

Enhancing safety of construction workers in Korea: an integrated text mining and machine learning framework for predicting accident types

Construction workers face a high risk of various occupational accidents, many of which can result in fatalities. This study aims to develop a prediction model for nine prevalent types of construction accidents, utilizing construction tasks, activities, and tools/materials as input features, through the application of machine learning-based multi-class classification algorithms. 152,867 construction accident summary reports, composed of both structured (construction task, construction activity, accident type) and unstructured data (tools/materials) were used for the study. The study employed several data processing techniques, including keyword extraction through text mining, Boruta feature selection, and SMOTE data resampling enhance model accuracy. Three performance metrics (Multi-class area under the receiver operating characteristic curve (MAUC), Multi-class Matthews Correlation Coefficient (MMCC), Geometric-mean (G-mean)) were used to compare the predictive performance of four machine learning algorithms, including Decision tree, Random forest, Naïve bayes, and XGBoost. Of the four algorithms, XGBoost showed the highest performance in predicting accident type (MAUC: 0.8603, MMCC: 0.3523, G-mean: 0.5009). Furthermore, a Shapley additive explanation (SHAP) analysis was conducted to visualize feature importance. The findings of this study make a valuable contribution to improving construction safety by presenting a prediction model for accident types derived from real-world big data.