{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T12:48:38Z","timestamp":1763988518866,"version":"3.45.0"},"reference-count":94,"publisher":"National Library of Serbia","issue":"4","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["ComSIS","COMPUT SCI INF SYST","COMPUT SCI INFORM SY","COMPUTER SCI INFORM","COMSIS J"],"published-print":{"date-parts":[[2025]]},"abstract":"<jats:p>In the commercial realm, particularly for businesses targeting consumers (B2C), the challenge of acquiring and retaining valuable potential customers is paramount. As chip technology continues to advance at breakneck speed, in line with Moore?s Law, various innovative AI technologies have emerged, yet this also highlights the infamous ?black-box? issue. Naturally, this has paved the way for the rise of Explainable AI (XAI) and machine learning. In response, this study proposes a universal explainability framework to tackle both the black-box conundrum and the limitation of customer list sizes. The framework leverages the fundamental Byte-Pair Encoding (BPE) algorithm from large language models to tokenize natural language data, integrating the results into customer data as feature columns, thereby constructing comprehensive Persona. Crucially, domain experts are involved in the model-building process, selecting and recommending features. These experts utilize depth-first search to identify additional, similar feature columns, which are then used as target categories for machine learning models. The final step involves classification tasks and prediction evaluations. The proposed framework demonstrates its effectiveness and generalizability through validation on public datasets, increasing the number of potential customers by 7.5 times compared to traditional modeling approaches. In case studies, the framework outperforms customer lists generated by experts based on past experience, yielding 2.4 times more customers, 3.8 times higher response rates, and 9 times more total respondents. More importantly, both the model-building process and predictive outcomes are interpretable through domain knowledge, enabling businesses to transfer experience and expertise, thus laying a solid foundation for large language models within the industry.<\/jats:p>","DOI":"10.2298\/csis241130068l","type":"journal-article","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:38:46Z","timestamp":1759235926000},"page":"1707-1756","source":"Crossref","is-referenced-by-count":0,"title":["Implementing persona in the business sector by a universal explainable AI framework based on byte-pair encoding"],"prefix":"10.2298","volume":"22","author":[{"given":"Zhenyao","family":"Liu","sequence":"first","affiliation":[{"name":"School of Economics and Management, Taizhou University Taizhou, Jiangsu Province, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Lun","family":"Liu","sequence":"additional","affiliation":[{"name":"Integration and Collaboration Laboratory, Department of Industrial Engineering and Engineering Management, National Tsing Hua University Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Chang","family":"Yeh","sequence":"additional","affiliation":[{"name":"Integration and Collaboration Laboratory, Department of Industrial Engineering and Engineering Management, National Tsing Hua University Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chia-Ling","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of International Logistics and Transportation Management, Kainan University Taoyuan, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1078","reference":[{"key":"ref1","doi-asserted-by":"crossref","unstructured":"A. Rakipi, O. Shurdi, and J. Imami, \u201cUtilization of data mining and machine learning in digital and electronic payments in banks,\u201d Corporate and Business Strategy Review, vol. 4, no. 4, pp. 243-251, 2023.","DOI":"10.22495\/cbsrv4i4siart5"},{"key":"ref2","doi-asserted-by":"crossref","unstructured":"W. Yeh, M. Chuang, and W. Lee, \u201cUniform parallel machine scheduling with resource consumption constraint,\u201d Applied Mathematical Modelling, vol. 39, no. 8, pp. 2131-2138, 2015.","DOI":"10.1016\/j.apm.2014.10.012"},{"key":"ref3","doi-asserted-by":"crossref","unstructured":"W. Yeh and S. Wei, \u201cEconomic-based resource allocation for reliable grid-computing service based on grid bank,\u201d Future Generation Computer Systems, vol. 28, no. 7, pp. 989-1002, 2012.","DOI":"10.1016\/j.future.2012.03.005"},{"key":"ref4","doi-asserted-by":"crossref","unstructured":"K. Pousttchi and M. Dehnert, \u201cExploring the digitalization impact on consumer decisionmaking in retail banking,\u201d Electronic Markets, vol. 28, no. 3, pp. 265-286, 2018.","DOI":"10.1007\/s12525-017-0283-0"},{"key":"ref5","doi-asserted-by":"crossref","unstructured":"P. Angelov, E. Soares, R. Jiang, N. Arnold, and P. Atkinson, \u201cExplainable artificial intelligence: an analytical review,\u201d WIREs Data Mining and Knowledge Discovery, vol. 11, no. 5, p. 2021, 2021.","DOI":"10.1002\/widm.1424"},{"key":"ref6","unstructured":"J. Achiam and et al., \u201cGpt-4 technical report,\u201d arXiv preprint arXiv:2303.08774, 2023."},{"key":"ref7","unstructured":"H. Touvron and et al., \u201cLlama 2: Open foundation and fine-tuned chat models,\u201d arXiv preprint arXiv:2307.09288, 2023."},{"key":"ref8","unstructured":"\u201cIntroducing llama: A foundational, 65-billion-parameter language model.\u201d https:\/\/ai.meta.com\/blog\/large-language-model-llama-meta-ai\/. Accessed: 2024\/4\/2."},{"key":"ref9","unstructured":"S. Spatharioti, D. Rothschild, D. Goldstein, and J. Hofman, \u201cComparing traditional and llm-based search for consumer choice: A randomized experiment,\u201d arXiv preprint arXiv:2307.03744, 2023."},{"key":"ref10","doi-asserted-by":"crossref","unstructured":"H. Corley, J. Rosenberger, W. Yeh, and T. Sung, \u201cThe cosine simplex algorithm,\u201d The International Journal of Advanced Manufacturing Technology, vol. 27, pp. 1047-1050, 2006.","DOI":"10.1007\/s00170-004-2278-1"},{"key":"ref11","unstructured":"B. Arcila, \u201cIs it a platform? is it a search engine? it\u2019s chatgpt! the european liability regime for large language models,\u201d Journal of Free Speech Law, vol. 3, p. 455, 2023."},{"key":"ref12","doi-asserted-by":"crossref","unstructured":"W. Yeh, \u201cNovel binary-addition tree algorithm (bat) for binary-state network reliability problem,\u201d Reliability Engineering and System Safety, vol. 208, p. 107448, 2021.","DOI":"10.1016\/j.ress.2021.107448"},{"key":"ref13","doi-asserted-by":"crossref","unstructured":"M. Karpinska and M. Iyyer, \u201cLarge language models effectively leverage document-level context for literary translation, but critical errors persist,\u201d in Proceedings of the Eighth Conference on Machine Translation, 2023.","DOI":"10.18653\/v1\/2023.wmt-1.41"},{"key":"ref14","doi-asserted-by":"crossref","unstructured":"W. Yeh, \u201cA new branch-and-bound approach for the n\/2\/flowshop\/f+ cmax flowshop scheduling problem,\u201d Computers & Operations Research, vol. 26, no. 13, pp. 1293-1310, 1999.","DOI":"10.1016\/S0305-0548(98)00106-3"},{"key":"ref15","doi-asserted-by":"crossref","unstructured":"A. Thirunavukarasu, D. Ting, K. Elangovan, L. Gutierrez, T. Tan, and D. Ting, \u201cLarge language models in medicine,\u201d Nature Medicine, vol. 29, no. 8, pp. 1930-1940, 2023.","DOI":"10.1038\/s41591-023-02448-8"},{"key":"ref16","doi-asserted-by":"crossref","unstructured":"C. Luo, B. Sun, K. Yang, T. Lu, and W. Yeh, \u201cThermal infrared and visible sequences fusion tracking based on a hybrid tracking framework with adaptive weighting scheme,\u201d Infrared Physics & Technology, vol. 99, pp. 265-276, 2019.","DOI":"10.1016\/j.infrared.2019.04.017"},{"key":"ref17","doi-asserted-by":"crossref","unstructured":"A. Mbakwe, I. Lourentzou, L. Celi, O. Mechanic, and A. Dagan, \u201cChatgpt passing usmle shines a spotlight on the flaws of medical education,\u201d PLOS Digital Health, vol. 2, no. 2, p. e0000205, 2023.","DOI":"10.1371\/journal.pdig.0000205"},{"key":"ref18","unstructured":"N. Chiliya, G. Herbst, and M. Roberts-Lombard, \u201cThe impact of marketing strategies on profitability of small grocery shops in south african townships,\u201d African Journal of Business Management, vol. 3, no. 3, p. 70, 2009."},{"key":"ref19","doi-asserted-by":"crossref","unstructured":"T. Damrongsakmethee and V.-E. Neagoe, \u201cData mining and machine learning for financial analysis,\u201d Indian Journal of Science and Technology, vol. 10, no. 39, pp. 1-7, 2017.","DOI":"10.17485\/ijst\/2017\/v10i39\/119861"},{"key":"ref20","doi-asserted-by":"crossref","unstructured":"R. Aditya and D. Satria, \u201cOptimizing bank marketing strategies through analysis using lightgbm,\u201d CoreID Journal, vol. 1, no. 2, pp. 58-65, 2023.","DOI":"10.60005\/coreid.v1i2.11"},{"key":"ref21","doi-asserted-by":"crossref","unstructured":"S. Shim, M. Eastlick, and S. Lotz, \u201cSearch-purchase (s-p) strategies of multi-channel consumers,\u201d Journal of Marketing Channels, vol. 11, no. 2-3, pp. 33-54, 2004.","DOI":"10.1300\/J049v11n02_03"},{"key":"ref22","doi-asserted-by":"crossref","unstructured":"A. Faria andW.Wellington, \u201cValidating business gaming: Business game conformity with pims findings,\u201d Simulation & Gaming, vol. 36, no. 2, pp. 259-273, 2005.","DOI":"10.1177\/1046878105275454"},{"key":"ref23","unstructured":"P. Chate, Behavioral Modelling of Customer Marketing Patterns and Review Prediction Using Machine Learning Techniques. PhD thesis, National College of Ireland, Dublin, 2022."},{"key":"ref24","doi-asserted-by":"crossref","unstructured":"M. Muslim, Y. Dasril, A. Alamsyah, and T. Mustaqim, \u201cBank predictions for prospective longterm deposit investors using machine learning lightgbm and smote,\u201d Journal of Physics: Conference Series, vol. 1918, no. 4, p. 042143, 2021.","DOI":"10.1088\/1742-6596\/1918\/4\/042143"},{"key":"ref25","doi-asserted-by":"crossref","unstructured":"E. Broek, A. Sergeeva, and M. Huysman, \u201cWhen the machine meets the expert: An ethnography of developing ai for hiring,\u201d MIS Quarterly, vol. 45, no. 3, 2021.","DOI":"10.25300\/MISQ\/2021\/16559"},{"key":"ref26","unstructured":"T. Jovanov and M. Stojanovski, \u201cMarketing knowledge and strategy for smes: Can they live without it?,\u201d in Thematic Collection of papers of international significance: Reengineering and entrepreneurship under the contemporary conditions of enterprise business, pp. 131-143, 2012."},{"key":"ref27","doi-asserted-by":"crossref","unstructured":"Y. Huang, M. Zhang, and Y. He, \u201cResearch on improved rfm customer segmentation model based on k-means algorithm,\u201d in 2020 5th International Conference on Computational Intelligence and Applications (ICCIA), 2020.","DOI":"10.1109\/ICCIA49625.2020.00012"},{"key":"ref28","doi-asserted-by":"crossref","unstructured":"E. Soares, P. Angelov, B. Costa, and M. Castro, \u201cActively semi-supervised deep rule-based classifier applied to adverse driving scenarios,\u201d in 2019 International Joint Conference on Neural Networks (IJCNN), 2019.","DOI":"10.1109\/IJCNN.2019.8851842"},{"key":"ref29","doi-asserted-by":"crossref","unstructured":"R. Blanco and C. Lioma, \u201cGraph-based term weighting for information retrieval,\u201d Information Retrieval, vol. 15, no. 1, pp. 54-92, 2011.","DOI":"10.1007\/s10791-011-9172-x"},{"key":"ref30","doi-asserted-by":"crossref","unstructured":"X. Xie, J. Niu, X. Liu, Z. Chen, S. Tang, and S. Yu, \u201cA survey on incorporating domain knowledge into deep learning for medical image analysis,\u201d Medical Image Analysis, vol. 69, p. 101985, 2021.","DOI":"10.1016\/j.media.2021.101985"},{"key":"ref31","doi-asserted-by":"crossref","unstructured":"C. Deng, X. Ji, C. Rainey, J. Zhang, and W. Lu, \u201cIntegrating machine learning with human knowledge,\u201d iScience, vol. 23, no. 11, p. 101656, 2020.","DOI":"10.1016\/j.isci.2020.101656"},{"key":"ref32","doi-asserted-by":"crossref","unstructured":"V. Belle and I. Papantonis, \u201cPrinciples and practice of explainable machine learning,\u201d Frontiers in Big Data, vol. 4, p. 688969, 2021.","DOI":"10.3389\/fdata.2021.688969"},{"key":"ref33","unstructured":"S. Lundberg and S. Lee, \u201cA unified approach to interpreting model predictions,\u201d in Advances in Neural Information Processing Systems, vol. 30, 2017."},{"key":"ref34","doi-asserted-by":"crossref","unstructured":"A. Arrieta and et al., \u201cExplainable artificial intelligence (xai): Concepts, taxonomies, opportunities and challenges toward responsible ai,\u201d Information Fusion, vol. 58, pp. 82-115, 2020.","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"ref35","doi-asserted-by":"crossref","unstructured":"Z. Liu,W. Yeh, K. Lin, C. Lin, and C. Chang, \u201cMachine learning based approach for exploring online shopping behavior and preferences with eye tracking,\u201d Computer Science and Information Systems, vol. 21, no. 2, pp. 593-623, 2024.","DOI":"10.2298\/CSIS230807077L"},{"key":"ref36","doi-asserted-by":"crossref","unstructured":"R. Roscher, B. Bohn, M. Duarte, and J. Garcke, \u201cExplainable machine learning for scientific insights and discoveries,\u201d IEEE Access, vol. 8, pp. 42200-42216, 2020.","DOI":"10.1109\/ACCESS.2020.2976199"},{"key":"ref37","doi-asserted-by":"crossref","unstructured":"H. Chia, \u201cThe emergence and need for explainable ai,\u201d Advances in Engineering Innovation, vol. 3, no. 1, pp. 1-4, 2023.","DOI":"10.54254\/2977-3903\/3\/2023023"},{"key":"ref38","unstructured":"E. Soares, P. Angelov, S. Biaso, M. Froes, and D. Abe, \u201cSars-cov-2 ct-scan dataset: A large dataset of real patients ct scans for sars-cov-2 identification,\u201d MedRxiv, 2020."},{"key":"ref39","doi-asserted-by":"crossref","unstructured":"F. Morais, A. Garcia, P. Santos, and L. Ribeiro, \u201cDo explainable ai techniques effectively explain their rationale? a case study from the domain expert\u2019s perspective,\u201d in 2023 26th International Conference on Computer Supported Cooperative Work in Design (CSCWD), 2023.","DOI":"10.1109\/CSCWD57460.2023.10152722"},{"key":"ref40","doi-asserted-by":"crossref","unstructured":"J. Dressel and H. Farid, \u201cThe accuracy, fairness, and limits of predicting recidivism,\u201d Science Advances, vol. 4, no. 1, p. eaao5580, 2018.","DOI":"10.1126\/sciadv.aao5580"},{"key":"ref41","unstructured":"A. Smith-Renner, R. Rua, and M. Colony, \u201cTowards an explainable threat detection tool,\u201d in IUI Workshops, 2019."},{"key":"ref42","doi-asserted-by":"crossref","unstructured":"S. Mathews, \u201cExplainable artificial intelligence applications in nlp, biomedical, and malware classification: A literature review,\u201d in Advances in Intelligent Systems and Computing, pp. 1269-1292, Springer International Publishing, 2019.","DOI":"10.1007\/978-3-030-22868-2_90"},{"key":"ref43","unstructured":"A. Das and P. Rad, \u201cOpportunities and challenges in explainable artificial intelligence (xai): A survey,\u201d arXiv preprint arXiv:2006.11371, 2020."},{"key":"ref44","doi-asserted-by":"crossref","unstructured":"S. Murindanyi, B. Mugalu, J. Nakatumba-Nabende, and G. Marvin, \u201cInterpretable machine learning for predicting customer churn in retail banking,\u201d in 2023 7th International Conference on Trends in Electronics and Informatics (ICOEI), 2023.","DOI":"10.1109\/ICOEI56765.2023.10125859"},{"key":"ref45","doi-asserted-by":"crossref","unstructured":"T. Clement, N. Kemmerzell, M. Abdelaal, and M. Amberg, \u201cXair: A systematic metareview of explainable ai (xai) aligned to the software development process,\u201d Machine Learning and Knowledge Extraction, vol. 5, no. 1, pp. 78-108, 2023.","DOI":"10.3390\/make5010006"},{"key":"ref46","unstructured":"Y. Han, \u201cResearch on precise service of academic journals based on user profile,\u201d Acta Editologica, vol. 2, pp. 142-146, 2021."},{"key":"ref47","unstructured":"D. Travis, \u201cHow to create personas your design team will believe in.\u201d https:\/\/www.userfocus.co.uk\/articles\/personas.html. Accessed: 2024\/4\/2."},{"key":"ref48","doi-asserted-by":"crossref","unstructured":"Y. Chang, Y. Lim, and E. Stolterman, \u201cPersonas: from theory to practices,\u201d in Proceedings of the 5th Nordic conference on Human-computer interaction: building bridges, pp. 439-442, 2008.","DOI":"10.1145\/1463160.1463214"},{"key":"ref49","doi-asserted-by":"crossref","unstructured":"L. W., O. K., L. C.G., and C. H.J., \u201cUser profile extraction from twitter for personalized news recommendation,\u201d in 16th International conference on advanced communication technology, pp. 779-783, IEEE, 2014.","DOI":"10.1109\/ICACT.2014.6779068"},{"key":"ref50","doi-asserted-by":"crossref","unstructured":"M. Raghuram, K. Akshay, and K. Chandrasekaran, \u201cEfficient user profiling in twitter social network using traditional classifiers,\u201d in Advances in Intelligent Systems and Computing, pp. 399- 411, Springer International Publishing, 2015.","DOI":"10.1007\/978-3-319-23258-4_35"},{"key":"ref51","unstructured":"R. Bonnie, \u201cThe power of the persona.\u201d https:\/\/www.pragmaticinstitute.com\/resources\/articles\/product\/the-power-of-the-persona\/. Accessed: 2024\/4\/2."},{"key":"ref52","doi-asserted-by":"crossref","unstructured":"Y. Yao, J. Duan, K. Xu, Y. Cai, Z. Sun, and Y. Zhang, \u201cA survey on large language model (llm) security and privacy: The good, the bad, and the ugly,\u201d High-Confidence Computing, vol. 4, no. 2, p. 100211, 2024.","DOI":"10.1016\/j.hcc.2024.100211"},{"key":"ref53","doi-asserted-by":"crossref","unstructured":"K. Bostrom and G. Durrett, \u201cByte pair encoding is suboptimal for language model pretraining,\u201d in Findings of the Association for Computational Linguistics: EMNLP 2020, 2020.","DOI":"10.18653\/v1\/2020.findings-emnlp.414"},{"key":"ref54","unstructured":"P. Gage, \u201cA new algorithm for data compression,\u201d The C Users Journal, vol. 12, no. 2, pp. 23- 38, 1994."},{"key":"ref55","doi-asserted-by":"crossref","unstructured":"J. Zhan and et al., \u201cAn effective feature representation of web log data by leveraging byte pair encoding and tf-idf,\u201d in Proceedings of the ACM Turing Celebration Conference-China, pp. 1- 6, 2019.","DOI":"10.1145\/3321408.3321568"},{"key":"ref56","unstructured":"\u201cSummary of the tokenizers.\u201d https:\/\/huggingface.co\/docs\/transformers\/tokenizer_summary#summary-of-the-tokenizers. Accessed: 2024\/4\/2."},{"key":"ref57","unstructured":"Thomwolf, \u201cBpe tokenizers and spaces before words.\u201d https:\/\/discuss.huggingface.co\/t\/bpe-tokenizers-and-spaces-before-words\/475. Accessed: 2024\/4\/10."},{"key":"ref58","doi-asserted-by":"crossref","unstructured":"R. A. and S. Borah, \u201cStudy of various methods for tokenization,\u201d in Applications of Internet of Things, pp. 193-200, Springer Singapore, 2020.","DOI":"10.1007\/978-981-15-6198-6_18"},{"key":"ref59","doi-asserted-by":"crossref","unstructured":"X. Gutierrez-Vasques, C. Bentz, and T. Samard\u017ei\u0107, \u201cLanguages through the looking glass of bpe compression,\u201d Computational Linguistics, vol. 49, no. 4, pp. 943-1001, 2023.","DOI":"10.1162\/coli_a_00489"},{"key":"ref60","doi-asserted-by":"crossref","unstructured":"N. Tavabi and K. Lerman, \u201cPattern discovery in physiological data with byte pair encoding,\u201d in Multimodal AI in Healthcare, pp. 227-243, Springer International Publishing, 2022.","DOI":"10.1007\/978-3-031-14771-5_16"},{"key":"ref61","doi-asserted-by":"crossref","unstructured":"N. Fradet, N. Gutowski, F. Chhel, and J. Briot, \u201cByte pair encoding for symbolic music,\u201d in Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023.","DOI":"10.18653\/v1\/2023.emnlp-main.123"},{"key":"ref62","doi-asserted-by":"crossref","unstructured":"H. Liu, \u201cByte-pair and n-gram convolutional methods of analysing automatically disseminated content on social platforms,\u201d MDPI AG, 2020.","DOI":"10.20944\/preprints202004.0214.v1"},{"key":"ref63","doi-asserted-by":"crossref","unstructured":"N. Nilsson, Principles of Artificial Intelligence. Springer Berlin Heidelberg, 1982.","DOI":"10.1007\/978-3-662-09438-9"},{"key":"ref64","doi-asserted-by":"crossref","unstructured":"F. Harary, \u201cThe explosive growth of graph theory,\u201d Annals of the New York Academy of Sciences, vol. 328, no. 1, pp. 5-11, 1979.","DOI":"10.1111\/j.1749-6632.1979.tb17762.x"},{"key":"ref65","doi-asserted-by":"crossref","unstructured":"R. Tarjan, \u201cDepth-first search and linear graph algorithms,\u201d SIAM Journal on Computing, vol. 1, no. 2, pp. 146-160, 1972.","DOI":"10.1137\/0201010"},{"key":"ref66","doi-asserted-by":"crossref","unstructured":"C. Photphanloet and R. Lipikorn, \u201cPm10 concentration forecast using modified depth-first search and supervised learning neural network,\u201d Science of The Total Environment, vol. 727, p. 138507, 2020.","DOI":"10.1016\/j.scitotenv.2020.138507"},{"key":"ref67","doi-asserted-by":"crossref","unstructured":"S. Rahmani, S. Fakhrahmad, and M. Sadreddini, \u201cCo-occurrence graph-based context adaptation: a new unsupervised approach to word sense disambiguation,\u201d Digital Scholarship in the Humanities, vol. 36, no. 2, pp. 449-471, 2020.","DOI":"10.1093\/llc\/fqz048"},{"key":"ref68","doi-asserted-by":"crossref","unstructured":"Y. Du, F. Li, T. Zheng, and J. Li, \u201cFast cascading outage screening based on deep convolutional neural network and depth-first search,\u201d IEEE Transactions on Power Systems, vol. 35, no. 4, pp. 2704-2715, 2020.","DOI":"10.1109\/TPWRS.2020.2969956"},{"key":"ref69","doi-asserted-by":"crossref","unstructured":"Q. Mei and M. G\u00fcl, \u201cMulti-level feature fusion in densely connected deep-learning architecture and depth-first search for crack segmentation on images collected with smartphones,\u201d Structural Health Monitoring, vol. 19, no. 6, pp. 1726-1744, 2020.","DOI":"10.1177\/1475921719896813"},{"key":"ref70","doi-asserted-by":"crossref","unstructured":"A. Syah, F. Helmiah, N. Irawati, and N. Hasibuan, \u201cDepth first search algorithm in the expert system for diagnosis of palm oil growth obstacles,\u201d in 4TH INTERNATIONAL CONFERENCE ON CURRENT TRENDS IN MATERIALS SCIENCE AND ENGINEERING 2022, 2024.","DOI":"10.1063\/5.0205513"},{"key":"ref71","doi-asserted-by":"crossref","unstructured":"G. Logeswari, S. Bose, and T. Anitha, \u201cAn intrusion detection system for sdn using machine learning,\u201d Intelligent Automation & Soft Computing, vol. 35, no. 1, pp. 867-880, 2023.","DOI":"10.32604\/iasc.2023.026769"},{"key":"ref72","doi-asserted-by":"crossref","unstructured":"W. Cai, R. Wei, L. Xu, and X. Ding, \u201cA method for modelling greenhouse temperature using gradient boost decision tree,\u201d Information Processing in Agriculture, vol. 9, no. 3, pp. 343-354, 2022.","DOI":"10.1016\/j.inpa.2021.08.004"},{"key":"ref73","unstructured":"G. Ke and et al., \u201cLightgbm: A highly efficient gradient boosting decision tree,\u201d in Advances in neural information processing systems, vol. 30, 2017."},{"key":"ref74","doi-asserted-by":"crossref","unstructured":"B. Wardani, S. Sa\u2019adah, and D. Nurjanah, \u201cMeasuring and mitigating bias in bank customers data with xgboost, lightgbm, and random forest algorithm,\u201d Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI), vol. 9, no. 1, pp. 142-155, 2023.","DOI":"10.26555\/jiteki.v9i1.25768"},{"key":"ref75","doi-asserted-by":"crossref","unstructured":"Y. Hua, \u201cAn efficient traffic classification scheme using embedded feature selection and lightgbm,\u201d in 2020 Information Communication Technologies Conference (ICTC), 2020.","DOI":"10.1109\/ICTC49638.2020.9123302"},{"key":"ref76","doi-asserted-by":"crossref","unstructured":"N. Chawla, K. Bowyer, L. Hall, andW. Kegelmeyer, \u201cSmote: synthetic minority over-sampling technique,\u201d Journal of artificial intelligence research, vol. 16, pp. 321-357, 2002.","DOI":"10.1613\/jair.953"},{"key":"ref77","doi-asserted-by":"crossref","unstructured":"J. Ponsam, S. Gracia, G. Geetha, S. Karpaselvi, and K. Nimala, \u201cCredit risk analysis using lightgbm and a comparative study of popular algorithms,\u201d in 2021 4th International Conference on Computing and Communications Technologies (ICCCT), 2021.","DOI":"10.1109\/ICCCT53315.2021.9711896"},{"key":"ref78","doi-asserted-by":"crossref","unstructured":"Y. Wong, K. Madhavan, and N. Elmqvist, \u201cTowards characterizing domain experts as a user group,\u201d in 2018 IEEE Evaluation and Beyond-Methodological Approaches for Visualization (BELIV), pp. 1-10, 2018.","DOI":"10.1109\/BELIV.2018.8634026"},{"key":"ref79","doi-asserted-by":"crossref","unstructured":"P. Fadde and P. Sullivan, \u201cDeveloping expertise and expert performance,\u201d in Handbook of Research in Educational Communications and Technology: Learning Design, pp. 53-72, 2020.","DOI":"10.1007\/978-3-030-36119-8_4"},{"key":"ref80","unstructured":"K. Chandrasekaran, Domain-Driven Design with Java - A Practitioner\u2019s Guide: Create simple, elegant, and valuable software solutions for complex business problems. Packt Publishing, 2021. https:\/\/ddd-practitioners.com\/home\/glossary\/domain-expert\/."},{"key":"ref81","doi-asserted-by":"crossref","unstructured":"Vujovi\u0107, \u201cClassification model evaluation metrics,\u201d International Journal of Advanced Computer Science and Applications, vol. 12, no. 6, 2021.","DOI":"10.14569\/IJACSA.2021.0120670"},{"key":"ref82","unstructured":"T. Saito and M. Rehmsmeier, \u201cBasic evaluation measures from the confusion matrix.\u201d https:\/\/classeval.wordpress.com\/introduction\/basic-evaluation-measures\/, 2017."},{"key":"ref83","doi-asserted-by":"crossref","unstructured":"P. Le, M. Nauta, V. Nguyen, S. Pathak, J. Schl\u00f6tterer, and C. Seifert, \u201cBenchmarking explainable ai - a survey on available toolkits and open challenges,\u201d in Proceedings of the Thirty- Second International Joint Conference on Artificial Intelligence, 2023.","DOI":"10.24963\/ijcai.2023\/747"},{"key":"ref84","doi-asserted-by":"crossref","unstructured":"A. Holzinger, \u201cFrom machine learning to explainable ai,\u201d in 2018 World Symposium on Digital Intelligence for Systems and Machines (DISA), 2018.","DOI":"10.1109\/DISA.2018.8490530"},{"key":"ref85","doi-asserted-by":"crossref","unstructured":"Z. Lipton, \u201cThe mythos of model interpretability,\u201d Queue, vol. 16, no. 3, pp. 31-57, 2018.","DOI":"10.1145\/3236386.3241340"},{"key":"ref86","unstructured":"C. Molnar, Interpretable machine learning. Lulu.com, 2020."},{"key":"ref87","unstructured":"J. Karkavelraja, \u201cAmazon sales dataset.\u201d https:\/\/www.kaggle.com\/datasets\/karkavelrajaj\/amazon-sales-dataset. Accessed: 2024\/4\/2."},{"key":"ref88","doi-asserted-by":"crossref","unstructured":"A. Gupta, A. Raghav, and S. Srivastava, \u201cComparative study of machine learning algorithms for portuguese bank data,\u201d in 2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), 2021.","DOI":"10.1109\/ICCCIS51004.2021.9397083"},{"key":"ref89","unstructured":"Lavanya, \u201cGoogle play store apps.\u201d https:\/\/www.kaggle.com\/datasets\/lava18\/google-play-store-apps. Accessed: 2024\/4\/10."},{"key":"ref90","unstructured":"P. Lokesh, \u201cAmazon products sales dataset 2023.\u201d https:\/\/www.kaggle.com\/datasets\/lokeshparab\/amazon-products-dataset. Accessed: 2024\/4\/2."},{"key":"ref91","unstructured":"D. Chen, \u201cOnline retail.\u201d UCI Machine Learning Repository, 2015."},{"key":"ref92","unstructured":"\u201cPersonal data protection act.\u201d https:\/\/law.moj.gov.tw\/LawClass\/LawAll.aspx?PCODE=G0380233. Accessed: 2024\/4\/2."},{"key":"ref93","unstructured":"\u201cBanking act.\u201d https:\/\/law.fsc.gov.tw\/LawContent.aspx?id=GL000624. Accessed: 2024\/4\/2."},{"key":"ref94","doi-asserted-by":"crossref","unstructured":"A. Caramazza and J. Shelton, \u201cDomain-specific knowledge systems in the brain: The animateinanimate distinction,\u201d Journal of Cognitive Neuroscience, vol. 10, no. 1, pp. 1-34, 1998.","DOI":"10.1162\/089892998563752"}],"container-title":["Computer Science and Information Systems"],"original-title":[],"language":"en","deposited":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T12:36:42Z","timestamp":1763987802000},"score":1,"resource":{"primary":{"URL":"https:\/\/doiserbia.nb.rs\/Article.aspx?ID=1820-02142500068L"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":94,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.2298\/csis241130068l","relation":{},"ISSN":["1820-0214","2406-1018"],"issn-type":[{"type":"print","value":"1820-0214"},{"type":"electronic","value":"2406-1018"}],"subject":[],"published":{"date-parts":[[2025]]}}}