[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120260-en":3,"doc-seo-120260-105":30,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120260,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Machine learning for detection of fraudulent financial transactions - Reviewer’s assessment - Bachelor Project","Reviewer’s assessment of a bachelor project on machine learning for detecting fraudulent financial transactions, covering topic difficulty, fulfillment of assignment requirements, and suitability of the chosen solution. The work is judged well-constructed with high professional quality, good English, and appropriate citations. Key reservations include handling of imbalanced datasets, synthetic-data evaluation choices, and the need for more informative experiments such as PR curves, balanced class weights, computation-time comparisons, and better dataset diversity.","REVIEWER´S ASSESSMENT OF FINAL WORK  \nI. IDENTIFICATION DATA  \nTitle: Machine learning for detection of fraudulent financial transactions  \nAuthor´s name: Lydie Rosenkrancová  \nType of assignment: Bachelor Project  \nFaculty: Faculty of Nuclear Sciences and Physical Engineering (FNSPE)  \nDepartment: Department of Mathematics  \nReviewer: Ing. Jiří Minarčík, Ph. D.  \nReviewer´s affiliation: Resistant AI  \nII. ASSESSMENT OF CRITERIA  \n\n| Work assignment average\u003Cbr>Assess how demanding the work topic is. |\n| --- |\n| Both theoretical and technical difficulty is not very high, but appropriate for bachelor’s thesis. All used methods were standard and readily available in many open-source packages. While the application domain may not beas straightforward, the problem definition is standard and domain agnostic, with the only specific challenge being the handling of imbalanced dataset. |\n\n\n| Fulfilling the assignment fulfilled\u003Cbr>Consider whether the work submitted meets the assignment. If necessary, give your comments on items of the assignment not fully answered, or judge whether the scope of the assignment has been broadened. If student failed to fully treat the assignment, try to assess the importance, impact and/or the reasons for the failings. |\n| --- |\n| All points of the assignment were fulfilled. |\n\n\n| Chosen approach to solution appropriate with reservations\u003Cbr>Assess whether student applied a correct approach or method of solution. |\n| --- |\n| The choice of assessed methods and their modifications makes sense. As suggested in the conclusion, timebased splits would be more appropriate, but the approach is acceptable for synthetic data. It seems that oversampling would make more sense that undersampling as the former does not lead to loss of information from the train set. For the Kaggle dataset, it would be more useful to see PR curves and to use balanced class weights setting for SVM. It would be useful to see computation time comparison for the methods and as well as more implementation details. Otherwise, the experimental setup and its analysis is well constructed and explained. |\n\n\n| Professional standard excellent\u003Cbr>Assess the professional standard of the work, application of course knowledge, references, and data from practice. |\n| --- |\n| Overall, the thesis is well-constructed, with no sections feeling rushed, and it maintains a high level of professional quality throughout. |\n\n\n| Level of formality and of the language used average\u003Cbr>Assess the use of scientific formalism, the typography and language of the work. |\n| --- |\n| The text is well-written and the author demonstrated a good standard of English, with only minor inconsistencies between the U.S. and British spelling. The mathematical descriptions were also well presented, though some minor inconsistencies in notation (e.g. for the input data X or probability P) could be improved for better readability. The presented plots are generally of high quality and readable, although some, like those in Figure 2. 2, would benefit from larger and more consistent labels. |\n\nChoice of references, citation correctness excellent   \nREVIEWER´S ASSESSMENT OF FINAL WORK  \n\n| Assess student´s effort in finding and using study sources for completing their work. Give characteristics of the references chosen. Assess whether student made use of all the relevant sources. Verify whether all items used are properly distinguished from the results obtained by student and their deliberations, whether there are no violations of citation ethics, and whether the bibliography presented is complete and complies with the citation usage and standards. |\n| --- |\n| The prior work appears to be properly cited, with the author referencing several relevant books of high-quality, and correctly citing seminal papers for the used methods. Overall, the citation standard is appropriate.\u003Cbr>However, I would suggest the author seek out original data sources rather than citing Statista in [1] . |\n\n\n| Further","cbCaivrC4c0w4woL","https://ap.wps.com/l/cbCaivrC4c0w4woL","pdf",288063,1,2,"English","en",105,"# I. IDENTIFICATION DATA\n# II. ASSESSMENT OF CRITERIA\n## Work assignment average\n## Fulfilling the assignment fulfilled\n## Chosen approach to solution appropriate with reservations\n## Professional standard excellent\n## Level of formality and of the language used average\n## Choice of references, citation correctness excellent\n## Assess student´s effort in finding and using study sources\n## Further comments and assessment\n# III. OVERALL ASSESSMENT, QUESTIONS TO BE ASKED DURING THE WORK DEFENCE, SUGGESTED GRADE","[{\"question\":\"How demanding is the thesis topic according to the reviewer?\",\"answer\":\"The reviewer considers theoretical and technical difficulty not very high, but appropriate for a bachelor’s thesis. Methods were standard and widely available, with the main specific challenge being imbalanced data handling.\"},{\"question\":\"What reservations does the reviewer have about the chosen solution and experiments?\",\"answer\":\"The approach is acceptable for synthetic data, but time-based splits would be more appropriate. The reviewer suggests oversampling over undersampling, and recommends PR curves, balanced class weights for SVM, computation-time comparisons, and more implementation details.\"},{\"question\":\"What strengths and improvement suggestions are given regarding references and results?\",\"answer\":\"References are properly cited with high-quality books and correct seminal papers, though the reviewer suggests using original data sources instead of citing Statista. Results are considered interesting but limited by dataset diversity and quality.\"}]","Machine learning for detection of fraudulent financial transactions - Reviewer’s assessment - Bachelor Project | PDF",1785729082,5,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":28},"machine-learning-for-detection-of-fraudulent-financial-transactions-reviewers-assessment-bachelor-project","",{"@graph":36,"@context":84},[37,53,67],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":21},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/machine-learning-for-detection-of-fraudulent-financial-transactions-reviewers-assessment-bachelor-project/120260/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"How demanding is the thesis topic according to the reviewer?","Question",{"text":74,"@type":75},"The reviewer considers theoretical and technical difficulty not very high, but appropriate for a bachelor’s thesis. Methods were standard and widely available, with the main specific challenge being imbalanced data handling.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What reservations does the reviewer have about the chosen solution and experiments?",{"text":79,"@type":75},"The approach is acceptable for synthetic data, but time-based splits would be more appropriate. The reviewer suggests oversampling over undersampling, and recommends PR curves, balanced class weights for SVM, computation-time comparisons, and more implementation details.",{"name":81,"@type":72,"acceptedAnswer":82},"What strengths and improvement suggestions are given regarding references and results?",{"text":83,"@type":75},"References are properly cited with high-quality books and correct seminal papers, though the reviewer suggests using original data sources instead of citing Statista. Results are considered interesting but limited by dataset diversity and quality.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":105,"show_sort_weight":106,"slug":107},"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":46,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":46,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":29,"slug":136},19,"General","general"]