[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122074-en":3,"doc-seo-122074-105":30,"detail-sidebar-cat-0-en-105":91},{"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},122074,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Machine Learning in Financial Decision Making - Optimizing Payment Conversion Rate","This thesis investigates how machine learning can strengthen financial decision-making by improving payment conversion rates. It builds a machine learning pipeline that combines historical and newly collected transactional data to predict the best transaction routing path, targeting higher approval rates while reducing operational costs. The work is carried out in collaboration with PayXpert, focusing on challenges common in real payment systems. Results compare neural networks with random forests for accuracy, interpretability, and efficiency, while addressing imbalanced datasets and new acquirer integration through incremental learning and synthetic data generation.","MACHINE LEARNING IN FINANCIAL DECISION MAKING: OPTIMIZING PAYMENT CONVERSION  \nRATE  \nTOMÀS TREVIÑO GUTIÉRREZ  \nThesis supervisor  \nLAURA MARTÍN GONZÁLEZ (PAYXPERT SPAIN, S. L. ) Tutor: ARGIMIRO ARRATIA QUESADA (Department of Computer Science)  \nDegree  \nBachelor's Degree in Informatics Engineering (Computing)  \nBachelor's thesis  \nFacultat d'Informàtica de Barcelona (FIB) Universitat Politècnica de Catalunya (UPC) -BarcelonaTech  \n25/06/2024  \nAbstract  \nThis thesis explores the integration of machine learning techniques in financial decision-making to enhance payment conversion rates. The study focuses on the development of a machine learning pipeline that leverages both historical and newly collected transactional data to predict the optimal routing path for transactions, thereby maximizing approval rates and minimizing costs.  \nThe research is conducted in collaboration with PayXpert, a fintech company specializing in payment services for online and retail merchants across Europe.  \nKey findings indicate that while neural networks provide the highest accuracy, random forests offer a balanced performance with better interpretability and efficiency, making them suitable for initial deployment. The study also addresses the challenges of imbalanced datasets and the integration of new acquirers into the system, proposing techniques such as incremental learning and synthetic data generation to maintain model robustness.  \nAcknowledgments  \nI’m grateful to my tutor, Argimiro Arratia Quesada from the Department of Computer Science, for his help in the occasions I’ve asked for it, and to Francesc Xavier Bellés Ros, my GEP tutor, for his feedback and support during the initial stages of the thesis.  \nI want to thank as well my thesis supervisor, Laura Martín González, for her great predisposition and helpfullness in becoming my director despite just recently having joined the company.  \nI would like to acknowledge the support of PayXpert, the company that provided the practical framework for this thesis, and my colleagues for their cooperation and insights.  \nA special mention to my partner, Idoia Torralba, for her unwavering support and patience during these intense months, and for making the journey all the more beautiful and enjoyable.  \nLastly, I would like to thank my sister Sara for being a huge foundation in my life, and my family and friends for their unwavering support and encouragement, without which this work would not have been possible.  \nContents  \n1 Context and scope 7  \n1.1 Introduction and contextualization ....................... 7  \n1.1.1 Context .................................. 7  \n1.1.2 Concepts .................................. 9  \n1.1.3 Problem to be solved ........................... 10  \n1.1.4 Stakeholders ................................ 11  \n1.2 Justification .................................... 12  \n1.3 Scope ....................................... 13  \n1.3.1 Objectives and sub-objectives ...................... 13  \n1.3.2 Requirements ............................... 13  \n1.3.3 Potential obstacles and risks ....................... 14  \n1.4 Methodology and rigor .............................. 14  \n1.4.1 Methodology ............................... 15  \n1.4.2 Monitoring tools and validation ..................... 16  \n2 Temporal planning 17  \n2.1 Task definition .................................. 17  \n2.1.1 Literature Review and Theoretical Framework Development ..... 17  \n2.1.2 Data Collection and Preprocessing ................... 18  \n2.1.3 Exploratory Data Analysis (EDA) .................... 18  \n2.1.4 Model Selection and Development .................... 19  \n2.1.5 Model Training and Validation ..................... 20  \n2.1.6 System Integration and Testing ..................... 20  \n2.1.7 Documentation and Reporting ...................... 21  \n2.1.8 Presentation Preparation ......................... 22  \n2.2 Gantt chart .................................... 25  \n2.3 Risk management ......................","cbCaiqYkNN38hXtW","https://ap.wps.com/l/cbCaiqYkNN38hXtW","pdf",769290,1,48,"English","en",105,"# Context and scope\n## Introduction and contextualization\n## Justification\n## Scope\n## Methodology and rigor\n# Temporal planning\n## Task definition\n## Gantt chart\n## Risk management\n# Data balance and new acquirers\n## Balancing the Dataset\n## Dealing with New Possible Acquirers\n## Results and Analysis\n## Conclusion\n# Model selection\n## Decision tree\n## Random forest\n## XGBoost\n## Neural network\n## Experiment and results\n## Model comparison and final decision\n# Budget\n## Cost Identification\n## Summary of Costs\n## Budgetary and Timeline Control\n## Performance Monitoring and Adjustments\n## Reporting and Agile Adjustments\n# Sustainability Considerations\n## Environmental Sustainability\n## Economic Sustainability\n## Social Sustainability\n# Conclusions\n## Key Findings","[{\"question\":\"What is the main goal of the thesis?\",\"answer\":\"To integrate machine learning into financial decision-making to enhance payment conversion rates by predicting an optimal transaction routing path.\"},{\"question\":\"How does the thesis use data to make predictions?\",\"answer\":\"It leverages both historical and newly collected transactional data to train a pipeline that selects the best routing path for transactions.\"},{\"question\":\"Which models are compared and what trade-offs are highlighted?\",\"answer\":\"Neural networks achieve the highest accuracy, while random forests provide a balanced performance with better interpretability and efficiency for initial deployment.\"}]","Machine Learning in Financial Decision Making - Optimizing Payment Conversion Rate | PDF",1785808699,121,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-in-financial-decision-making-optimizing-payment-conversion-rate","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-in-financial-decision-making-optimizing-payment-conversion-rate/122074/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main goal of the thesis?","Question",{"text":75,"@type":76},"To integrate machine learning into financial decision-making to enhance payment conversion rates by predicting an optimal transaction routing path.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis use data to make predictions?",{"text":80,"@type":76},"It leverages both historical and newly collected transactional data to train a pipeline that selects the best routing path for transactions.",{"name":82,"@type":73,"acceptedAnswer":83},"Which models are compared and what trade-offs are highlighted?",{"text":84,"@type":76},"Neural networks achieve the highest accuracy, while random forests provide a balanced performance with better interpretability and efficiency for initial deployment.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]