[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123395-en":3,"doc-seo-123395-105":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},123395,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Unveiling Customer Insights - An Interpretable Machine Learning Approach to Bank Telemarketing Data","Financial institutions play a key role in economic growth, and phone-based outreach remains widely used in banking despite digital alternatives. This study builds a model to predict customer applications from telemarketing campaigns using the publicly available Bank Marketing Data Set with strong class imbalance. It compares imbalanced treatments and categorical encodings across machine learning models, then applies interpretable methods to identify the drivers behind predictions. LightGBM with class weight and one-hot encoding achieves the highest AUC of 0.948; SHAP indicates economic-factor features dominate over individual customer attributes, while error analysis shows similar feature patterns can mislead the model.","Research Article  \nUnveiling Customer Insights: An Interpretable Machine Learning Approach to Bank Telemarketing Data  \nChin Lertvipada 1 and Sirisup Laohakiat2*  \nReceived: 10 March 2025  \nRevised: 21 July 2025  \nAccepted: 29 July 2025  \nABSTRACT  \nFinancial institutions play a vital role in driving the economy. Despite the advent of digital financial systems, phone-based product offerings remain popular in the banking sector. This study focuses on building a model to predict customer applications from telemarketing campaigns. By utilizing the publicly available Bank Marketing Data Set, which exhibits significant class imbalance, we explored various combinations of effective imbalanced treatments and categorical encodings in conjunction with machine learning models to identify the most optimal combination for prediction. Additionally, interpretable machine learning techniques were employed to delve into the critical features and the underlying reasoning behind the model's predictions. The experiment revealed that the LightGBM model with Class weight and One-hot encoding yielded the best AUC score of 0.948. Using SHAP to explain the model's behavior, we found that the features related to economic factors hold greater significance compared to individual customer attributes. Furthermore, error analysis on false negative instances demonstrated that the similarity of instance characteristics of some important features could mislead the models and result in inaccurate prediction. These findings shed light on the model's decision-making process and offer insights for enhancing prediction accuracy and understanding customer behavior in financial product applications. The results offer actionable guidance for optimizing business operations by enabling more efficient lead targeting, reducing resource waste in telemarketing efforts, and supporting data-driven decision-making in customer outreach strategies.  \nKeywords: Machine learning, Interpretable machine learning, Bank telemarketing, SHAP  \n1 Whitelabel and RTA, Agoda, Bangkok 10330, Thailand  \n2 Department of Computer Science, Faculty of Science, Srinakharinwirot University, Bangkok 10110, Thailand  \n􀀍 Corresponding author, email: [sirisup@g.swu.ac.th](sirisup@g.swu.ac.th)  \nIntroduction  \nFinancial institutions are pivotal to economic growth, and the ability to identify, attract, and retain depositors has long been a benchmark of operational success. Over the past decade, customer analytics has transformed this process—shifting marketing decisions from intuition‑driven initiatives to data‑driven, personalized outreach that spans segmentation, churn prediction, lifetime‑value estimation, and campaign optimization. Within this broader landscape, predicting telemarketing responses remains an area of high practical value, because direct phone contact is still one of the most cost‑effective acquisition channels for many banks.  \nDespite a gradual migration toward digital self‑service platforms, outbound calls continue to deliver strong conversion rates—provided that calls are placed to customers who are both eligible and receptive. Unsolicited calls to low‑propensity customers, on the other hand, incur monetary costs, waste staff time, and risk damaging brand reputation. Consequently, recent research has focused on machine‑learning methods that can score a lead list before dialing begins, thereby aligning telemarketing with the larger movement toward precision marketing in customer analytics.  \nPrevious telemarketing studies [1-8] have shown that tree‑based ensemble models outperform traditional logistic regression when all available features are used. Yet two key gaps persist. First, many of these studies rely on information that becomes available only after the first contact—such as “call duration”—rendering their models impractical for pre‑call lead screening. Second, most implementations are black boxes that offer little insight into why a particular customer is predicted to accept","cbCaivECwspxVAvD","https://ap.wps.com/l/cbCaivECwspxVAvD","pdf",1182196,1,22,"English","en",105,"# Abstract\n# Introduction\n## Telemarketing in customer analytics\n## Modeling gaps and limitations\n## Interpretable machine learning and SHAP\n## Related work and examples","[{\"question\":\"What is the document’s main goal?\",\"answer\":\"To build an interpretable machine learning model that predicts customer applications from bank telemarketing campaign data and identifies what drives those predictions.\"},{\"question\":\"Which approach performed best for prediction quality?\",\"answer\":\"The LightGBM model with class weight and one-hot encoding achieved the best AUC score of 0.948.\"},{\"question\":\"How does the study use interpretability to explain model decisions?\",\"answer\":\"It applies SHAP to quantify feature contributions at global and local levels, revealing that economic-factor features are more significant than individual customer attributes.\"}]","Unveiling Customer Insights - An Interpretable Machine Learning Approach to Bank Telemarketing Data | PDF",1785816272,55,{"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},"unveiling-customer-insights-an-interpretable-machine-learning-approach-to-bank-telemarketing-data","",{"@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/unveiling-customer-insights-an-interpretable-machine-learning-approach-to-bank-telemarketing-data/123395/",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 document’s main goal?","Question",{"text":75,"@type":76},"To build an interpretable machine learning model that predicts customer applications from bank telemarketing campaign data and identifies what drives those predictions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which approach performed best for prediction quality?",{"text":80,"@type":76},"The LightGBM model with class weight and one-hot encoding achieved the best AUC score of 0.948.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the study use interpretability to explain model decisions?",{"text":84,"@type":76},"It applies SHAP to quantify feature contributions at global and local levels, revealing that economic-factor features are more significant than individual customer attributes.","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"]