{"id":1040,"date":"2023-05-02T10:00:20","date_gmt":"2023-05-02T10:00:20","guid":{"rendered":"https:\/\/artelnics.com\/?post_type=case_studies&#038;p=1040"},"modified":"2026-11-09T11:37:58","modified_gmt":"2026-11-09T11:37:58","slug":"banking-sector-case","status":"publish","type":"case_studies","link":"https:\/\/artelnics.com\/case_studies\/banking-sector-case\/","title":{"rendered":"Increasing sales of telemarketing campaigns in a bank"},"content":{"rendered":"<div class=\"aui aui-content-page artelnics-shared-page\" data-artelnics-shared-content>\n<article class=\"artelnics-shared-case\">\n<p class=\"artelnics-shared-case-lead\">Predictive customer targeting helps a bank focus telemarketing campaigns on the customers most likely to purchase.<\/p>\n<div class=\"artelnics-shared-case-meta\"><span class=\"artelnics-shared-case-tag\">Banking<\/span><span class=\"artelnics-shared-case-tag\">Predictive targeting<\/span><span class=\"artelnics-shared-case-tag\">Campaign optimization<\/span><\/div>\n<h2>Challenge<\/h2>\n<p>The bank wanted to improve telemarketing effectiveness as repeated campaigns increased costs and customer rejections. Its previous campaign success rate was 1%, making better customer selection a priority.<\/p>\n<h2>Data<\/h2>\n<p>The dataset contained 1,000,000 customers and 500 features covering personal information, accounts, products, insurance and transaction activity. The target recorded whether a customer purchased in a previous campaign.<\/p>\n<ul>\n<li>Personal variables: sex, age and nationality.<\/li>\n<li>Account variables: balances and credit card debt.<\/li>\n<li>Product variables: mortgages and car leasing.<\/li>\n<li>Insurance variables: life and home insurance.<\/li>\n<li>Transaction variables: cash point and website usage.<\/li>\n<\/ul>\n<h2>Solution<\/h2>\n<p>Artelnics analyzed relationships between customer features and campaign outcomes, then built an artificial neural network to rank customers by purchase probability.<\/p>\n<p>Individual correlations were below 10%, indicating that targeting required multiple variables. The strongest relationships involved the number of services held, recent cash point activity and life insurance, highlighting the relevance of customer engagement.<\/p>\n<div class=\"aui-card-grid aui-grid-two\">\n<div class=\"aui-card\"><strong>Model<\/strong><\/p>\n<p>Artificial neural network for purchase propensity.<\/p>\n<\/div>\n<div class=\"aui-card\"><strong>Targeting<\/strong><\/p>\n<p>Customers ranked by their likelihood of conversion.<\/p>\n<\/div>\n<\/div>\n<h2>Results<\/h2>\n<p>The analysis indicated that selecting the right customers could increase conversion from 1% to 2.5%\u2014from one purchase per 100 contacts to one per 40 contacts.<\/p>\n<p>The cumulative gain analysis showed that contacting the 30% of customers most likely to purchase could capture 80% of total sales.<\/p>\n<p>A profit scenario assumed a \u20ac5 cost per contact and a \u20ac1,000 benefit per purchase. Under those assumptions, contacting the highest-ranked 35% of customers produced a projected maximum benefit of \u20ac750,000, compared with \u20ac125,000 without the model.<\/p>\n<h2>Illustrations<\/h2>\n<figure><img decoding=\"async\" src=\"https:\/\/artelnics.com\/wp-content\/uploads\/2023\/08\/logistic-correlations-bank.webp\" alt=\"Logistic correlations between the input variables and the output variable\" \/><figcaption>Logistic correlations between the input variables and the output variable<\/figcaption><\/figure>\n<figure><img decoding=\"async\" src=\"https:\/\/artelnics.com\/wp-content\/uploads\/2023\/08\/bank-neural-network.png\" alt=\"Customer targeting neural network\" \/><figcaption>Customer targeting neural network<\/figcaption><\/figure>\n<figure><img decoding=\"async\" src=\"https:\/\/artelnics.com\/wp-content\/uploads\/2023\/08\/cummulative-gain-chart-bank.jpg\" alt=\"Cummulative gain chart\" \/><figcaption>Cummulative gain chart<\/figcaption><\/figure>\n<figure><img decoding=\"async\" src=\"https:\/\/artelnics.com\/wp-content\/uploads\/2023\/08\/profit-chart-bank.jpg\" alt=\"Profit chart\" \/><figcaption>Profit chart<\/figcaption><\/figure>\n<\/article>\n<nav class=\"artelnics-shared-related\" aria-label=\"Case study actions\">\n<div><strong>Have a similar challenge?<\/strong><span>Artelnics can help turn operational data into a practical AI system.<\/span><\/div>\n<div class=\"aui-actions artelnics-shared-related-actions\"><a class=\"aui-button aui-button--secondary\" href=\"\/case_studies\/\">View all projects<\/a><a class=\"aui-button\" href=\"\/contact\/\">Talk to us<\/a><\/div>\n<\/nav>\n\n\n<\/div>","protected":false},"excerpt":{"rendered":"<p>Predictive customer targeting helps a bank focus telemarketing campaigns on the customers most likely to purchase.<\/p>\n","protected":false},"featured_media":624,"parent":0,"menu_order":0,"template":"","categories":[],"class_list":["post-1040","case_studies","type-case_studies","status-publish","has-post-thumbnail","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/artelnics.com\/api\/wp\/v2\/case_studies\/1040","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/artelnics.com\/api\/wp\/v2\/case_studies"}],"about":[{"href":"https:\/\/artelnics.com\/api\/wp\/v2\/types\/case_studies"}],"version-history":[{"count":14,"href":"https:\/\/artelnics.com\/api\/wp\/v2\/case_studies\/1040\/revisions"}],"predecessor-version":[{"id":3371,"href":"https:\/\/artelnics.com\/api\/wp\/v2\/case_studies\/1040\/revisions\/3371"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/artelnics.com\/api\/wp\/v2\/media\/624"}],"wp:attachment":[{"href":"https:\/\/artelnics.com\/api\/wp\/v2\/media?parent=1040"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/artelnics.com\/api\/wp\/v2\/categories?post=1040"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}