{"id":528,"date":"2013-11-04T21:49:29","date_gmt":"2013-11-04T20:49:29","guid":{"rendered":"http:\/\/data-science.ch\/?p=528"},"modified":"2014-06-20T14:28:22","modified_gmt":"2014-06-20T12:28:22","slug":"selecting-customers-by-their-lifetime-value","status":"publish","type":"post","link":"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/","title":{"rendered":"Selecting Customers by their Lifetime Value"},"content":{"rendered":"<div align=\"justify\">\n<p><a href=\"http:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/COLOURBOX7764582_small.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"alignleft wp-image-710 size-medium\" src=\"http:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/COLOURBOX7764582_small-300x300.jpg\" alt=\"Back view of businesswoman\" width=\"300\" height=\"300\" srcset=\"https:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/COLOURBOX7764582_small-300x300.jpg 300w, https:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/COLOURBOX7764582_small-150x150.jpg 150w, https:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/COLOURBOX7764582_small.jpg 950w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a>In business, especially marketing, it is often necessary to perform customer selection. The typical task involves defining a set of customers for upselling, cross-selling or retention actions. Traditionally, the selection criterion is the positive response probability. While this identifies customers who are the most likely to respond, it does not necessarily provide the optimal solution from which the business profits the most.<\/p>\n<p>Over the last years, the concept of <i>customer lifetime value<\/i> (CLV) has attracted increasing attention. It suggests rating and selecting the customers by the present value of all future revenues that are attributed to their relationship. Hence, the focus lies on customer quality, rather than customer quantity. While this may sound logical, it provides a huge analytical challenge: the CLV is driven by the future behavior of a customer, which of course is not known in advance. Predictive analytics can and needs to be used for modeling customer dynamics, and often big data is involved.<\/p>\n<p><!--more--><\/p>\n<p><strong>Novel Semi-Markov Model Approach<\/strong><\/p>\n<p>Members of the Datalab at ZHAW developed a scalable framework based on Semi-Markov models (SMM) which can be used for structured CLV estimation. The basis of this approach lies in partitioning the customers into a space with several (usually 2-20) distinct states. This allows for differentiated lifetime models, transition probabilities and revenue distributions. We illustrate the concept with an example of a CLV system implemented for a telecommunication company in Switzerland. The states are as follows:<\/p>\n<p style=\"text-align: center\"><a href=\"http:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/state-space.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-large wp-image-683\" src=\"http:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/state-space-1024x614.png\" alt=\"state-space\" width=\"584\" height=\"350\" srcset=\"https:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/state-space-1024x614.png 1024w, https:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/state-space-300x180.png 300w, https:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/state-space-500x300.png 500w, https:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/state-space.png 1888w\" sizes=\"auto, (max-width: 584px) 100vw, 584px\" \/><\/a><\/p>\n<p>Now for each of these states, we require a state-specific<\/p>\n<ul>\n<li>prediction model providing each individual&#8217;s soujourn time<\/li>\n<li>prediction model providing each individual&#8217;s transition probabilities<\/li>\n<li>prediction model providing each individual&#8217;s revenue<\/li>\n<\/ul>\n<p>Hence the SMM-based CLV computation for the present example requires a fair number of prediction models. Most of them rely on numerous features which besides socio-demographic data contain the full details of past product usage. This can and does involve data from billions of connections and therefore definitely marks a big data task. Once all parameters for a customer are estimated, his\/her CLV can be computed in closed form, based on SMM algebra.<\/p>\n<p><strong>Challenges in the Practical Implementation<\/strong><\/p>\n<p>However, neither for the customer relationship manager, nor for the data analyst the task is finished once the CLV estimation framework is set up: it needs to be applied in regular intervals (typically monthly or weekly), for being able to track customer movements, changes in customer behavior, et cetera. Completely rebuilding all prediction models would be much too time consuming and fortunately also did not prove to be necessary. The canonical approach is to just keep the current models running in a non-reviewed fashion and have them reproduce their output. While this usually works for short horizons, the models degrade in quality over shorter or longer time spans. This creates the need for an automatic system that produces the necessary output, but also monitors the output quality and sets a red flag if human interaction is required. However, the challenges of building and operating such an automatic system will be discussed in a future blog post on this site.<\/p>\n<\/div>\n<p><!--more--><\/p>\n<p><!--more--><\/p>\n<p><!--more--><\/p>\n<p><!--more--><\/p>\n<p><!--more--><\/p>\n<p><!--more--><\/p>\n<p><!--more--><\/p>\n<p><!--more--><\/p>\n<div class=\"pt-sm\">Schlagw\u00f6rter: <a href=\"https:\/\/blog.zhaw.ch\/datascience\/tag\/analytical-crm\/\">Analytical CRM<\/a>, <a href=\"https:\/\/blog.zhaw.ch\/datascience\/tag\/big-data\/\">Big Data<\/a>, <a href=\"https:\/\/blog.zhaw.ch\/datascience\/tag\/predictive-analytics\/\">Predictive Analytics<\/a><br><\/div>","protected":false},"excerpt":{"rendered":"<p>In business, especially marketing, it is often necessary to perform customer selection. The typical task involves defining a set of customers for upselling, cross-selling or retention actions. Traditionally, the selection criterion is the positive response probability. While this identifies customers who are the most likely to respond, it does not necessarily provide the optimal solution [&hellip;]<\/p>\n","protected":false},"author":40,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"ngg_post_thumbnail":0,"footnotes":""},"categories":[7,9],"tags":[15,3,16],"features":[],"class_list":["post-528","post","type-post","status-publish","format-standard","hentry","category-blog","category-research","tag-analytical-crm","tag-big-data","tag-predictive-analytics"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v27.2 (Yoast SEO v27.2) - https:\/\/yoast.com\/product\/yoast-seo-premium-wordpress\/ -->\n<title>Selecting Customers by their Lifetime Value - Data Science made in Switzerland<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Selecting Customers by their Lifetime Value\" \/>\n<meta property=\"og:description\" content=\"In business, especially marketing, it is often necessary to perform customer selection. The typical task involves defining a set of customers for upselling, cross-selling or retention actions. Traditionally, the selection criterion is the positive response probability. While this identifies customers who are the most likely to respond, it does not necessarily provide the optimal solution [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/\" \/>\n<meta property=\"og:site_name\" content=\"Data Science made in Switzerland\" \/>\n<meta property=\"article:published_time\" content=\"2013-11-04T20:49:29+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2014-06-20T12:28:22+00:00\" \/>\n<meta property=\"og:image\" content=\"http:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/COLOURBOX7764582_small-300x300.jpg\" \/>\n<meta name=\"author\" content=\"dtli\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"dtli\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/\"},\"author\":{\"name\":\"dtli\",\"@id\":\"https:\/\/blog.zhaw.ch\/datascience\/#\/schema\/person\/8d00a2cdae359611857df4ea2af34578\"},\"headline\":\"Selecting Customers by their Lifetime Value\",\"datePublished\":\"2013-11-04T20:49:29+00:00\",\"dateModified\":\"2014-06-20T12:28:22+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/\"},\"wordCount\":514,\"image\":{\"@id\":\"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/#primaryimage\"},\"thumbnailUrl\":\"http:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/COLOURBOX7764582_small-300x300.jpg\",\"keywords\":[\"Analytical CRM\",\"Big Data\",\"Predictive Analytics\"],\"articleSection\":[\"Blog\",\"Research\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/\",\"url\":\"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/\",\"name\":\"Selecting Customers by their Lifetime Value - Data Science made in Switzerland\",\"isPartOf\":{\"@id\":\"https:\/\/blog.zhaw.ch\/datascience\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/#primaryimage\"},\"thumbnailUrl\":\"http:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/COLOURBOX7764582_small-300x300.jpg\",\"datePublished\":\"2013-11-04T20:49:29+00:00\",\"dateModified\":\"2014-06-20T12:28:22+00:00\",\"author\":{\"@id\":\"https:\/\/blog.zhaw.ch\/datascience\/#\/schema\/person\/8d00a2cdae359611857df4ea2af34578\"},\"breadcrumb\":{\"@id\":\"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/#primaryimage\",\"url\":\"https:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/COLOURBOX7764582_small.jpg\",\"contentUrl\":\"https:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/COLOURBOX7764582_small.jpg\",\"width\":950,\"height\":950},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Startseite\",\"item\":\"https:\/\/blog.zhaw.ch\/datascience\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Selecting Customers by their Lifetime Value\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/blog.zhaw.ch\/datascience\/#website\",\"url\":\"https:\/\/blog.zhaw.ch\/datascience\/\",\"name\":\"Data Science made in Switzerland\",\"description\":\"Ein Blog der ZHAW Z\u00fcrcher Hochschule f\u00fcr Angewandte Wissenschaften\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/blog.zhaw.ch\/datascience\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/blog.zhaw.ch\/datascience\/#\/schema\/person\/8d00a2cdae359611857df4ea2af34578\",\"name\":\"dtli\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/secure.gravatar.com\/avatar\/6410e2156f5cdcba8b0ac2ba0bd1ff69f66812c19ab9eeaa807485a8f3ccbffc?s=96&d=mm&r=g\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/6410e2156f5cdcba8b0ac2ba0bd1ff69f66812c19ab9eeaa807485a8f3ccbffc?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/6410e2156f5cdcba8b0ac2ba0bd1ff69f66812c19ab9eeaa807485a8f3ccbffc?s=96&d=mm&r=g\",\"caption\":\"dtli\"},\"url\":\"https:\/\/blog.zhaw.ch\/datascience\/author\/dtli\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Selecting Customers by their Lifetime Value - Data Science made in Switzerland","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/","og_locale":"en_US","og_type":"article","og_title":"Selecting Customers by their Lifetime Value","og_description":"In business, especially marketing, it is often necessary to perform customer selection. The typical task involves defining a set of customers for upselling, cross-selling or retention actions. Traditionally, the selection criterion is the positive response probability. While this identifies customers who are the most likely to respond, it does not necessarily provide the optimal solution [&hellip;]","og_url":"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/","og_site_name":"Data Science made in Switzerland","article_published_time":"2013-11-04T20:49:29+00:00","article_modified_time":"2014-06-20T12:28:22+00:00","og_image":[{"url":"http:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/COLOURBOX7764582_small-300x300.jpg","type":"","width":"","height":""}],"author":"dtli","twitter_card":"summary_large_image","twitter_misc":{"Written by":"dtli","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/#article","isPartOf":{"@id":"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/"},"author":{"name":"dtli","@id":"https:\/\/blog.zhaw.ch\/datascience\/#\/schema\/person\/8d00a2cdae359611857df4ea2af34578"},"headline":"Selecting Customers by their Lifetime Value","datePublished":"2013-11-04T20:49:29+00:00","dateModified":"2014-06-20T12:28:22+00:00","mainEntityOfPage":{"@id":"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/"},"wordCount":514,"image":{"@id":"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/#primaryimage"},"thumbnailUrl":"http:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/COLOURBOX7764582_small-300x300.jpg","keywords":["Analytical CRM","Big Data","Predictive Analytics"],"articleSection":["Blog","Research"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/","url":"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/","name":"Selecting Customers by their Lifetime Value - Data Science made in Switzerland","isPartOf":{"@id":"https:\/\/blog.zhaw.ch\/datascience\/#website"},"primaryImageOfPage":{"@id":"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/#primaryimage"},"image":{"@id":"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/#primaryimage"},"thumbnailUrl":"http:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/COLOURBOX7764582_small-300x300.jpg","datePublished":"2013-11-04T20:49:29+00:00","dateModified":"2014-06-20T12:28:22+00:00","author":{"@id":"https:\/\/blog.zhaw.ch\/datascience\/#\/schema\/person\/8d00a2cdae359611857df4ea2af34578"},"breadcrumb":{"@id":"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/#primaryimage","url":"https:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/COLOURBOX7764582_small.jpg","contentUrl":"https:\/\/blog.zhaw.ch\/datascience\/files\/2013\/11\/COLOURBOX7764582_small.jpg","width":950,"height":950},{"@type":"BreadcrumbList","@id":"https:\/\/blog.zhaw.ch\/datascience\/selecting-customers-by-their-lifetime-value\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Startseite","item":"https:\/\/blog.zhaw.ch\/datascience\/"},{"@type":"ListItem","position":2,"name":"Selecting Customers by their Lifetime Value"}]},{"@type":"WebSite","@id":"https:\/\/blog.zhaw.ch\/datascience\/#website","url":"https:\/\/blog.zhaw.ch\/datascience\/","name":"Data Science made in Switzerland","description":"Ein Blog der ZHAW Z\u00fcrcher Hochschule f\u00fcr Angewandte Wissenschaften","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/blog.zhaw.ch\/datascience\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/blog.zhaw.ch\/datascience\/#\/schema\/person\/8d00a2cdae359611857df4ea2af34578","name":"dtli","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/6410e2156f5cdcba8b0ac2ba0bd1ff69f66812c19ab9eeaa807485a8f3ccbffc?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/6410e2156f5cdcba8b0ac2ba0bd1ff69f66812c19ab9eeaa807485a8f3ccbffc?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/6410e2156f5cdcba8b0ac2ba0bd1ff69f66812c19ab9eeaa807485a8f3ccbffc?s=96&d=mm&r=g","caption":"dtli"},"url":"https:\/\/blog.zhaw.ch\/datascience\/author\/dtli\/"}]}},"_links":{"self":[{"href":"https:\/\/blog.zhaw.ch\/datascience\/wp-json\/wp\/v2\/posts\/528","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.zhaw.ch\/datascience\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.zhaw.ch\/datascience\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.zhaw.ch\/datascience\/wp-json\/wp\/v2\/users\/40"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.zhaw.ch\/datascience\/wp-json\/wp\/v2\/comments?post=528"}],"version-history":[{"count":3,"href":"https:\/\/blog.zhaw.ch\/datascience\/wp-json\/wp\/v2\/posts\/528\/revisions"}],"predecessor-version":[{"id":711,"href":"https:\/\/blog.zhaw.ch\/datascience\/wp-json\/wp\/v2\/posts\/528\/revisions\/711"}],"wp:attachment":[{"href":"https:\/\/blog.zhaw.ch\/datascience\/wp-json\/wp\/v2\/media?parent=528"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.zhaw.ch\/datascience\/wp-json\/wp\/v2\/categories?post=528"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.zhaw.ch\/datascience\/wp-json\/wp\/v2\/tags?post=528"},{"taxonomy":"features","embeddable":true,"href":"https:\/\/blog.zhaw.ch\/datascience\/wp-json\/wp\/v2\/features?post=528"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}