FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201337715> ?p ?o ?g. }

• W3201337715 abstract "A business that conducts direct marketing activities (e.g. direct mail, outbound-telemarketing, email marketing) has two primary concerns regarding the management of its customer base  – (1) maintaining and deepening the relationship value with current / past customers and (2) acquisition of new customers. The use of predictive models specifically and data science generally, applied to maintaining current customer relationships is well known and is composed of related activities such as cross-sell (finding the next best offer), retention (intervening prior to customer attrition) and measurement of and experimentation to increase lifetime value (LTV). The richness of data captured on current customers as they interact with a business allows for continuous analysis and optimization of efforts aimed at these outcomes. For example, order/transaction history, web site visits, customer service interaction, social media usage, collected demographics and past responsiveness to marketing can be leveraged for data mining. Acquisition of new customers, in a targeted sense (i.e. not mass advertising) is more difficult, more expensive and less well studied. The fact that a prospect, by definition, has had no past (purchase) interaction with a brand greatly limits the amount of data that can be analyzed. Direct marketing to prospects requires the ability to identify prospects as individual units (consumers, businesses or households), acquire the means to contact them (e.g. street address, telephone number, email address) and most importantly, decide which prospects to contact based on expected return on investment. Co-operative databases exist as a means to collect and aggregate data for prospecting. These databases become a surrogate for the company's own customer database and are a powerful means from which to identify, locate and select the most likely to respond prospect units. This thesis examines a specific example of mining a business-to-business (B2B) co-operative database for the purpose of selecting prospect units to which to market with a direct mail catalog. Specifically, we show the efficacy of using modern machine learning algorithms, Gradient Boosted Regression Trees and Random Forests, to build highly predictive models to forecast response of prospect units to direct mail marketing offers. Within this thesis, we examine the algorithms in detail, apply them to a real life problem and use the models to further explain the underlying processes associated with the identification of those most likely to respond to a marketing offer.%%%%Submitted in Partial Fulfillment of the Requirements for the Degree of Master of Science in Data Mining.; Thesis advisor: Darius Dziuda.; M.S.,Central Connecticut State University,,2013.;" @default.
• W3201337715 created "2021-09-27" @default.
• W3201337715 creator A5053965619 @default.
• W3201337715 date "2013-01-01" @default.
• W3201337715 modified "2023-09-24" @default.
• W3201337715 title "An Application of Gradient Boosted Regression Trees and Random Forests to Prospect Direct Marketing Response Modeling" @default.
• W3201337715 hasPublicationYear "2013" @default.
• W3201337715 type Work @default.
• W3201337715 sameAs 3201337715 @default.
• W3201337715 citedByCount "0" @default.
• W3201337715 crossrefType "journal-article" @default.
• W3201337715 hasAuthorship W3201337715A5053965619 @default.
• W3201337715 hasConcept C101276457 @default.
• W3201337715 hasConcept C130721881 @default.
• W3201337715 hasConcept C140781008 @default.
• W3201337715 hasConcept C144133560 @default.
• W3201337715 hasConcept C162853370 @default.
• W3201337715 hasConcept C2777276756 @default.
• W3201337715 hasConcept C2780378061 @default.
• W3201337715 hasConcept C536005652 @default.
• W3201337715 hasConceptScore W3201337715C101276457 @default.
• W3201337715 hasConceptScore W3201337715C130721881 @default.
• W3201337715 hasConceptScore W3201337715C140781008 @default.
• W3201337715 hasConceptScore W3201337715C144133560 @default.
• W3201337715 hasConceptScore W3201337715C162853370 @default.
• W3201337715 hasConceptScore W3201337715C2777276756 @default.
• W3201337715 hasConceptScore W3201337715C2780378061 @default.
• W3201337715 hasConceptScore W3201337715C536005652 @default.
• W3201337715 hasLocation W32013377151 @default.
• W3201337715 hasOpenAccess W3201337715 @default.
• W3201337715 hasPrimaryLocation W32013377151 @default.
• W3201337715 hasRelatedWork W117061049 @default.
• W3201337715 hasRelatedWork W2189271473 @default.
• W3201337715 hasRelatedWork W2259647566 @default.
• W3201337715 hasRelatedWork W229614685 @default.
• W3201337715 hasRelatedWork W2304656450 @default.
• W3201337715 hasRelatedWork W2307075403 @default.
• W3201337715 hasRelatedWork W2502912625 @default.
• W3201337715 hasRelatedWork W2538187747 @default.
• W3201337715 hasRelatedWork W2742441636 @default.
• W3201337715 hasRelatedWork W2793879779 @default.
• W3201337715 hasRelatedWork W2907573203 @default.
• W3201337715 hasRelatedWork W2972518767 @default.
• W3201337715 hasRelatedWork W2990678714 @default.
• W3201337715 hasRelatedWork W3042066948 @default.
• W3201337715 hasRelatedWork W3087861066 @default.
• W3201337715 hasRelatedWork W3099386891 @default.
• W3201337715 hasRelatedWork W3125221465 @default.
• W3201337715 hasRelatedWork W3141651165 @default.
• W3201337715 hasRelatedWork W3208261001 @default.
• W3201337715 hasRelatedWork W768111943 @default.
• W3201337715 isParatext "false" @default.
• W3201337715 isRetracted "false" @default.
• W3201337715 magId "3201337715" @default.
• W3201337715 workType "article" @default.