Development and demonstration of a Customer Super-Profiling tool utilising data analytics for alternative targeting in marketing campaigns

Date
2018-12
Journal Title
Journal ISSN
Volume Title
Publisher
Stellenbosch : Stellenbosch University
Abstract
ENGLISH ABSTRACT:Being part of a competitive generation demands that a business has good marketing policies to attract new customers as well as to retain existing ones. Marketing managers can develop long-term and healthy relationships with customers, if they can detect and predict changes in their customers' purchasing behaviour. With the growth of information systems and technology, businesses have an increasing capability to accumulate huge quantities of customer data in large databases. However, much of these potentially useful marketing insights into customer characteristics and their purchasing patterns often remains hidden and untapped. Therefore, businesses can achieve competitive advantages by studying customer behaviour through data mining tools (i.e. supervised and unsupervised learning) and techniques (i.e.classification, regression and clustering). The goal of this research project was to develop a Customer Super-Profiling (CSP) tool that has the ability to analyse large (non-aggregate) customer datasets, considering both demographic and behavioural features. The data analytics was done by utilising more than one data mining tool, which generates customer super-profiles. These profiles are used to attract and classify new customers as well as to retain existing customers, providing the user with the ability to predict each customer's specific needs. This research project outlines a general methodology for segmentation of customers by using the model of Recency, Frequency and Monetary (RFM), together with k-means clustering (unsupervised learning) to identify the various types of customers within the dataset. Customer profiles are then generated, in the form of decision rules (supervised learning) to identify each type of customer as well as classifying them into the various clusters created. These predictions are performed based on the customers' demographic and behavioural features. The CSP tool was applied and demonstrated on large customer datasets from four different domains and useful results were found.
AFRIKAANSE OPSOMMING: Om deel te wees van 'n mededingende generasie vereis dat 'n besigheid oor 'n goeie bemarkingsbeleid beskik om nuwe kliënte te werf asook om bestaande kliënte te behou. Bemarkingsbestuurders kan langtermyn en gesonde verhoudings met kliënte ontwikkel, as hulle veranderinge in hul kliënte se koopgedrag kan opspoor en voorspel. Met die groei van inligtingstelsels en tegnologie het besighede 'n toenemende vermoë om groot hoeveelhede kliëntedata in groot databasisse op te bou. Baie van hierdie potensieël nuttige bemarkingsinligting oor kliënteienskappe en hul kooppatrone bly egter steeds weggesteek en onbenut. Daarom kan besighede mededingende voordele behaal deur kliëntgedrag met data-ontginningsgereedskap (d.w.s. begeleiding en onbegeleide leer) en tegnieke (d.w.s. klassifikasie, regressie en groepering) te bestudeer. Die doel van hierdie navorsingsprojek was om 'n Kliënt-superprofiel (KSP) instrument te ontwikkel wat die vermoë het om groot (nie-saamgestelde) kliëntdatastelle te analiseer, met inagneming van beide demograëse en gedragseienskappe. Die data-analise is gedoen deur gebruik te maak van meer as een data-ontginningsgereedskap, wat kliënte se superprofiele genereer. Hierdie profiele word gebruik om nuwe kliënte te lok en te klassifiseer, sowel as om bestaande kliënte te behou, wat die gebruiker die vermoë bied om elke kliënt se spesifieke behoeftes te voorspel. Hierdie navorsingsprojek beskryf 'n algemene metodologie vir segmentasie van kliënte deur gebruik te maak van die model van Onlangs, Frekwensie en Monet^ere waarde (OFM), tesame met k-mediane (onbegeleide leer) om die verskillende tipes kliënte binne die datastel te identifiseer. Kliëntprofiele word dan gegenereer in die vorm van besluitreëls (begeleide leer) om elke tipe kliënt te identifiseer asook om hulle in die verskillende groepe wat geskep word, te klassifiseer. Hierdie voorspellings word uitgevoer op grond van die demografiese en gedragseienskappe van die kliënte. Die KSP-instrument is toegepas en gedemonstreer op groot kliëntdatastelle van vier verskillende domeine en nuttige resultate was gevind.
Description
Thesis (MEng)--Stellenbosch University, 2018.
Keywords
Data mining, Data analytics, Marketing -- Management, Consumer profiling, K-means clustering, Machine learning, Big data, UCTD
Citation