Usage of data mining for analyzing customer mindset



Similar documents
Business Intelligence represents a fundamental shift in the purpose, objective and use of information

Introduction to Marketing of Financial Services

Marketing Consultancy Division (MCD) Export Consultancy Unit (ECU) Export in Focus. Export Market Expansion Strategies. Rabi-I, 1427 (April, 2006)

COURSE PROFILE. Business Data Analysis IT431 Fall

Basics of Supply Chain Management

Case Study. Sonata develops. comprehensive BI Application for a leading provider of Animal Nutrition Solutions. Ananthakrishnan

Copernicus & Big Data: A Perspective from the European EO Services Industry. Geoff Sawyer: EARSC Secretary General

The Importance of Market Research

The Importance Advanced Data Collection System Maintenance. Berry Drijsen Global Service Business Manager. knowledge to shape your future

Data Abstraction Best Practices with Cisco Data Virtualization

Data Mining & Advanced Analytics

Importance and Contribution of Software Engineering to the Education of Informatics Professionals

Research Report. Abstract: The Emerging Intersection Between Big Data and Security Analytics. November 2012

The Business of Campaign Response Tracking

Economic Research and Digital Business Transformation COMPANY PROFILE

Data Warehouse: Introduction

Onex Solutions Private Limited (Onex Solutions) is a one stop shop for all your marketing needs!!

Integrate Marketing Automation, Lead Management and CRM

Job Profile Data & Reporting Analyst (Grant Fund)

366 Degrees Gaining Extra Degrees of Success

Business Intelligence and DataWarehouse workshop

TOWARDS OF AN INFORMATION SERVICE TO EDUCATIONAL LEADERSHIPS: BUSINESS INTELLIGENCE AS ANALYTICAL ENGINE OF SERVICE

BRISTOL CITY COUNCIL ROLE AND EMPLOYEE PROFILE: Architect (Practitioner Level) Specific Role Data Architect

Development of Long-term Relationships with Clients in Financial Sector Companies as a Source of Competitive Advantage 1

Feature Guide. Virto Commerce Platform

their needs. customer, and suggest alternative products when a customer requested product is not available.

Organizational Applications and Solutions SCM and ERP

WHITE PAPER. Vendor Managed Inventory (VMI) is Not Just for A Items

Work- and Process Organisation

Vision and Draft Findings

Volume 2, Issue 11, November 2014 International Journal of Advance Research in Computer Science and Management Studies

Standardization or Harmonization? You need Both

Professional Leaders/Specialists

Kontaktia Ltd. The specialist of customer relationships

Project Name: Herefordshire and Worcestershire Short Course Market Research Proposal. Andrew Corcoran

Information for Components Beacon ESOL Program Courses. Table of Contents

Data Warehouse Scope Recommendations

Network Security Trends in the Era of Cloud and Mobile Computing

E-Commerce-SWOT Analysis

Specialist Programs. Composite Fencing. Frequently Asked Questions FAQS

A Quick Read on the State of Small Business and the Small Business Success Index 2009 Baseline Study of Small Business Success

Hybrid Course Design and Instruction Guidelines

Global Services in Education, Ltd

Talking Bout. a Revolution 100% 110% 120% 90% 80% 70% 130% 140%

Better Practice Guide Financial Considerations for Government use of Cloud Computing

Secretary of Energy Steven Chu, U.S. Department of Energy. Acting Under Secretary David Sandalow, U.S. Department of Energy

Job Classification Details Department Job Function Job Family Job Title Job Code Salary Level

White Paper on Business Process Outsourcing in Automotive Industry

Advertising, Media, & PR Website Design and Online Marketing Agency SEO Services PPC Marketing Marketing

GUJARAT TECHNOLOGICAL UNIVERSITY

Atom Insight Business Solution Bundles

Mobile Workforce. Improving Productivity, Improving Profitability

The Pharma Forecasting Course

FCA US INFORMATION & COMMUNICATION TECHNOLOGY MANAGEMENT

PHYSICIAN COMPENSATION PLAN DESIGN STRATEGY

SCAN BASED TRADING SBT FOR RETAILERS

What is Software Risk Management? (And why should I care?)

Workshop on Business Analysis

The Cost of Not Nurturing Leads

IPMA Research Award 2008 Mario Vanhoucke. Measuring time A project performance simulation study

Do you have little or no incentive to enhance your agents listings online because there is no clear way to track the results or measure payback?

School of Management College of Sport and Human Dynamics School of Management... 4

ITIL Service Offerings & Agreement (SOA) Certification Program - 5 Days

MSc Enterprise Systems Development and Management (Full Time/ Part Time) E560

UNIVERSITY OF LETHBRIDGE. Mgt 4390 Z Leading Organizational Change. Course Outline

For both options: Please consult the Unisa website for admission requirements

Transcription:

Internatinal Jurnal f Electrnics and Cmputer Science Engineering 2533 Available Online at www.ijecse.rg ISSN- 2277-1956 Usage f data mining fr analyzing custmer mindset Priti Sadaria 1, Miral Kthari 1 Department f Cmputer Science, Virani Science Cllege, Ygidham Gurukul, Rajkt, Gujarat, India 2 Department f MCA, AITS, Ygidham Gurukul, Rajkt, Gujarat, India 1 Saurastra University 2 Gujarat Technlgical University 1 priti_ds_2012@yah.cm 2 Abstract- As this is the era f Infrmatin Technlgy, n filed remains untuched by cmputer science. The technlgy has becme an integral part f the business prcess. By implementing different data mining techniques and algrithms n the feedback cllected frm the custmer, we can analyzed the data. With help f this analyzed infrmatin we have clear idea abut the custmer s mind set and can take meaning full decisin fr prductin and marketing f particular prduct. T study abut custmer mindset different mdels like classificatin and assciatin mdels are used in data mining. Keywrds Data mining, Custmer Relatinship Management, Market Basket Analysis I. INTRODUCTION Nw a day in every field, Infrmatin technlgy is used. In the fields like banking, rail-way reservatin, educatin sectr, gvernment sectr and als in medical fields cmputer technlgy used widely. T enhance the prductin and marketing f any prduct is the mst difficult jb. Effective prductin and prper Marketing is very much imprtant fr any industry. In cmpetitive envirnment at lw cst ne has t prvide best qualities prduct t the custmer. Fr prductin and marketing f any prduct, ne has t knw custmer mind set first( refer Figure 1). Individual custmer segment s infrmatin can be gather thrugh nline custmer r by maintain different custmer prfile. By analyzing different segments f custmer ne can knw abut characteristic and behavir twards particular prduct. Sme nline cmpanies can get infrmatin frm custmer at very lw cst frm custmer wh are use t purchase prduct nline[1 - Kwk Wai Cheung, James, Martin 2003]. Depending n these infrmatin individual custmers prfile can be built and we can increase face t face marking. Als cmpany can display lts f infrmatin abut existing prducts, new prducts and new scheme launched recently. With cmmunicating with custmer we can understand and influence custmer behavir tward particular prduct. Ultimately it imprves custmer retentin and custmer lyalty fr prduct[2 - E.W.T. Ngai, Li Xiu, D.C.K. Chau 2008]. It als includes attentin twards custmer services fr effective and efficient custmer satisfactin. The Data Mining is the prcess f extracting infrmatin frm large data sets with help f different techniques and algrithms and after analyzing data, the derived infrmatin can be used t achieve r fulfill sme specific task. By implementing different data mining techniques and algrithms, we can analyze this data which is cllected frm the custmer and can develp a grup f relevant infrmatin. Frm different mdels available fr data mining techniques, classificatin and assciatin mdes are used fr analyzing custmer mindset. The prcesses f analyzing custmer mindset can als cnsider as Custmer Relatinship Management. By using this analyzed infrmatin, we may expand marketing; we may take meaningful decisin fr future plan f cmpany r may take decisin fr develping new prducts and services. Custmer Relatinship Management can be categrized int tw parts, ne is peratinal and ther is analytical. Autmatin f business prcesses include int peratinal custmer relatinship management and analysis f custmer behavirs and characteristics can be include int analytical custmer relatinship management.

Usage f data mining fr analyzing custmer mindset 2534 Services Custmer Fcus Sales Marketin g Figure 1. Different Custmer Aspects II. RESEARCH METHODOLOGY T analyze custmer mindset s many articles are reviewed frm many business related jurnals. Knwledge discvery is the mst imprtant aspect f data mining fr research related t the custmer relatinship management. The articles which specify actual usage f data mining fr analyze custmer mindset are reviewed. Business Surce Premier, ABI/INFORM database etc. are reviewed t understand usage f data mining in custmer relatinship management. Different categry f custmer relatinship management and data mining mdel is mainly fcused. Prblem Definiti n Data Gathering and Mdel Building and Evaluatin Knwledge Develpment Figure 2. Knwledge Discveries

IJECSE, Vlume1, Number 4 Priti Sadaria and Miral Kthari Knwledge Discvery in Database is implemented fr analyzed data (refer Figure 2). Frm previusly vast cllected data sme infrmatin is extracted by implementing Knwledge Discvery in Database[3 William, Gregry and Christpher 1992]. III. CLASSIFICATION METHOD Custmer Relatinship Management can be categrized int main fur dimensins (refer Figure 3) [4 Swift, Parvatiyar, Sheth 2001]. Custmer Identificatin Custmer Attractin Custmer Retentin Custmer Develpment T develp lng term relatinship with custmer by cnsidering custmer value and understating custmer requirement deeply, these dimensins have main rle in marketing f any prduct. [5 Au & Chau - 2003, 6 - Krachlauer et al 2004, Ling & Yen 2001). By cllecting infrmatin frm different custmer large database can be created and by analyzing this database ne can identify hidden characteristic and behavir f custmer. The cmmn aspect f data mining is t develp specific mdel frm infrmatin f the database. Fr specific data mdeling any technique can be used frm fllwing list - Assciatin mdeling Classificatin Clustering Frecasting Regressin Sequence discvery Visualizatin These mdels are mentined in different articles related t the data mining mdels [6 Ahmed 2004, Carrier & Pvel 2003, 8 - Mitra, Pal & Mitra 2002, 9 - Turban et al - 2007]. Any mdel frm abve mentined mdel can be pted accrding t the business requirement. Different data mining algrithms are used fr different mdel f data mining. Custmer Attractin Custmer Identificatin Custmer Relatinship Management Custmer Retensin Custmer Develpment Figure 3. Graphical Layut f Custmer Celatinship Management Dimensin

Usage f data mining fr analyzing custmer mindset 2536 A. Graphical Layut CRM dimensin - Different techniques f data mining can be implemented n these fur dimensins f custmer relatinship management. Mst prfitable and quality riented custmer grup can be identified thrugh the cycle f these fur dimensins and can fcus fr future aspect. Custmer Identificatin Target custmer analysis and custmer segmentatin can be cnsidered fr custmer identificatin. The segment f the custmer which is mst prfitable is searched frm the different custmer segments fr target custmer analysis. As far as cnsideratin fr custmer segmentatin, accrding t the scenari f similarity between different custmer sme custmer segments can be gruped tgether frm entire set f custmer. (10 - W,Bae, & Park 2005) Custmer Attractin Direct marketing cncept is used fr custmer attractin. After identifying custmer segment, direct marketing is used t target sme specific grup f custmer with help f different channels. Direct phne call fr specific scheme t sme specific custmer is the example f direct marketing. Custmer Retentin Fr lng term relatinship with particular custmer, satisfactin in aspect f quality and price is mst imprtant[ 6 Kracklauer et al. 2004]. Custmer retentin can be identified by taking feedback frm the custmer. One t ne marketing cncept is used fr knwing custmer retentin. Custmer Develpment Expected ttal incme frm particular custmer fr the cmpany can be frecast with help f custmer lifetime value analysis [12 Drew, Mani, Betz, & Datta 2001, 13 - Etzin, Fisher, & Wasserkrug 2005]. Custmer develpment includes prmtinal activities fr clsely related custmer t prvide varius services. Market basket analysis is als fcused fr custmer develpment. Purchase behavir f custmer is cnsidered fr market basket analysis. Custmer relatinship can be maintained in different aspect with varius marketing styles. Marketing styles depends n varius business categries. Different business categry use varius aspects fr marketing like direct marketing, crss selling, segment analysis, prduct mix analysis etc. Table1 Business applicatin types Types f Types f cmpany Types f business Marketing scenari sectr applicatins Segmentatin analysis Retail Custmer segmentatin Marketing segmentatin Prduct mix analysis Retail Prmtinal prduct mix Prduct mix analysis Crss selling Retail Custmer crss selling Prduct crss selling Direct marketing Retail Analysis f name list f advertisement Direct mail marketing

IJECSE, Vlume1, Number 4 Priti Sadaria and Miral Kthari B. Data mining mdels classificatin - Fur dimensin f Custmer Relatinship Management can be supprted by seven data mining techniques like Assciatin mdeling, Classificatin, Clustering, Frecasting, Regressin, Sequence discvery, Visualizatin. Assciatin mdeling is used t identify different items which are available tgether depending n the market basket analysis and in crss selling f prducts. Algrithms like apriri and statistics are use fr assciatin mdeling. Classificatin includes different classes f the infrmatin depending n the predictin f future custmer behavir depending n certain criteria. Generally neural netwrks and decisin trees are used fr classificatin. The clustering technique f data mining mdel is used fr segmenting hetergeneus ppulatin int a number f mre hmgeneus clusters [14 Ahmed 2004, 15 - Berry & Linff 2004]. Discriminatin analysis and neural netwrks tls are used fr clustering. Future planning fr the cmpany is designed with help f frecasting technique. Frecasting is based n cntinuusly valued utcmes. Tls used fr frecasting is survival analysis and neural netwrks. One example f fre casting mdel is demand frecast. Data Warehuse Prfile Discvery Prspect Selectin Mail Sending Mining Engine Marketing Tls Prcess Respnce Figure 4. Usage f data mining in Marketing Prmtin Regressin technique is ne kind f statistical estimatin technique which is used t map each data bject t real value. Mdeling f causal relatinship, predictin based n frecasting are the example f usage f regressin. Tls used fr regressin are lgistic regressin and linear regressin. Sequence discvery technique f data mining cncentrate n the states f the prcess generating the sequence ver sme particular time perid. Tls used fr sequence discvery are set thery and statistics. The last technique f data mining mdel is visualizatin. Cmplex pattern can be viewed by custmer by presentatin f data thrugh visualizatin. Mst cmmn examples f visualizatin are Hygraphs,3D graphs and SeeNet. Cmbinatin f any tw r mre data mining technique can be used accrding t the requirement f the cmpany fr particular prduct s prductin. Certain meaningful decisin can be taken with help f the analyzed data by different data mining mdels (refer Figure 4).

Usage f data mining fr analyzing custmer mindset 2538 IV. CONCLUSION This review paper indicates that any industry r cmpany can plan fr future prductin and marketing f prduct with help f analyzing and extracting infrmatin frm different databases. Custmer Relatinship Management is used t knw custmer mindset. Mre ver varius data mining techniques can be implemented fr preparing data mdel frm gathered infrmatin. This paper indicates general aspect f custmer fr any prduct. The limitatin f this paper is that particular prduct is nt identified and reviewed here. It can be useful t knw nrmal scenari f custmer fr purchasing prducts. V. REFERENCES [1] Kwk Wai Cheung, James T. Kwk, Martin H. Law, Kwk-Ching Tsui (2003) Mining Custmer prduct rating fr persnalized marketing. [2] E.W.T. Ngai, Li Xiu, D.C.K. Chau (2008) Applicatin f data mining techniques in custmer relatinship management a literature review and classifictin. [3] William J. Frawley, Gregry Piatesky Shapir and Christpher J. Matheus (1992) Knwledge Discvery in Database an Overview. [4] Swift, Parvatiyar, Sheth 2001 Applicatin f data mining techniques in custmer relatinship management a literature review and classifictin. [5] Au W. H., Chan K. C. & Ya X. 2003 - A nevel evlutinary data mining algrithm with applicatin t churn predictin. [6] Kracklauer,A. H., Mills D. Q. & Seifert D. 2004 Custmer management as the rigin f cllabrative custmer relatinship management. Cllabrative Custmer Relatinship Management. [7] Chin Hung Hsu (2009) Data mining t imprve industrial standards and enhance prductin and marketing : An empirical study in apparel industry. [8] Mitra S. Pal, S. K. & Mitra 2002 Data Mining in sft cmputing framewrk : A survey. [9] Turban E., Arnsn, J.E. Liang, T.P., & Sharda R. 2007 Decisin supprt and business intelligence systems. [10] W J. Y. Bae S.M., & Park S. C. 2005 Visualizatin methd fr custmer map. Expert System with Applicatin. [11] Kracklauer,A. H., Mills D. Q. & Seifert D. 2004 Custmer management as the rigin f cllabrative custmer relatinship management. Cllabrative Custmer Relatinship Management [12] Drew J.H., Mani D.R., Betz A.L. & Datta P. 2001 Targeting custmer with statiscal and data mining techniques, Jurnal f Service Research. [13] Etzin O., Fisher A. & Wasserkrig S. 2005 E CLV : A mdeling apprach fr custmer lifetime evaluatin in e- cmmerce dmain, withan applicatin and case study fr nline auctin, Infrmatin Systems Frntiers. [14] Ahmed S. R. 2004 Applicatin f data mining in retail business. Infrmatin Technlgy : Cding and Cmputing. [15] Berry M. J., & Linff G.S 2004 Data mining techniques secnd editin fr marketing, sales and custmer relatinship management.