- Количество слайдов: 14
SAS Enterprise Miner for Analytical CRM SAS Institute Ltd 15 February 2001 Copyright © 2000 , SAS Institute Inc. All rights reserved.
Who we Are The world’s largest privately held software company Meeting the needs of decision makers in business, government and beyond Delivering The Power to Know for 24 years
Worldwide Customer Base 796 Banking 292 Telecommunications 898 Insurance 1142 Services 361 Retail 187 Transportation 160 Publishing/Media 1575 Manufacturing 1013 Pharma/Chemical 163 Oil and Gas 2100 Public/Government 1392 Universities 98% 90% 98% 67% Fortune 100 Global 500 Customer Retention Customers Extend Investment Yearly
SAS in Hong Kong Banking/Insurance American Express AXA Insurance Bank of China BPI Citibank Dao Heng Bank Group Hang Seng Bank HSBC HK Mortgage Corp. ING Baring Standard Chartered Bank Chase Manhattan Bank Government Census & Statistics Department of Health Education Department HK Housing Authority HK TDC Hospital Authority ITSD Planning Department Rating & Valuation Dept. Security Bureau Social Welfare Dept. Transport Dept. Communications Cable & Wireless HKT Cathay Pacific Airways Federal Express HK Air Cargo Terminal HK Telecom CSL MTRC OOCL Smar. Tone Mobile Wharf Cable Others ACNielsen Ltd. Asia Television Caltex Oil China Light & Power Coca Cola China Ltd. HK Electric Co. Ltd. IBM China/HK Park N’ Shop Reader’s Digest Television Broadcast Ltd.
Why SAS? With SAS Institute’s reporting and data mining software, we can improve our understanding of customers and deliver tailored solutions to them. Y. B. Yeung, Head of IT, HSBC There are four components to the system we put in place – data management, statistical analysis, reporting and information delivery. Other vendors can provide one or two of these but SAS can provide all four, with powerful integration between each step. Kelvin Poon, Statistician, Hospital Authority Whether it’s credit scoring in Singapore, customer retention in Hong Kong or acquisition modeling in India, SAS helps us get the answers Jim Thomason, Senior Information Systems Manager, Standard Chartered
The power to know your customers. Increase your revenues: n Compile your customers’ entire buying history – Web, catalog, storefront – everything. n Identify your most profitable customers. n Predict future buying behaviors. n Target your marketing dollars where the payoff is greatest.
SASSAS Enterprise Miner
SAS Enterprise Miner references Banking & Financial Services AXA Financial, Bank of America, Wells Fargo (USA), First Union (USA), Generale de Banque (Belgium), Deutsche Bank (Germany), Old Mutual (South Africa), Caja de Ahorros de Asturias (Spain), Hang Seng Bank (Hong Kong), Hongkong and Shanghai Banking Corporation, NG Bank (Netherlands), Banque Sofinco (France), Banco Comercial Portugues, Nordbanken (Sweden), Standard Chartered (Singapore), MBNA Direct Limited (UK), Credito Italiano (Italy), Cariplo (Italy), Mapfre (Spain), Reale Mutua (Italy) Telecommunications Belgacom (Belgium), Proximus (Belgium), British Telecom (UK), Telenor Media (Norway), Telia Mobitel (Sweden), Tele Danmark, France Telecom, T-Mobil (Germany), US West (USA), AT&T (USA), MT&T (USA), Hutchison Telecom (Hong Kong), PCCW HKT (Hong Kong), SKTelecom (Korea), Malaysia Telecom, Maxis (Malaysia), Orange (Australia), Smar. Tone (Hong Kong), Telstra (Australia) Other Amazon. com (USA), Outpost. com (USA), British Airways (UK), Cathay Pacific Airways (Hong Kong), Marks & Spencer (UK), Cecile (Japan), Eddie Bauer (USA), UCB Pharma (USA), Shanghai Baosteel (PRC)
Top Vendors as Selected by the Readers of DM Review Data Warehousing/Business Intelligence Products 1 SAS 2 3 4 5 6 7 8 9 10 11 12 NCR Oracle Corporation Computer Associates Cognos Corporation Micro. Strategy Incorporated Microsoft Corporation IBM Informix Business Solutions Hyperion SAP America SPSS Inc.
An Example Business Objective: Direct marketing department of a retail products company wants to increase catalog sales revenue. They want to target only current customers likely to make a catalog purchase.
Input Variables Category Variables Demographic AGE INCOME MARRIED SEX C 0 A 6 Description OWNHOME Age in years Yearly income in thousands 1 if married, 0 otherwise F or M 1 if change of address in last 6 months, 0 otherwise 1 if own home, 0 otherwise Geographic LOC Location of residence, A-H Monetary VALUE 24 Total value of purchases in past 24 months
Input Variables Category Variables Description Recency/ Frequency BUY 6 BUY 12 BUY 18 Number of purchases in last 6 months Number of purchases in last 12 months Number of purchases in last 18 months Purchase History DISCBUY RETURN 24 1 if discount buyer, 0 otherwise 1 if product return in past 24 months, 0 otherwise Response RESPOND 1 if responder to test mailing, 0 otherwise
Propensity To Buy Customer Id Score Cust_id_01 0. 72 Cust_id_03 0. 91 Cust_id_02 0. 23 Cust_id_03 0. 91 Cust_id_04 Sort By Cust_id_04 Score 0. 80 Cust_id_01 0. 72 0. 80 Cust_id_05 0. 45 Cust_id_06 0. 28 Cust_id_02 0. 23 : :