Marketing Optimization Example Maureen McClatchey, Ph.D. 1/23/20131Denver SAS User's Group presentation.

Slides:



Advertisements
Similar presentations
Segmenting B2B Markets Anand G. Khanna
Advertisements

Connor Trent & Connor Seay
The Role of SAS in the Analytics Framework Aleksandar Zajic VP Business Analytics
Copyright © 2012, SAS Institute Inc. All rights reserved. SAS CUSTOMER INTELLIGENCE SOLUTION BRIEFING SAS MARKETING OPTIMIZATION AND SAS ADAPTIVE CUSTOMER.
Linear Programming. Introduction: Linear Programming deals with the optimization (max. or min.) of a function of variables, known as ‘objective function’,
McGraw-Hill/Irwin ©2008 The McGraw-Hill Companies, All Rights Reserved CHAPTER 9 CUSTOMER RELATIONSHIP MANAGEMENT.
10.1 © 2007 by Prentice Hall 10 Chapter E-Commerce: Digital Markets, Digital Goods.
5-1 Copyright ©The McGraw-Hill Companies, Inc. Permission required for reproduction or display.
Making the Evidence-Based Program Fit Your Needs: Adaptation and Your Program Summary.
Reinforcement learning
PRODUCTION PLANNING ELİF ERSOY Production Planning2 WHAT IS PRODUCTION PLANNING?  Production planning is a process used by manufacturing.
CEFRIEL Deliverable R4.1.5 MAIS adaptive and reconfigurable modem Giovanni Paltenghi Roma – 24 Novembre 2005.
Copyright © 2005 Pearson Education Inc. Personal Selling and Direct Marketing Chapter 17 PowerPoint slides Express version Instructor name Course name.
Copyright  2004 McGraw-Hill Australia Pty Ltd PPTs t/a Marketing 4/e by Quester, McGuiggan, Perreault and McCarthy 2–1 Part 1: Marketing strategy and.
Beyond Opportunity; Enterprise Miner Ronalda Koster, Data Analyst.
ESTABLISH YOUR MARKETING GOALS. WE'LL TAKE CARE OF THE REST. Business proposal 2015.
Life Time Value Analysis Definition: LTV is the net present value (NPV) of the profit that you will realize on the average new customer during a given.
Four Corners TB & HIV Conference National Native American AIDS Prevention Center October 24, 2012 Social Marketing in Native Communities.
CRM in Marketing CRM Initiatives. CRM Marketing Initiatives Cross-Selling Selling a product or service to a customer as a result of another purchase Selling.
Information Technology (IT)-Enabled Marketing. True relationship marketing requires a fundamental shift in attitude towards viewing the customer as a.
Comparison of Classification Methods for Customer Attrition Analysis Xiaohua Hu, Ph.D. Drexel University Philadelphia, PA, 19104
McGraw-Hill/Irwin McGraw-Hill/Irwin Copyright © 2009 by The McGraw-Hill Companies, Inc. All rights reserved.
Financial and Cost-Volume-Profit Models
WOOD 492 MODELLING FOR DECISION SUPPORT Lecture 1 Introduction to Operations Research.
Copyright Cengage Learning 2013 All Rights Reserved 1 Chapter 21: Customer Relationship Management (CRM) Introduction to Designed & Prepared by Laura Rush.
Customer Relationship Management (CRM). Introduction  Customer Relationship Management is a process used for developing stronger relationship between.
Marketing Part 1 Indicator 1.04 – Employ marketing information to develop a marketing plan.
WF Marketing Part 1 Indicator 1.04 – Employ marketing information to develop a marketing plan.
Chapter 13 Genetic Algorithms. 2 Data Mining Techniques So Far… Chapter 5 – Statistics Chapter 6 – Decision Trees Chapter 7 – Neural Networks Chapter.
Lecture 9: Knowledge Discovery Systems Md. Mahbubul Alam, PhD Associate Professor Dept. of AEIS Sher-e-Bangla Agricultural University.
© IDM Academy 2008 Beyond Segmentation The Challenge of Contact Optimisation Mike Talbot CTO/Founder Alterian.
1 Conducting a needs assessment - 7 Barbie E. Keiser University of Vilnius May 2007.
Model Map The model map identifies the underlying hierarchical budget model structure and serves as a “home screen” allowing one-click navigation to all.
Chapter 4 MODELING AND ANALYSIS. Model component Data component provides input data User interface displays solution It is the model component of a DSS.
1 Market Optimization Phase VI May 2012 i = 1, …, M customers j = 1, …, N offers A = (a ij ) is a matrix where a ij = 1, if offer j is to be targeted to.
Exam 3 Review Decision Trees Cluster Analysis Association Rules Data Visualization SAS.
The Ten Creative Commandments September 15, 2008.
Integrating the Broad Range Applications of Predictive Modeling in a Competitive Market Environment Jun Yan Mo Mosud Cheng-sheng Peter Wu 2008 CAS Spring.
Using the Right Method to Collect Information IW233 Amanda Murphy.
Study Unit 9 Decision Analysis and Risk Management.
Linear Programming Erasmus Mobility Program (24Apr2012) Pollack Mihály Engineering Faculty (PMMK) University of Pécs João Miranda
MARKETING ENVIRONMENT. THE MARKETING ENVIRONMENT The Marketing Environment can be defined all the Internal and External Factors and Forces that affect.
Sule Ozmen-CRM CRM Customer Relationship Management Şule Özmen Week 6 Digital Economy Customers Became Number One They are empowered customers.
Chapter 4 Marketing Intelligence and Database Research.
MKT 346: Marketing of Services Dr. Houston
Cluster Analysis Potyó László. Cluster: a collection of data objects Similar to one another within the same cluster Similar to one another within the.
OO Methodology Elaboration Iteration 2 - Design Patterns -
Gerhard Steinke1 Enterprise Requirements Planning (ERP) Customer Relationship Management (CRM) Data Warehousing.
Prepared by Diane Tanner University of North Florida Flexible Vs. Static Budgets Chapter 7.
CISC 849 : Applications in Fintech Namami Shukla Dept of Computer & Information Sciences University of Delaware iCARE : A Framework for Big Data Based.
How to Be a Great Partner! Steve Erickson National Consultant to CPA Firms.
Managerial Economics Linear Programming Aalto University School of Science Department of Industrial Engineering and Management January 12 – 28, 2016 Dr.
Given a set of data points as input Randomly assign each point to one of the k clusters Repeat until convergence – Calculate model of each of the k clusters.
1 05 IT.ppt Market and Customer Management - Customer Loyalty 5. Loyalty and Information Technology Frequently asked questions: qWhat is a customer loyalty.
Cluster Analysis What is Cluster Analysis? Types of Data in Cluster Analysis A Categorization of Major Clustering Methods Partitioning Methods.
Market and Customer Management - Customer Loyalty 1 MANAGEMENT SUMMARY.
MARKETING MIX. What is Marketing Mix? The marketing mix is the combination of marketing activities that an organisation engages in so as to best meet.
The Marketing Mix. 4.2 Marketing Applications The Marketing Mix: Consists of variables controlled by marketing professionals in an effort to satisfy the.
Customer Relationship Management. Presentation By: Tarun Rattan Jyoti Sodani Akash Gupta Saloni.
The analytics of constrained optimal decisions microeco nomics spring 2016 dynamic pricing (II) ………….1integrated market ………….2 uniform pricing: no capacity.
Process and System Characterization Describe and characterize transport and transformation phenomena based reactor dynamics ( 반응공학 ) – natural and engineered.
8 - 1 Copyright © 2006, The McGraw-Hill Companies, Inc. All rights reserved.
Managerial Economics Linear Programming
Pricing of Services.
Business Analytics Applications in Budget Modelling
Customer Relationship Management
Marketing leads Optimization at Fortis RBB
Week 11 Knowledge Discovery Systems & Data Mining :
Biomedical Business Model Canvas
Presentation transcript:

Marketing Optimization Example Maureen McClatchey, Ph.D. 1/23/20131Denver SAS User's Group presentation

“BASEBALL IS 90% MENTAL AND THE OTHER HALF IS PHYSICAL” Quote from Yogi Berra 1/23/2013Denver SAS User's Group presentation2

What is marketing optimization? Optimization enables us to determine – the optimal set of customers to target in a marketing campaign and – the optimal communications (offer type) to use for each customer. 1/23/20133 Denver SAS User's Group presentation

Marketing Optimization enables us to 1) determine the optimal set of customers to target in a marketing campaign 2) and the optimal communications to use for each customer. 3) You can choose the objective to be optimized. For example – Maximize expected revenue or profit – Minimize expected cost of campaign – Maximize total number of expected responses 1/23/20134 Denver SAS User's Group presentation

Marketing Optimization Example: Business question design tailors predictive models Models applied to customers calling in to Telecommunications Call Centers – Customers asked for permission to use their proprietary information as part of the call before marketing begins. Partnership and collaboration among marketers, IT and statisticians 1/23/20135 Denver SAS User's Group presentation

Goal of Marketing Optimization The goal is to obtain an assignment of each customer to an offer type that optimizes the objective – e.g., maximize expected profit At the same time satisfy various marketing constraints – e.g., budget constraints, # offers restrictions, channel capacities, contact policy restrictions 1/23/2013 Denver SAS User's Group presentation 6

Marketing Optimization Input Tables Input tables to eliminate ineligible assignments of customers to offer types – Customer table – Customer table variables: Identification number, Location, Probability( Attrition), Revenue, Expected Value(Attrition) = Probability(Attrition)*NPV, Automatic payment for services, Product subscriber, Credit rating, Demographic cluster values – (macro or micro) 1/23/2013 Denver SAS User's Group presentation 7

How Does Lifetime Value Fit In? Calculate Lifetime Value (LTV) Create a rule so that customers with the highest expected value of retention also have the highest LTV Optimize the objective 1/23/2013 Denver SAS User's Group presentation 8

Campaign Table Campaign_CdCampaign_Desc Camp_1Retention campaign 1 Camp_2Retention campaign 2 1/23/2013 Denver SAS User's Group presentation 9

Communication Table Campaign_CdCommunication_CdAvg_Exp_ValAvg_Prob Camp_1Comm_111 Camp_1Comm_211 Camp_2Comm_311 Camp_2Comm_411 1/23/2013 Denver SAS User's Group presentation 10

Control Table Campaign_CdCommunication_ Cd Column_NmNumeric_Measure Camp_1Comm_1Prob_Attrition_Reason1Prob Camp_1Comm_2Prob_Attrition_Reason2Prob Camp_2Comm_3Prob_Attrition_Reason3Prob Camp_2Comm_4Prob_Attrition_Reason4Prob Camp_1Comm_1Exp_Val_AttritionExp_Val Camp_1Comm_2Exp_Val_AttritionExp_Val Camp_2Comm_3Exp_Val_AttritionExp_Val Camp_2Comm_4Exp_Val_AttritionExp_Val 1/23/2013 Denver SAS User's Group presentation 11

Additions to MO Constraints Minimum Responses Contact Policies Attrition probabilities in the customer table need to be calibrated to recent behavior. – Can be handled with a multiplier in a look-up table 1/23/2013 Denver SAS User's Group presentation 12

Additions to MO (cont’d) Create a project Create a scenario Calculate the objective Maximize adjusted profit Expected value = probability(retention)*net present value 1/23/2013 Denver SAS User's Group presentation 13

Additions to MO (cont’d) Enter constraints and contact policies Idea: Use a sequential algorithm at first. Then use the sequential algorithm to create a customer table in SAS. Compare results of sequential algorithm to results using Marketing Optimization. Optimize a scenario Results: Optimal offer for each customer 1/23/2013 Denver SAS User's Group presentation 14

Think about optimization What are we optimizing? – Please carefully consider. Is there no harm? – What are the benefits of optimization in your biomedical research/pharmaceutical/business setting? Think about what you are doing! – Slow down a bit and reflect – Ask yourself, “What are the pros?” “What are the cons?” and most importantly, “What are the probable consequences from this work?” – Then do the ethical thing! 1/23/2013Denver SAS User's Group presentation15

Wish list Build in an ‘after-the-fact’ evaluation component. – What worked? – What did not work? – Quality improve the system – Repeat recursively 1/23/ Denver SAS User's Group presentation