Uncovering Hidden Profits: The Next Step in Optimizing i i Direct Marketing Dmitry Krass Rotman School of Management University of Toronto and Custometrics Inc.
Outline Direct marketing and Analytical Models Introduction Ranking vs. Forecasting Models MO: Multi-Product Optimization Multi-Product Multi-Period Optimization Summary 2
Direct Marketing and Analytics: A brief Introduction 1:1 Direct Marketing: marketing action customized to an individual level Typical Channels: Telemarketing (TM), Addressed/Unaddressed Direct Mail (DM), E-mail, Salesperson contact, etc Analytics (mainly statistical i / data mining i techniques) have long been accepted in DM community Acceptance by other marketing areas has been slower However, analytics is usually compartmentalized and (in our opinion) underused 3
Typical 1:1 DM Campaign Planning / Design: Decide on offer, creative, budgets; comm. channels Traditional home of Targeting: select targets from Where analytics belongs. Requires analytics (typically) a large universe of New data flows Targeting potential targets New / better Models statistical models Optimization Execution: mailing schedules, etc. Models DSS Tools Automation Evaluation: Did the message work? Did the targeting work? Overall ROI? 4
Targeting Models: A brief Introduction Goal: select targets (customers or geographical regions) to include in the campaign from a (much) larger universe Assume: contacting the whole universe is infeasible due to cost and/or capacity constraints How should these best prospects be selected? Exp. Activation Rate 5.00% 4.00% 3.00% Decision Rules 2.00% Targeting Models: much more effective 1.00% Typical targeting model is a statistical model relating expected response to Past behavioural history (RFM) Target characteristics (demographics, etc.) Other factors (seasonality, campaign specifics) Goal: separate best from the rest 0.00% Know: 20% of customers often account for 80% of response Gains Chart: Sample Program 1 2 3 4 5 6 7 8 9 10 Contact top two deciles deciles 5
Targeting Models: Ranking vs. Forecasting Ranking: separating high from low responders Often sufficient for Campaign Targeting Forecasting: predicting actual response rates A typical Targeting Model does a good job of ranking, but is a poor forecasting tool Forecasting is much harder! Requires much richer data; frequent model re-builds Actual Resp. Ra ate 2.5% 2.0% 1.5% 1.0% 0.5% 0.0% Good Ranking Gains Chart: Sample Program 1 2 3 4 5 6 7 8 9 10 deciles Ac ctual Resp. Rate 2.5% 2.0% 15% 1.5% 1.0% 0.5% 0.0% Poor Forecasting Actual vs. Expected Model Ideal 0.00% 2.00% 4.00% 6.00% Expected Response Rate 6
Why Ranking is not Enough Simple planning question: how many targets to include in the campaign? Simple answer: communicate to margin Example Margin = ($ Benefit of Response)*(Prob. Of Response) ($ Communication Cost) Include target if Margin > 0 But poor forecast of response undermines this! Benefit = $50, Comm. Cost = $1 Top 3 deciles should be included (based on exp. response rates) Actually should only include 2 deciles Exp. ROI = 66% Actual ROI = -1% $1.50 $0.50 $0.00 Margins: Sample Program $1.00 Exp. Margin $0.50 $1.00 $1.50 Act. Margin 1 2 3 4 5 6 7 8 9 10 deciles 7
Building Forecasting Models Relative target quality is often quite stable => ranking is much easier then forecasting Typically models mis-forecast because They fail to include communication history/ offer specifics They fail to include recent economic/ competitive trends The data they were calibrated on is too old The coefficients/ set of significant factors is too old Using predictive models for planning support / optimization i i requires Maintaining full communication history Richer variable set Rapid data refreshes Rapid model rebuilding cycle More data management / modeling sophistication 8
Outline Direct marketing and Analytical Models MO: Multi-Product Optimization System DM Planning and Analytics System Description Strategic Support Beyond MO Multi-Product Multi-Period Optimization Summary 9
DM Planning Tasks An Integrated DM campaign involves a number of offers executed simultaneously (or nearly so) Here, an offer may involve different products or variations of the same product Each target (customer or region) can receive at most one offer in a given time period Issues: Construct targeting lists for each offer Which customers to include? In which list? How large should different lists be? Given fixed overall budget, find optimal targeting list design while meeting side constraints These constraints often include minimal / maximal list sizes, certain markets to include /exclude, etc. 10
Example A telecommunications company runs monthly unaddressed direct mail campaigns to acquire new customers Campaigns are targeted at a geographical region level (postal walks or other distribution units) Each walk contains a number of households If a walk is targeted, every household must be mailed The current campaign involves five different product offers Products have different profitabilities in different regions Total budget is $1,000 (ok to exceed by a bit) Average contact cost is $.175 per household Constraint: the spend on each product should be between $100 and $300 11
Data for Example Assume first only ranking models are available Product profit margins are Prod1>.>Prod5 12
Typical Solution : Priority Targeting A typical company solves this problem by priority targeting Prioritize products (by profit margins or less objectively) Prepare targeting lists one product at a time Problems: Targets that are desirable (highly ranked) for one product are often desirable for many products Lists for higher-priority products steal all the best targets; lower-priority products left with very poor lists High profit margin does not mean high profitability (more expensive products often have lower response rates) Meeting all the constraints makes designing priority- assigned dlists non-trivial tiil 13
List Based on Priority Targeting Product Priority in order of margin: Prod 1> >Prod 5 Total budget is $1000 Each product spend should be between $100 and $330. 14
From Ranked-Based Lists to Multi- Product Optimization Issues with Ranked-based lists There were a number of conflicts between products. Were they resolved correctly (i.e., in profit-maximizing way)? What is the expected number of orders for the created list? Expected profit? Need Forecasting, not Ranking models Models should be able to Estimate effect of communication (i.e., sending offer X to region Y) Account for cross-product effects (e.g., Prod1 offer may lead to Prod2 sale and vice versa) To estimate Profitability need LTV (life-time value) estimates for each product Also need an Optimization Model to enumerate all possible lists satisfying our requirements and pick the best one These pieces together make up the MO System 15
Optimization Models: Key components Decision variables: represent target-to-list assignments Objective Function (MOS): what are we trying to optimize? Basis: response curve estimated by the forecasting model (for any given assignment must be able to compute expected response for each product) Poor objective: maximize total response to the campaign (responses to products A and B may have very different tfinancial i impact) Good objective: maximize overall Profit Need an estimate of LTV impact of response for each product; costs (both contact and product delivery) may differ in different locations Constraints Budget Business Constraints (min / max support for each product, etc.) Modeling Constraints crucial. Ensure that optimization does not leave the trust region of the underlying forecasting model 16
Optimization Model - Comments Software: solvers are becoming more prevalent, but require highly-skilled user; interface with statistical models a big issue Dimensionality often very large (while number of offers is usually small less than 20, number of potential targets can be in the millions) May require customized optimization algorithms Natural extensions: allow the model to decide which offers to use Makes the problem even harder to solve Evaluation / control groups much more intricate than for the one-product case Key to the whole process: accurate and sophisticated parameter estimates (i.e., good forecasting models built on good ddata) 17
Example Cont. Optimized vs. Ranked List Optimized list performs over 2x better Profitable in all areas Very different from the ranked list 18
Strategic Decision Support: Scenario Simulators Cost of constraints: What is the impact of min/max spend constraints? In this example, removing constraints increases the opt. profit by 6% Constraints are not very costly The only products used in the unconstrained run are Prod3 and Prod5 These are the key products in spite of low unit profit margins What is the optimal budget? Plug in different budget levels into the model Should consider increasing budget to $4000 range 19
MO and Planning Support The true benefit of MO is that it allows analytics to take an earlier seat at the table: Before budgetary decisions and offers are finalized and while constraints are still flexible By the targeting stage, many of these decisions are frozen, sharply reducing potential benefits of analytical models 20
Issues with MO List fatigue Repeated communication with the same customers induces fatigue Blackouts typical fatigue-fighting strategy Can quickly lead to deteriorating list quality Would like a more scientific approach to fatigue management For some targets it may be optimal to suspend communication for one or more periods; for others repeated communication may be fine Past communication affects future response Need to ensure long-term, not one-period profitability 21
Issues with MO cont. Spacing out offers may be better Multi-wave communication Need to balance that versus potential fatigue Multi-period planning DM budgets are often quarterly or bi-annual, while execution is monthly Little flexibility in monthly budgets Need multi-period, multi-channel approach 22
Outline Direct marketing and Analytical Models MO: Multi-Product Optimization System M 2 0: Multi-Product Multi-Period Optimization System Setting Thinking in sequences Impact to date Beyond M 2 0 Summary 23
M 2 O: Setting Assume k-period planning horizon Total budget is specified Have a set of offers (products) to select from and a universe of targets Often have additional constraints (new product intros require certain minimal support, etc.) Questions Who? When? How? Which offers should be used? How should the budget be allocated? 24
The Essence of M 2 O Right Customers Right Products Right Timing 25
M 2 O: Key Insight Must think in terms of k-period communication sequences s = {Prod 1, Prod*, Prod2,...Prod1} P d1} Prod* - is an artificial offer signifying a decision not to communicate In our example, assuming 3-period planning horizon, some of the sequences are {Prod1, Prod1, Prod1} {Prod1,Prod2,Prod3} P d2 P d3} {Prod*, Prod4,Prod*} Etc. For each sequence s must be able to estimate t k- period expected response pattern: Expected response for each product in each period if sequence s is used 26
M 2 O: Main Challenges Estimation: Statistical models must be sophisticated enough to capture full cross-product cross-period effects Data management Must capture long communication history in the data Must have enough variation in histories at the target level to enable accurate estimation Optimization With m products and k planning periods there are (m+1) k potential communication sequences for each target The dimensionality of the Optimization model becomes huge Even in our toy example with 3 planning periods, 5 product and 15 targets have 15*(6)3 = 3240 decision variables For practical problems need effective heuristics (specialized algorithms) Planning cycles are often compressed in time: quick running times amust 27
Payoff: M 2 O in Action M 2 OStarts
Payoff: M 2 O in Action, an example The system has now been implemented for 6 quarters Gradually gained trust, allowed more participation i i in planning / budget allocation The system is very profitable for the client ROI of between 1,690% to 2,141% based on 12 month net cash; ROI of between 4,063% to 5,099% based on LTV About 2/3 of the total impact comes from better targeting, about 1/3 comes from planning support During each planning period, on average 50% of the initial iti budget gets re-allocated based on system s recommendations The client is now much more attuned to costing out constraints before imposing them, etc. 29
Beyond M 2 0: Multi-product, Multiperiod, multi-channel system (M 3 0) Natural next step is to integrate multiple communication channels Easy part: if at most one communication per target per period rule holds, channels can be regarded as new offers Dimensionality grows, but the system still works Hard part: communications can be overlaid E.g., a direct mail and E-mail in the same period Need to estimate cross-channel effects; may differ by communication sequence Dimensionality jumps Work in progress... 30
Outline Direct marketing and Analytical Models MO: Multi-Product Optimization System M 2 0: Multi-Product Multi-Period Optimization System Summary Decision Support for DM Other challenges 31
Decision Support for Direct Marketing 3 0 MO M Typical Basic Execution: LTV-based cross-product cross-channel multi-period optimization Strategic support: Comprehensive analysis of budgetary scenarios, offer timing, channel interactions Prevalence: We (Custometrics) are getting there Execution: LTV-based analytical models with cross-product single-channel optimization within each period Strategic support: Limited (single-period, single-channel scenarios can be analyzed) Prevalence: state of the art; only a few leading-edge organizations have access to this technology Execution: Product-specific p ranking models Strategic support: data-base pulls only Prevalence: typical operating mode for an organization with strong analytics support team (major banks, etc.) Execution: Business decision i rules Strategic support: data-base pulls only Prevalence: very common 32
Other challenges Integrating channels with different target concepts E.g., mass and 1:1 channels Evaluation Many challenging problems As the sophistication of the Decision Support Systems grows, so do the evaluation challenges: how do you measure impact of a truly strategic system? Execution Many tough and interesting analytical problems at this stage as well 33
Optimizing Direct Marketing Campaigns Questions? 34