BT4211 Data-Driven Marketing: Customer: Purchase Choice, Quantity, Duration

BT4211
Data-Driven Marketing
Customer: Purchase Choice, Quantity,
Duration
March 7, 2018 1
Purchase Decisions & Models
 Purchase choice
– Whether the customer will buy/churn?
– What brand/product/service will the customer buy?
• Binary logit (logistic regression) model, multinomial logit model
 Purchase quantity
– How much or how many units will the customer buy?
• Count data model (Poisson, negative binomial)
 Duration: inter-purchase, customer lifetime
– How soon will the customer make another purchase?
– How long will the customer stay on with the firm?
• Linear regression model, hazard model
2
Binary Response Models
 Linear probability model
– Link function
3
 Linear probability model

– Problems for binary responses
• Error term violates homoscedasticity assumption of
classical linear regression model
– Heteroscedasticity, if not corrected for, can increase prediction
error
• Predicted probability may not be bounded from 0 to 1
– Predictions can be impossible to interpret as probabilities
4
 Binary logit (logistic regression) model

– Link function
– Estimation method
• Maximum likelihood estimation
– Interpretation
• Odds ratio:
• Odds ratio per standard deviation change in x:
5
 Binary probit model

– Link function
6
 Logistic regression with rare events data

– Problems
• Rare event response rates below 1% are not unusual
• Binary logit and probit models can under-estimate
response probability in such cases
• Predicted response probabilities under-estimate the
actual likelihood of response
– Solutions
• Adjustments with choice-based sampling
7
Multinomial Response Models
 Multinomial response model

– Specification
• Number of choice (or response) alternatives is J
• Probability of a consumer i choosing alternative j
– Applications
• Brand or product choices
• Customer segment predictions
8
 Choice of function results in different

multinomial model types
• Examples: logit, probit, nested logit, ordered logit, etc.
 Alternative-varying regressors
• Regressors xi take different values for different alternatives
• Examples: costs of transport modes, prices of brands

 Alternative-invariant regressors
• Regressors xi take same values across alternatives
• Examples: socioeconomic status such as income, gender 9

 Model evaluation and selection methods

– Range of in-sample fitted probabilities for each
alternative
• Wider the range, the more discriminating is the model
– Akaike and/or Bayesian Information Criterion
– Pseudo R2
10
 Conditional logit model (CL)
• For alternative-varying regressors
 Multinomial logit model (MNL)

• For alternative-invariant regressors
 Mixed logit model (ML)

• For both alternative-varying and -invariant regressors
11
 Example:
12
 Example: marginal effects

– Conditional logit model (CL):
– Multinomial logit model (MNL):
13
Marginal Effects of Regressors
 Marginal effects of regressors:

– Change in conditional mean of y when regressors
x change by one unit
– Linear regression:
– Non-linear regression:
– General regression function
14
Marginal Effects of Regressors
 Marginal effects of regressors

– Calculus method
– All 3 measures are same for linear models

– All 3 measures are different for non-linear models
• Care must be taken in interpreting estimated coefficients
• R, Stata commands: margins, after model estimations 15
Count Data Models
 Overview of count data

– Discrete data with ordered metric (0,1,2,3,…)
• Examples
– Number of beers a consumer drinks in a week
– Number of mail orders a customer makes in a year
– Number of complaints a customer makes in a month
– Alternative modeling methods
• Multinomial logit model
– Inappropriate since dependent variable is ordered
• Linear regression model
– Inappropriate assumptions of normally distributed error terms
and continuous nature of dependent variable
16
Count Data Models
 Poisson regression model

– Specification
17
Count Data Models

– Limitations
• Distribution is parameterized in terms of a single scalar
parameter
• Excess zeros problem
– More zeros in data than Poisson model predicts
• Over-dispersion in data
– Variance exceeds mean but Poisson model implies equality of
variance and mean
– Poisson MLE is still consistent, if conditional mean is correctly
specified
– Leads to deflated standard errors, inflated t statistics
– Over-dispersion and under-dispersion test statistics
18
Count Data Models
 Negative binomial regression model

– Specification
• Conditional distribution of Yi given ui
• Unconditional distribution of Yi
19
Count Data Models

– Specification
• Unconditional distribution of Yi with ui assumed to be
from a Gamma distribution
• Mean:
• Variance:
20
Duration Models
 Overview of duration data

– Continuous or discrete time duration variable
• Example questions addressed by duration models
– What is the probability that a customer in a telecommunication
company will remain as a customer after a year?
– What is the attrition probability of each customer in a month?
– Are attrition probabilities different depending on the customer’s
demographic characteristics?
– What is the expected duration of a customer’s relationship with
the firm?
26
Duration Models
 Overview of duration data
– Censoring
• Buyer 1: complete information
• Buyer 2: left-censored
• Buyer 3: right-censored
• Buyer 4: left-and-right censored
• Buyer 5: interval-censored
Buyer 1
Buyer 2
Buyer 3
Buyer 4
Buyer 5
t0 Observation Window tN

27
Duration Models
 Linear regression model

– Method
• Simplest model to explain the relation between customer duration and
other explanatory variables
• Focus only on sample of prior customers (with full lifespan observed)
and omit right-censored observations, i.e., current customers
– Limitations
• Potential censoring bias, since data sample does not include all
customers, but only those prior ones with full lifespan observed
– Problematic especially when number of complete observations is small
relative to number of incomplete observations (i.e., current customers)
• Limited in helping to manage customer relationships
– Does not address probability of attrition during specified time periods
28
Duration Models
 Hazard model
– Objective
• Models length of time spent in a given state before
transition to another state
– Duration from being an active customer to a churned one
– Duration between two consecutive purchases
– Basic concepts
• Cumulative distribution function
• Survivor function
– Probability that the length of duration is at least t 29

Duration Models
 Hazard model
– Basic concepts
• Hazard rate function
– Instantaneous probability of leaving a state conditional on

survival to time t
• Cumulative hazard rate function
30
Duration Models
 Hazard model
– Basic concepts
• Hazard rate function: examples
31
Duration Models
 Hazard model
– Basic concepts
• Hazard rate function plots
32
Duration Models
 Hazard model
– Exponential distribution
• Constant hazard rate that does not vary with time
• Memory-less property
– Weibull distribution
• Hazard is monotonically increasing if
• Hazard is monotonically decreasing if
• can be a function of covariates X
– Generalized Weibull distribution
• Additional shape parameter , gives more flexibility
• Hazard is unimodal or U-shaped if 33
Duration Models
 Hazard model
– Gompertz distribution
• Hazard is monotonically increasing if
– Log-normal distribution
• Hazard is inverted U-shaped
– Log-logistic distribution
• Hazard is inverted U-shaped if
– Main issues in modeling
• Dependence on correct model specification
• Proportional Hazard (PH) model
• Accelerated Failure Time (AFT) model 34
Duration Models
 Maximum likelihood estimation

• Uncensored observations
• Censored observations
 Likelihood function for ith observation
 Log-likelihood function for entire sample
35
Proportional Hazard Model
 Conditional hazard rate
 Baseline hazard
• If 0 (t ,  ) is assumed to be non/semi-parametric =>

Cox Proportional Hazard model
 Scale factor
 Distributional examples
• Exponential, Weibull, Gompertz distributions 36
Proportional Hazard Model
 Interpretation
– Hazard ratio:
– Relative hazard rate:
• Percentage change of hazard rate with respect to the
unit change of the independent variable
37
Accelerated Failure Time Model
 Models ln(t) rather than t
 Conditional hazard rate
• Acceleration of baseline hazard if

• Deceleration of baseline hazard if
 Distributional examples
• Exponential, Weibull, Log-normal, Log-logistic distribution 38
Stata Commands for Models
 Linear regression model

• reg; xtreg
 Binary logit, probit model
• logit; probit; xtlogit; xtprobit
 Conditional logit model
• clogit
 Multinomial logit model
• mlogit
• poisson; xtpoisson
39
Stata Commands for Models

• nbreg; xtnbreg
 Tobit (Type I) model
• tobit; xttobit
 Tobit (Type II) model
• heckman
 Proportional hazard model
• stcox x1, x2, …; streg x1, x2, …; xtstreg x1, x2, …
 Accelerated failure time model
• streg x1, x2, …, time; xtstreg x1, x2, …, time
40

BT4211 Data-Driven Marketing: Customer: Purchase Choice, Quantity, Duration

Uploaded by

Copyright:

Available Formats

BT4211 Data-Driven Marketing: Customer: Purchase Choice, Quantity, Duration

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

BT4211 Data-Driven Marketing: Customer: Purchase Choice, Quantity, Duration

Uploaded by

Copyright:

Available Formats

BT4211

 Linear probability model

 Linear probability model

 Binary logit (logistic regression) model

 Binary probit model

 Logistic regression with rare events data

 Multinomial response model

 Choice of function results in different

• Examples: costs of transport modes, prices of brands

• Examples: socioeconomic status such as income, gender 9

 Model evaluation and selection methods

 Multinomial logit model (MNL)

 Mixed logit model (ML)

 Example: marginal effects

 Marginal effects of regressors:

– General regression function

 Marginal effects of regressors

– All 3 measures are same for linear models

 Overview of count data

 Poisson regression model

 Poisson regression model

 Negative binomial regression model

• Conditional distribution of Yi given ui

 Negative binomial regression model

 Overview of duration data

t0 Observation Window tN

 Linear regression model

– Probability that the length of duration is at least t 29

– Instantaneous probability of leaving a state conditional on

 Maximum likelihood estimation

 Likelihood function for ith observation

 Log-likelihood function for entire sample

 Conditional hazard rate

• If 0 (t ,  ) is assumed to be non/semi-parametric =>

 Models ln(t) rather than t

 Conditional hazard rate

• Acceleration of baseline hazard if

 Linear regression model

 Negative binomial regression model

You might also like