SlideShare ist ein Scribd-Unternehmen logo
1 von 22
Downloaden Sie, um offline zu lesen
Optimal Personalized Treatment Learning Models
with Insurance Applications
PhD Student: Leo Guelman
Advisor: Dr. Montserrat Guill´en
PhD in Economics
University of Barcelona
March 2, 2015
1 / 22
Outline
1 Motivation
2 Problem formulation
3 Objectives
4 Challenges
5 Contributions
6 Limitations and future work
2 / 22
Motivation
Predictive learning has been established as a core strategic
capability in many scientific disciplines and industries.
Common goal: Predict the value of a response variable using
a collection of covariates or “predictors” under static
conditions.
From Predictive to Causal Modeling
• Predictive Modeling has been established as a core strategic capability of
many top insurers.
• Common goal: to predict a response variable using a collection of attributes
under static conditions — i.e., assumes “business as usual” conditions.
• Causal Modeling goes one step further: the interest is in estimating/
predicting the response under changing conditions — e.g., induced by
alternative actions or “treatments”.
3
X YCovariates Response
XCovariates Potential responses
Y (1)
Y (2)
Actions
A = 0
A = 1
Causal learning goes one step further: the interest is in
estimating/predicting the response under changing conditions
– e.g., induced by alternative actions or “treatments”.
From Predictive to Causal Modeling
• Predictive Modeling has been established as a core strategic capability of
many top insurers.
• Common goal: to predict a response variable using a collection of attributes
under static conditions — i.e., assumes “business as usual” conditions.
• Causal Modeling goes one step further: the interest is in estimating/
predicting the response under changing conditions — e.g., induced by
alternative actions or “treatments”.
3
X YCovariates Response
XCovariates Potential responses
Y (1)
Y (2)
Actions
A = 0
A = 1
3 / 22
Motivation
In the context of causal learning, the main interest has been in
identifying the Average Treatment Effect (ATE):
ATE = E[Y |A = 1] − E[Y |A = 0].
In many important settings, subjects can show significant
heterogeneity in response to actions/treatments – i.e., what
works for one subject may not work for another. Here the ATE is
less relevant.
The objective becomes to select the optimal action or
“treatment” for each subject based on individual characteristics.
Introduction
Current Approaches
Personalized Medicine
Goal
“Providing meaningful improved health outcomes for patients by
delivering the right drug at the right dose at the right time.”
How Do We Apply Personalized Medicine?
Learn individualized treatment rules: tailor treatments based
on patient characteristics.
Concepts & Tools
Symptoms
Demographics
Disease history
Biomarkers
Imaging
Bioinformatics
Pharmacogenomics
Concepts & Tools
Symptoms
Demographics
Disease history
Biomarkers
Imaging
Bioinformatics
Pharmacogenomics
When Do We Apply Personalized Medicine?
Single-Decision Setup.
Multi-Decision Setup.
Optimal defined as the treatment that maximizes the probability
of a desirable outcome.
We call the task of learning the optimal personalized treatment
personalized treatment learning (PTL).
4 / 22
Problem Formulation
Assume a randomized experiment – i.e., subjects are randomly
assigned to two treatments, denoted by A ∈ {0, 1}.
Let Y (a) ∈ {0, 1} denote a binary potential response of a
subject if assigned to treatment A = a, a = {0, 1}.
So the observed response is Y = AY (1) + (1 − A)Y (0).
Subjects are characterized by a p-dimensional vector of
baseline predictors X = (X1, . . . , Xp) .
Data consist of L i.i.d. realizations of
(Y , A, X), {(Y , A , X ), = 1, . . . , L}.
5 / 22
Problem Formulation
At the most granular level, the personalized treatment
effect (PTE) is a comparison between Y (1) and Y (0) on the
same subject. Usually,
Y (1) − Y (0) ∀ = {1, . . . , L}.
But this quantity is unobserved...
In practice, the best we can do is to estimate the PTE by
conditioning on subjects with profile X = x.
Thus, we define the PTE by
τ(x) = E[Y (1) − Y (0)|X = x]
= E[Y |X = x, A = 1] − E[Y |X = x, A = 0].
6 / 22
Problem Formulation
A personalized treatment rule H is a map from the space of
baseline covariates X to the space of treatments A,
H(X) : Rp
→ {0, 1}.
An optimal treatment rule is one that maximizes the expected
outcome, E[Y (H(X))], if the personalized treatment rule is
implemented for the whole population.
Since Y is binary, this expectation has a probabilistic interpretation.
That is, E[Y (H(X))] = P Y (H(X)) = 1 and thus τ(x) ∈ [−1, 1].
Assuming all treatments cost the same, the optimal personalized
treatment rule H∗
= argmaxH E[Y (H(X))] for a subject with
covariates X = x is given by
H∗
=
1 if τ(x) > 0
0 otherwise.
7 / 22
The Simplest Approach to PTE Estimation
1 Estimate E[Y |X, A = 1] using the treated subjects only.
2 Estimate E[Y |X, A = 0] using the control subjects only.
3 An estimate of the PTE for a subject with predictors X = x is
ˆτ(x) = ( ˆY |X = x , A = 1) − ( ˆY |X = x , A = 0).
Pros:
Any conventional statistical or algorithmic binary classification
method may serve to fit the models.
Cons:
Method aims to predict the wrong target: it emphasizes the
prediction accuracy on the response under each treatment, not
the accuracy in estimating the change in the response
caused by the treatment.
Relevant predictors for Y under each treatment are usually
different from relevant PTE predictors.
As a result, it tends to perform poorly in practice.
8 / 22
Objectives
Formalize personalized treatment learning (PTL) as a new
branch of statistical learning.
Create the first comprehensive systematic review of the
existing PTL methods (Tian and Tibshirani, 2014; Radcliffe and
Surry, 2011; Ja´skowski and Jaroszewicz, 2012; Su et al., 2009; Qian and
Murphy, 2011; Zhao et al., 2012; Rubin and Waterman, 2006;
Larsen, 2009; Imai and Ratkovic, 2013, and others).
Build improved statistical/algorithmic methods for
estimating, selecting and assessing PTL models.
Introduce PTL models to insurance applications.
Build open source software implementing our proposed
methods for fitting PTL models, as well as the existing ones,
and make it freely available for academia/industry.
9 / 22
Key Challenges
The fundamental problem of PTL models: The quantity we are
trying to predict (i.e., the optimal personalized treatment) is
unknown on a given training data set.
Size of main effects relative to treatment heterogeneity
effects: The magnitude of the variability in the response due to the
treatment heterogeneity effects is usually much smaller than the
variability due to the main effects.
Overfitting: The risk of overfitting increases markedly in PTL
models compared to conventional predictive learning problems.
Model selection and assessment: Methods for variable selection
and model selection/assessment used in conventional predictive
learning problems need to be redefined in the context of PTL
models.
10 / 22
Contributions
Introduced and formalized the concept of personalized treatment
learning (PTL) within a causal inference framework, and described
its relevance to a wide variety of fields ranging from economics to
medicine (Ch. 1-2).
Provided the first comprehensive description of the existing PTL
methods (Ch. 3) and proposed two novel methods – namely, uplift
random forests (Ch. 4) and causal conditional inference trees
(Ch. 5). Our proposal outperforms the existing methods in an
extensive numerical simulation study (Ch. 6).
PTL models require not only developing new estimation methods,
but also new methods for assessing model performance. We
formalized the concept of the Qini curve and the Qini coefficient,
and discussed general useful methods for model assessment and
selection for PTL models (Ch. 7).
11 / 22
Contributions
We described the relevance of PTL models to insurance
marketing, and illustrated two applications to optimize client
retention and cross-selling using experimental data from a large
Canadian insurer (Ch. 8).
We presented a novel approach to measuring price-elasticity and
economic price optimization in non-life insurance based on PTL
modeling principles in the context of observational data (Ch. 9).
Selecting the optimal personalized treatment in insurance also
requires consideration of the expected losses under treatment
alternatives. We described an unprecedented application of
gradient boosting models to estimate loss cost in non-life
insurance, with key advantages over the conventional generalized
linear model approach (Ch. 10).
We implemented most of the statistical methods and algorithms
described in this thesis in a package named uplift (Guelman, 2014),
which is now freely available from the CRAN (Comprehensive R
Archive Network) repository under the R statistical computing
environment (Ch. 11).
12 / 22
PTL with Experimental Data
An Application to Insurance Cross-Sell Optimization
Cross-sell rates by group
Treatment Control
Purchased home policy = N 30,184 3,322
Purchased home policy = Y 789 75
Cross-sell rate 2.55% 2.21%
The average treatment effect (ATE) is 0.34% (2.55% −
2.21%) which is NOT statistically significant (P value =
0.23).
Cross-sell rate by PTL model decile
Deciles
0.03 0.06
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q q
Profitable targets Not profitable targets
0
2
4
6
8
10
12
1 2 3 4 5 6 7 8 9 10
Decile
Cross−sellrate(%)
Group q qTreatment Control
Prototype causal conditional inference tree
0.34%
0.05%
prodCnt ≤ 1
0.65%
1.22%
adjBranch
0.38%
0.67% 2.52%
age ≤ 45
-1.2% 0.32%
xdate ≤ 2
-1.6%
age ≤ 42
-0.2%
The tree-based procedure identifies
a subgroup of clients with significant
positive impact from the cross-sell
activity (PTE = 2.52%).
13 / 22
Causal Conditional Inference Tree - Pseudocode
Algorithm 1 Causal conditional inference tree
1: for each terminal node do
2: Test the global null hypothesis H0 of no interaction effect between
the treatment A and any of the p predictors at a level of significance
α based on a permutation test (Strasser and Weber, 1999)
3: if the null hypothesis H0 cannot be rejected then
4: Stop
5: else
6: Select the j∗
th predictor Xj∗ with the strongest interaction effect
(i.e., the one with the smallest adjusted P value)
7: Choose a partition Ω∗
of the covariate Xj∗ in two disjoint sets
M ⊂ Xj∗ and Xj∗  M based on the G2
(Ω) split criterion
8: end if
9: end for
G2
(Ω) =
(L − 4){
Left Node
( ¯YnL
(1) − ¯YnL
(0)) −
Right Node
( ¯YnR
(1) − ¯YnR
(0))}2
ˆσ2{1/LnL
(1) + 1/LnL
(0) + 1/LnR
(1) + 1/LnR
(0)}
14 / 22
Numerical simulations – Performance comparison
“Strong” treatment heterogeneity effects
Simulation scenarios are obtained by varying: (i) the strength of the main
effects relative to the treatment heterogeneity effects, (ii) the correlation
among the covariates, (iii) the magnitude of the random noise.
qqqqqq
q
q
qqqq
qqq
qqq
q
q
qqqq
q
qqqqq
qqqqqqqq qqqq
q
qqqqq
qqqqqqqq q
q
q q
q
q
q q q q
q q q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
qq
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q q
q
q q
q
q
q
q q
q q q q
q q q
q
q
qq
q
qq
q
q
q
qq
q
qq
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
qq
q
qq
q
q
q
q
q q q
q q
q
q q
Scenario 1 Scenario 2
Scenario 3 Scenario 4
0.00
0.25
0.50
0.75
0.00
0.25
0.50
0.75
0.00
0.25
0.50
0.75
−0.3
0.0
0.3
0.6
l2svm
ccif
upliftRF
dsm
dsm−RF
mom−RF
mom
mcm
cknn
mcm−RF
int
int−RF
ccif
upliftRF
dsm−RF
mom−RF
cknn
mcm−RF
int−RF
l2svm
mom
mcm
dsm
int
ccif
l2svm
upliftRF
mom−RF
dsm−RF
mom
mcm
dsm
mcm−RF
cknn
int−RF
int
ccif
upliftRF
dsm−RF
mom−RF
mcm−RF
cknn
int−RF
mom
mcm
l2svm
dsm
int
Method
Spearman'srankcorrelationcoefficient
15 / 22
Numerical simulations – Performance comparison
“Weak” treatment heterogeneity effects
q
q
q
q
q qq
q
q
q
q
q
q q
q
q q
q q
q q
q
q
q
q
q
q
q
qq
q
q
q
qq
q
qq
q
qq
q
qq
qq
q
q q q
q q q q
q
q
q q
q
qq q
q
q
q
q
qq
q
q
q
q
q
q
qq
q
q
q
q
q
q
q
q
q q
q
q q q
q
q
q q
qq
q
q
q
q
q
q
q
q
q
q
q
qq
q
q
q
q
q
q
q
q
q
q
q
qq
q
q
q
qqq
q
q
q
q
q
q
q
q
q
q
qq
q
q
q
qqq
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
qq
q
q
q
q
qq
q
q q
q
q q q
q q q q
q
Scenario 5 Scenario 6
Scenario 7 Scenario 8
0.00
0.25
0.50
0.75
−0.5
0.0
0.5
0.00
0.25
0.50
0.75
−0.25
0.00
0.25
0.50
dsm
ccif
upliftRF
l2svm
dsm−RF
mom−RF
int
cknn
mcm−RF
int−RF
mom
mcm
ccif
upliftRF
dsm−RF
dsm
mom−RF
cknn
mcm−RF
int−RF
l2svm
mom
mcm
int
dsm
ccif
upliftRF
dsm−RF
mom−RF
mcm−RF
cknn
l2svm
int−RF
int
mom
mcm
ccif
upliftRF
dsm−RF
mom−RF
mcm−RF
cknn
dsm
int−RF
l2svm
mom
mcm
int
Method
Spearman'srankcorrelationcoefficient
16 / 22
PTL with Observational Data
An application to Auto Insurance Economic Price Optimization
Background
Objective: Determine the
policyholder-level premium
(playing the role of the
treatment) that maximizes the
expected profitability of an
existing insurance portfolio,
subject to a fixed overall retention
rate.
Requires estimating the expected
client retention outcome under
alternative insurance rates (price
elasticity), and loss cost.
Clients were historically exposed
to rating actions based on a
non-random assignment
mechanism, which requires
designing an observational study.
Maximize an expected profit function
Max
Z a∀ ∀a
∀ ∀a
Z a P (1 + RCa)(1 − ˆLR a)(1 − ˆˆr a)
subject to a retention constraint
∀a
Z a = 1 ∀
Z a ∈ {0, 1}
∀ a
Z a
ˆˆr a/L ≤ α.
q
Current state
Efficie
ntfrontie
r
A
B
C
0
10
20
30
0.90 0.92 0.94 0.96
Retention rate (1 − α)
Expectedprofit(%)
17 / 22
uplift Package Highlights
First R package implementing PTL models
Exploratory Data Analysis (EDA) tools customized for
PTL models
Check balance of covariates (checkBalance)
Univariate uplift analysis (explore)
Preliminary variable screening (niv)
Estimating personalized treatment effects
Causal conditional inference forests (ccif)
Uplift random forests (upliftRF)
Modified covariate method (tian_transf)
Modified outcome method (rvtu)
Uplift k-nearest neighbor (upliftKNN)
Performance assessment for PTL models
Uplift by decile (performance)
Qini curve and Qini-coefficient (qini)
Other functionality
Profiling PTL models (modelProfile)
Monte-Carlo simulations (sim_pte)
18 / 22
Fitting a CCIF using uplift
ccif implements recursive partitioning in a causal conditional inference
framework.
fit <- ccif(formula = Y ~ trt(A) + X1 + X2 + X3,
data = mydata,
ntree = 1000,
split_method = "Int",
distribution = approximate (B=999),
pvalue = 0.05,
verbose = TRUE)
Table: Some ccif options
ccif argument Description
mtry Number of variables to be tested in each node
ntree Number of trees in the forest
split_method Split criteria: "KL", "ED", "Int" or "L1"
interaction.depth The maximum depth of variable interactions
pvalue Maximum acceptable p-value required to make a split
bonferroni Apply Bonferroni adjustment to pvalue
minsplit Minimum number of obs. for a split to be attempted
... Additional args. passed to coin::independence_test.
19 / 22
Manuscripts Linked to Thesis
[1] Guelman, L. (2014). uplift: Uplift modeling. R package version 0.3.5.
[2] Guelman, L. and Guill´en, M. (2014). A causal inference approach to measure price
elasticity in automobile insurance. Expert Systems with Applications, 41(2):387–396.
[3] Guelman, L., Guill´en, M. and P´erez-Mar´ın, A. M. (2014). A survey of personalized
treatment models for pricing strategies in insurance. Insurance: Mathematics and
Economics, 58:68–76.
[4] Guelman, L., Guill´en, M. and P´erez-Mar´ın, A. M. (2014). Uplift random forests.
Cybernetics & Systems. Accepted.
[5] Guelman, L., Guill´en, M. and P´erez-Mar´ın, A. M. (2014). A decision support
framework to implement optimal personalized marketing interventions. Decision
Support Systems, 72: 24–32.
[6] Guelman, L. (2012). Gradient boosting trees for auto insurance loss cost modeling
and prediction. Expert Systems with Applications, 39(3):3659–3667.
[7] Guelman, L., Guill´en, M. and P´erez-Mar´ın, A. M. (2012). Random forests for uplift
modeling: An insurance customer retention case. In Engemann, K. J., Lafuente, A. M.
G., and Merig´o, J. M., editors, Modeling and Simulation in Engineering, Economics
and Management, pages 123–133. Springer Berlin Heidelberg, New York, NY.
20 / 22
Talks Linked to Thesis
[1] Guill´en, M. and Guelman, L. (2014). “New trends in predictive modelling - the uplift models success story”.
R in Insurance Conference, London, UK. (July 14, 2014).
[2] Guelman, L. and Guill´en, M. (2014). “Actionable predictive learning for insurance profit maximization”.
Casualty Actuarial Society, Ratemaking and Product Management Seminar, Washington, D.C., USA (April 1,
2014).
[3] Guelman, L. (2013). “An introduction to causal learning with applications to price elasticity modeling in
Casualty insurance”. University of Barcelona, UB Economics Seminars, Barcelona, Spain (November 28, 2013).
[4] Guelman, L., Guill´en, M. and P´erez-Mar´ın, A.M. (2013). “Evaluating customer loyalty with advanced uplift
models”. APRIA, Annual Conference, New York, USA (July 28-31, 2013).
[5] Guill´en, M., Guelman, L., M. and P´erez-Mar´ın, A.M. (2013). “Customer retention and price elasticity. Are
motor insurance policies homogeneous with respect to loyalty?”. 2013 Astin colloquium, The Hague, Netherlands
(May 21-24, 2013).
[6] Guelman, L. and Lee, S. (2013). “Balancing robust statistics - gradient boosting”. Casualty Actuarial Society,
Ratemaking and Product Management Seminar, Los Angeles, USA (March 12-13, 2013).
[7] Guelman, L., Guill´en, M. and P´erez-Mar´ın, A.M. (2012). “Random forests for uplift modeling: an insurance
customer retention case”. Association of Modeling and Simulation in Enterprise (AMSE) - International Conference
on Modeling and Simulation, New York, USA (May 30-June 1, 2012). – Outstanding Scholarly Research
Contribution Award, AMSE.
[8] Guelman, L. and Lee, S. (2012). “Balancing robust statistics and data mining in ratemaking: gradient boosting
modeling”. Casualty Actuarial Society, Ratemaking and Product Management Seminar, Philadelphia, USA (March
20-21, 2012).
21 / 22
Limitations and Future Work
1 Extensions to multi-category and continuous treatment settings.
2 Extensions to continuous uncensored and survival responses.
3 Extensions to dynamic treatment regimes: treatment type may be
repeatedly adjusted according to an ongoing individual response.
4 Absolute vs. relative treatment effects – in some settings, defining
the treatment effect in terms of the ratio of the expected responses
under alternative treatment conditions, instead of the difference
between the expected responses may be more appropriate.
22 / 22

Weitere ähnliche Inhalte

Was ist angesagt?

2010 smg training_cardiff_day1_session3_higgins
2010 smg training_cardiff_day1_session3_higgins2010 smg training_cardiff_day1_session3_higgins
2010 smg training_cardiff_day1_session3_higgins
rgveroniki
 
Interventions for children’s dental anxiety: Validating a coping styles scale
Interventions for children’s dental anxiety: Validating a coping styles scaleInterventions for children’s dental anxiety: Validating a coping styles scale
Interventions for children’s dental anxiety: Validating a coping styles scale
Matt Williams
 
PMED Opening Workshop - Credible Ecological Inference for Medical Decisions w...
PMED Opening Workshop - Credible Ecological Inference for Medical Decisions w...PMED Opening Workshop - Credible Ecological Inference for Medical Decisions w...
PMED Opening Workshop - Credible Ecological Inference for Medical Decisions w...
The Statistical and Applied Mathematical Sciences Institute
 

Was ist angesagt? (20)

Regression to the Mean
Regression to the MeanRegression to the Mean
Regression to the Mean
 
Nicholas Jewell MedicReS World Congress 2014
Nicholas Jewell MedicReS World Congress 2014Nicholas Jewell MedicReS World Congress 2014
Nicholas Jewell MedicReS World Congress 2014
 
Ct lecture 6. test of significance and test of h
Ct lecture 6. test of significance and test of hCt lecture 6. test of significance and test of h
Ct lecture 6. test of significance and test of h
 
2010 smg training_cardiff_day1_session3_higgins
2010 smg training_cardiff_day1_session3_higgins2010 smg training_cardiff_day1_session3_higgins
2010 smg training_cardiff_day1_session3_higgins
 
Cochrane Collaboration
Cochrane CollaborationCochrane Collaboration
Cochrane Collaboration
 
演講-Meta analysis in medical research-張偉豪
演講-Meta analysis in medical research-張偉豪演講-Meta analysis in medical research-張偉豪
演講-Meta analysis in medical research-張偉豪
 
Introduction tocausalinference april02_2020
Introduction tocausalinference april02_2020Introduction tocausalinference april02_2020
Introduction tocausalinference april02_2020
 
Network meta-analysis & models for inconsistency
Network meta-analysis & models for inconsistencyNetwork meta-analysis & models for inconsistency
Network meta-analysis & models for inconsistency
 
4. Calculate samplesize for cross-sectional studies
4. Calculate samplesize for cross-sectional studies4. Calculate samplesize for cross-sectional studies
4. Calculate samplesize for cross-sectional studies
 
Imran rizvi statistics in meta analysis
Imran rizvi statistics in meta analysisImran rizvi statistics in meta analysis
Imran rizvi statistics in meta analysis
 
Duration of Psychological Therapy
Duration of Psychological TherapyDuration of Psychological Therapy
Duration of Psychological Therapy
 
Statistics in meta analysis
Statistics in meta analysisStatistics in meta analysis
Statistics in meta analysis
 
Does publication bias inflate the apparent efficacy of psychological treatmen...
Does publication bias inflate the apparent efficacy of psychological treatmen...Does publication bias inflate the apparent efficacy of psychological treatmen...
Does publication bias inflate the apparent efficacy of psychological treatmen...
 
Interventions for children’s dental anxiety: Validating a coping styles scale
Interventions for children’s dental anxiety: Validating a coping styles scaleInterventions for children’s dental anxiety: Validating a coping styles scale
Interventions for children’s dental anxiety: Validating a coping styles scale
 
Meta analysis
Meta analysisMeta analysis
Meta analysis
 
PMED Opening Workshop - Credible Ecological Inference for Medical Decisions w...
PMED Opening Workshop - Credible Ecological Inference for Medical Decisions w...PMED Opening Workshop - Credible Ecological Inference for Medical Decisions w...
PMED Opening Workshop - Credible Ecological Inference for Medical Decisions w...
 
PMED Transition Workshop - Some Recent Advances in Precision Medicine and Mac...
PMED Transition Workshop - Some Recent Advances in Precision Medicine and Mac...PMED Transition Workshop - Some Recent Advances in Precision Medicine and Mac...
PMED Transition Workshop - Some Recent Advances in Precision Medicine and Mac...
 
8.Calculate samplesize for clinical trials (continuous outcome)
8.Calculate samplesize for clinical trials (continuous outcome)8.Calculate samplesize for clinical trials (continuous outcome)
8.Calculate samplesize for clinical trials (continuous outcome)
 
META ANALYSIS
META ANALYSISMETA ANALYSIS
META ANALYSIS
 
Network meta-analysis with integrated nested Laplace approximations
Network meta-analysis with integrated nested Laplace approximationsNetwork meta-analysis with integrated nested Laplace approximations
Network meta-analysis with integrated nested Laplace approximations
 

Andere mochten auch (6)

HdR
HdRHdR
HdR
 
Soutenance julie viard_partie_1
Soutenance julie viard_partie_1Soutenance julie viard_partie_1
Soutenance julie viard_partie_1
 
Econometrics 2017-graduate-3
Econometrics 2017-graduate-3Econometrics 2017-graduate-3
Econometrics 2017-graduate-3
 
Graduate Econometrics Course, part 4, 2017
Graduate Econometrics Course, part 4, 2017Graduate Econometrics Course, part 4, 2017
Graduate Econometrics Course, part 4, 2017
 
Econometrics, PhD Course, #1 Nonlinearities
Econometrics, PhD Course, #1 NonlinearitiesEconometrics, PhD Course, #1 Nonlinearities
Econometrics, PhD Course, #1 Nonlinearities
 
Slides econometrics-2017-graduate-2
Slides econometrics-2017-graduate-2Slides econometrics-2017-graduate-2
Slides econometrics-2017-graduate-2
 

Ähnlich wie Lg ph d_slides_vfinal

25_Anderson_Biostatistics_and_Epidemiology.ppt
25_Anderson_Biostatistics_and_Epidemiology.ppt25_Anderson_Biostatistics_and_Epidemiology.ppt
25_Anderson_Biostatistics_and_Epidemiology.ppt
PriyankaSharma89719
 
Theory and Practice of Integrating Machine Learning and Conventional Statisti...
Theory and Practice of Integrating Machine Learning and Conventional Statisti...Theory and Practice of Integrating Machine Learning and Conventional Statisti...
Theory and Practice of Integrating Machine Learning and Conventional Statisti...
University of Malaya
 

Ähnlich wie Lg ph d_slides_vfinal (20)

#2ECcourse.ppthjjkhkjhkjhjkjhkhhkhkhkhkj
#2ECcourse.ppthjjkhkjhkjhjkjhkhhkhkhkhkj#2ECcourse.ppthjjkhkjhkjhjkjhkhhkhkhkhkj
#2ECcourse.ppthjjkhkjhkjhjkjhkhhkhkhkhkj
 
#2ECcourse.pptgjdgjgfjgfjhkhkjkkjhkhkhkjhjkj
#2ECcourse.pptgjdgjgfjgfjhkhkjkkjhkhkhkjhjkj#2ECcourse.pptgjdgjgfjgfjhkhkjkkjhkhkhkjhjkj
#2ECcourse.pptgjdgjgfjgfjhkhkjkkjhkhkhkjhjkj
 
Does transfer to intensive care units reduce mortality for deteriorating ward...
Does transfer to intensive care units reduce mortality for deteriorating ward...Does transfer to intensive care units reduce mortality for deteriorating ward...
Does transfer to intensive care units reduce mortality for deteriorating ward...
 
Sample size and power calculations
Sample size and power calculationsSample size and power calculations
Sample size and power calculations
 
Projecting ‘time to event’ outcomes in technology assessment: an alternative ...
Projecting ‘time to event’ outcomes in technology assessment: an alternative ...Projecting ‘time to event’ outcomes in technology assessment: an alternative ...
Projecting ‘time to event’ outcomes in technology assessment: an alternative ...
 
Analytical Comparison of Mathematical Modeling in the Diagnostic Expert Systems
Analytical Comparison of Mathematical Modeling in the Diagnostic Expert SystemsAnalytical Comparison of Mathematical Modeling in the Diagnostic Expert Systems
Analytical Comparison of Mathematical Modeling in the Diagnostic Expert Systems
 
2014-10-22 EUGM | WEI | Moving Beyond the Comfort Zone in Practicing Translat...
2014-10-22 EUGM | WEI | Moving Beyond the Comfort Zone in Practicing Translat...2014-10-22 EUGM | WEI | Moving Beyond the Comfort Zone in Practicing Translat...
2014-10-22 EUGM | WEI | Moving Beyond the Comfort Zone in Practicing Translat...
 
Using Value-of-Information methodology to inform the design of clinical trial...
Using Value-of-Information methodology to inform the design of clinical trial...Using Value-of-Information methodology to inform the design of clinical trial...
Using Value-of-Information methodology to inform the design of clinical trial...
 
25_Anderson_Biostatistics_and_Epidemiology.ppt
25_Anderson_Biostatistics_and_Epidemiology.ppt25_Anderson_Biostatistics_and_Epidemiology.ppt
25_Anderson_Biostatistics_and_Epidemiology.ppt
 
2014-10-22 EUGM | ROYCHAUDHURI | Phase I Combination Trials
2014-10-22 EUGM | ROYCHAUDHURI | Phase I Combination Trials2014-10-22 EUGM | ROYCHAUDHURI | Phase I Combination Trials
2014-10-22 EUGM | ROYCHAUDHURI | Phase I Combination Trials
 
A Bayesian Industry Approach to Phase 1 Combination Trials in Oncology
A Bayesian Industry Approach to Phase 1 Combination Trials in OncologyA Bayesian Industry Approach to Phase 1 Combination Trials in Oncology
A Bayesian Industry Approach to Phase 1 Combination Trials in Oncology
 
Sample size &amp; meta analysis
Sample size &amp; meta analysisSample size &amp; meta analysis
Sample size &amp; meta analysis
 
Sample determinants and size
Sample determinants and sizeSample determinants and size
Sample determinants and size
 
Theory and Practice of Integrating Machine Learning and Conventional Statisti...
Theory and Practice of Integrating Machine Learning and Conventional Statisti...Theory and Practice of Integrating Machine Learning and Conventional Statisti...
Theory and Practice of Integrating Machine Learning and Conventional Statisti...
 
Analysis and Interpretation
Analysis and InterpretationAnalysis and Interpretation
Analysis and Interpretation
 
RCT to causal inference.pptx
RCT to causal inference.pptxRCT to causal inference.pptx
RCT to causal inference.pptx
 
PMED Transition Workshop - Dynamic Treatment Regimes via Reward Ignorant Mode...
PMED Transition Workshop - Dynamic Treatment Regimes via Reward Ignorant Mode...PMED Transition Workshop - Dynamic Treatment Regimes via Reward Ignorant Mode...
PMED Transition Workshop - Dynamic Treatment Regimes via Reward Ignorant Mode...
 
Landau dunn 20march2013
Landau dunn 20march2013Landau dunn 20march2013
Landau dunn 20march2013
 
Effective strategies to monitor clinical risks using biostatistics - Pubrica....
Effective strategies to monitor clinical risks using biostatistics - Pubrica....Effective strategies to monitor clinical risks using biostatistics - Pubrica....
Effective strategies to monitor clinical risks using biostatistics - Pubrica....
 
The SPSS-effect on medical research
The SPSS-effect on medical researchThe SPSS-effect on medical research
The SPSS-effect on medical research
 

Mehr von Arthur Charpentier

Mehr von Arthur Charpentier (20)

Family History and Life Insurance
Family History and Life InsuranceFamily History and Life Insurance
Family History and Life Insurance
 
ACT6100 introduction
ACT6100 introductionACT6100 introduction
ACT6100 introduction
 
Family History and Life Insurance (UConn actuarial seminar)
Family History and Life Insurance (UConn actuarial seminar)Family History and Life Insurance (UConn actuarial seminar)
Family History and Life Insurance (UConn actuarial seminar)
 
Control epidemics
Control epidemics Control epidemics
Control epidemics
 
STT5100 Automne 2020, introduction
STT5100 Automne 2020, introductionSTT5100 Automne 2020, introduction
STT5100 Automne 2020, introduction
 
Family History and Life Insurance
Family History and Life InsuranceFamily History and Life Insurance
Family History and Life Insurance
 
Machine Learning in Actuarial Science & Insurance
Machine Learning in Actuarial Science & InsuranceMachine Learning in Actuarial Science & Insurance
Machine Learning in Actuarial Science & Insurance
 
Reinforcement Learning in Economics and Finance
Reinforcement Learning in Economics and FinanceReinforcement Learning in Economics and Finance
Reinforcement Learning in Economics and Finance
 
Optimal Control and COVID-19
Optimal Control and COVID-19Optimal Control and COVID-19
Optimal Control and COVID-19
 
Slides OICA 2020
Slides OICA 2020Slides OICA 2020
Slides OICA 2020
 
Lausanne 2019 #3
Lausanne 2019 #3Lausanne 2019 #3
Lausanne 2019 #3
 
Lausanne 2019 #4
Lausanne 2019 #4Lausanne 2019 #4
Lausanne 2019 #4
 
Lausanne 2019 #2
Lausanne 2019 #2Lausanne 2019 #2
Lausanne 2019 #2
 
Lausanne 2019 #1
Lausanne 2019 #1Lausanne 2019 #1
Lausanne 2019 #1
 
Side 2019 #10
Side 2019 #10Side 2019 #10
Side 2019 #10
 
Side 2019 #11
Side 2019 #11Side 2019 #11
Side 2019 #11
 
Side 2019 #12
Side 2019 #12Side 2019 #12
Side 2019 #12
 
Side 2019 #9
Side 2019 #9Side 2019 #9
Side 2019 #9
 
Side 2019 #8
Side 2019 #8Side 2019 #8
Side 2019 #8
 
Side 2019 #7
Side 2019 #7Side 2019 #7
Side 2019 #7
 

Lg ph d_slides_vfinal

  • 1. Optimal Personalized Treatment Learning Models with Insurance Applications PhD Student: Leo Guelman Advisor: Dr. Montserrat Guill´en PhD in Economics University of Barcelona March 2, 2015 1 / 22
  • 2. Outline 1 Motivation 2 Problem formulation 3 Objectives 4 Challenges 5 Contributions 6 Limitations and future work 2 / 22
  • 3. Motivation Predictive learning has been established as a core strategic capability in many scientific disciplines and industries. Common goal: Predict the value of a response variable using a collection of covariates or “predictors” under static conditions. From Predictive to Causal Modeling • Predictive Modeling has been established as a core strategic capability of many top insurers. • Common goal: to predict a response variable using a collection of attributes under static conditions — i.e., assumes “business as usual” conditions. • Causal Modeling goes one step further: the interest is in estimating/ predicting the response under changing conditions — e.g., induced by alternative actions or “treatments”. 3 X YCovariates Response XCovariates Potential responses Y (1) Y (2) Actions A = 0 A = 1 Causal learning goes one step further: the interest is in estimating/predicting the response under changing conditions – e.g., induced by alternative actions or “treatments”. From Predictive to Causal Modeling • Predictive Modeling has been established as a core strategic capability of many top insurers. • Common goal: to predict a response variable using a collection of attributes under static conditions — i.e., assumes “business as usual” conditions. • Causal Modeling goes one step further: the interest is in estimating/ predicting the response under changing conditions — e.g., induced by alternative actions or “treatments”. 3 X YCovariates Response XCovariates Potential responses Y (1) Y (2) Actions A = 0 A = 1 3 / 22
  • 4. Motivation In the context of causal learning, the main interest has been in identifying the Average Treatment Effect (ATE): ATE = E[Y |A = 1] − E[Y |A = 0]. In many important settings, subjects can show significant heterogeneity in response to actions/treatments – i.e., what works for one subject may not work for another. Here the ATE is less relevant. The objective becomes to select the optimal action or “treatment” for each subject based on individual characteristics. Introduction Current Approaches Personalized Medicine Goal “Providing meaningful improved health outcomes for patients by delivering the right drug at the right dose at the right time.” How Do We Apply Personalized Medicine? Learn individualized treatment rules: tailor treatments based on patient characteristics. Concepts & Tools Symptoms Demographics Disease history Biomarkers Imaging Bioinformatics Pharmacogenomics Concepts & Tools Symptoms Demographics Disease history Biomarkers Imaging Bioinformatics Pharmacogenomics When Do We Apply Personalized Medicine? Single-Decision Setup. Multi-Decision Setup. Optimal defined as the treatment that maximizes the probability of a desirable outcome. We call the task of learning the optimal personalized treatment personalized treatment learning (PTL). 4 / 22
  • 5. Problem Formulation Assume a randomized experiment – i.e., subjects are randomly assigned to two treatments, denoted by A ∈ {0, 1}. Let Y (a) ∈ {0, 1} denote a binary potential response of a subject if assigned to treatment A = a, a = {0, 1}. So the observed response is Y = AY (1) + (1 − A)Y (0). Subjects are characterized by a p-dimensional vector of baseline predictors X = (X1, . . . , Xp) . Data consist of L i.i.d. realizations of (Y , A, X), {(Y , A , X ), = 1, . . . , L}. 5 / 22
  • 6. Problem Formulation At the most granular level, the personalized treatment effect (PTE) is a comparison between Y (1) and Y (0) on the same subject. Usually, Y (1) − Y (0) ∀ = {1, . . . , L}. But this quantity is unobserved... In practice, the best we can do is to estimate the PTE by conditioning on subjects with profile X = x. Thus, we define the PTE by τ(x) = E[Y (1) − Y (0)|X = x] = E[Y |X = x, A = 1] − E[Y |X = x, A = 0]. 6 / 22
  • 7. Problem Formulation A personalized treatment rule H is a map from the space of baseline covariates X to the space of treatments A, H(X) : Rp → {0, 1}. An optimal treatment rule is one that maximizes the expected outcome, E[Y (H(X))], if the personalized treatment rule is implemented for the whole population. Since Y is binary, this expectation has a probabilistic interpretation. That is, E[Y (H(X))] = P Y (H(X)) = 1 and thus τ(x) ∈ [−1, 1]. Assuming all treatments cost the same, the optimal personalized treatment rule H∗ = argmaxH E[Y (H(X))] for a subject with covariates X = x is given by H∗ = 1 if τ(x) > 0 0 otherwise. 7 / 22
  • 8. The Simplest Approach to PTE Estimation 1 Estimate E[Y |X, A = 1] using the treated subjects only. 2 Estimate E[Y |X, A = 0] using the control subjects only. 3 An estimate of the PTE for a subject with predictors X = x is ˆτ(x) = ( ˆY |X = x , A = 1) − ( ˆY |X = x , A = 0). Pros: Any conventional statistical or algorithmic binary classification method may serve to fit the models. Cons: Method aims to predict the wrong target: it emphasizes the prediction accuracy on the response under each treatment, not the accuracy in estimating the change in the response caused by the treatment. Relevant predictors for Y under each treatment are usually different from relevant PTE predictors. As a result, it tends to perform poorly in practice. 8 / 22
  • 9. Objectives Formalize personalized treatment learning (PTL) as a new branch of statistical learning. Create the first comprehensive systematic review of the existing PTL methods (Tian and Tibshirani, 2014; Radcliffe and Surry, 2011; Ja´skowski and Jaroszewicz, 2012; Su et al., 2009; Qian and Murphy, 2011; Zhao et al., 2012; Rubin and Waterman, 2006; Larsen, 2009; Imai and Ratkovic, 2013, and others). Build improved statistical/algorithmic methods for estimating, selecting and assessing PTL models. Introduce PTL models to insurance applications. Build open source software implementing our proposed methods for fitting PTL models, as well as the existing ones, and make it freely available for academia/industry. 9 / 22
  • 10. Key Challenges The fundamental problem of PTL models: The quantity we are trying to predict (i.e., the optimal personalized treatment) is unknown on a given training data set. Size of main effects relative to treatment heterogeneity effects: The magnitude of the variability in the response due to the treatment heterogeneity effects is usually much smaller than the variability due to the main effects. Overfitting: The risk of overfitting increases markedly in PTL models compared to conventional predictive learning problems. Model selection and assessment: Methods for variable selection and model selection/assessment used in conventional predictive learning problems need to be redefined in the context of PTL models. 10 / 22
  • 11. Contributions Introduced and formalized the concept of personalized treatment learning (PTL) within a causal inference framework, and described its relevance to a wide variety of fields ranging from economics to medicine (Ch. 1-2). Provided the first comprehensive description of the existing PTL methods (Ch. 3) and proposed two novel methods – namely, uplift random forests (Ch. 4) and causal conditional inference trees (Ch. 5). Our proposal outperforms the existing methods in an extensive numerical simulation study (Ch. 6). PTL models require not only developing new estimation methods, but also new methods for assessing model performance. We formalized the concept of the Qini curve and the Qini coefficient, and discussed general useful methods for model assessment and selection for PTL models (Ch. 7). 11 / 22
  • 12. Contributions We described the relevance of PTL models to insurance marketing, and illustrated two applications to optimize client retention and cross-selling using experimental data from a large Canadian insurer (Ch. 8). We presented a novel approach to measuring price-elasticity and economic price optimization in non-life insurance based on PTL modeling principles in the context of observational data (Ch. 9). Selecting the optimal personalized treatment in insurance also requires consideration of the expected losses under treatment alternatives. We described an unprecedented application of gradient boosting models to estimate loss cost in non-life insurance, with key advantages over the conventional generalized linear model approach (Ch. 10). We implemented most of the statistical methods and algorithms described in this thesis in a package named uplift (Guelman, 2014), which is now freely available from the CRAN (Comprehensive R Archive Network) repository under the R statistical computing environment (Ch. 11). 12 / 22
  • 13. PTL with Experimental Data An Application to Insurance Cross-Sell Optimization Cross-sell rates by group Treatment Control Purchased home policy = N 30,184 3,322 Purchased home policy = Y 789 75 Cross-sell rate 2.55% 2.21% The average treatment effect (ATE) is 0.34% (2.55% − 2.21%) which is NOT statistically significant (P value = 0.23). Cross-sell rate by PTL model decile Deciles 0.03 0.06 q q q q q q q q q q q q q q q q q q q q Profitable targets Not profitable targets 0 2 4 6 8 10 12 1 2 3 4 5 6 7 8 9 10 Decile Cross−sellrate(%) Group q qTreatment Control Prototype causal conditional inference tree 0.34% 0.05% prodCnt ≤ 1 0.65% 1.22% adjBranch 0.38% 0.67% 2.52% age ≤ 45 -1.2% 0.32% xdate ≤ 2 -1.6% age ≤ 42 -0.2% The tree-based procedure identifies a subgroup of clients with significant positive impact from the cross-sell activity (PTE = 2.52%). 13 / 22
  • 14. Causal Conditional Inference Tree - Pseudocode Algorithm 1 Causal conditional inference tree 1: for each terminal node do 2: Test the global null hypothesis H0 of no interaction effect between the treatment A and any of the p predictors at a level of significance α based on a permutation test (Strasser and Weber, 1999) 3: if the null hypothesis H0 cannot be rejected then 4: Stop 5: else 6: Select the j∗ th predictor Xj∗ with the strongest interaction effect (i.e., the one with the smallest adjusted P value) 7: Choose a partition Ω∗ of the covariate Xj∗ in two disjoint sets M ⊂ Xj∗ and Xj∗ M based on the G2 (Ω) split criterion 8: end if 9: end for G2 (Ω) = (L − 4){ Left Node ( ¯YnL (1) − ¯YnL (0)) − Right Node ( ¯YnR (1) − ¯YnR (0))}2 ˆσ2{1/LnL (1) + 1/LnL (0) + 1/LnR (1) + 1/LnR (0)} 14 / 22
  • 15. Numerical simulations – Performance comparison “Strong” treatment heterogeneity effects Simulation scenarios are obtained by varying: (i) the strength of the main effects relative to the treatment heterogeneity effects, (ii) the correlation among the covariates, (iii) the magnitude of the random noise. qqqqqq q q qqqq qqq qqq q q qqqq q qqqqq qqqqqqqq qqqq q qqqqq qqqqqqqq q q q q q q q q q q q q q q q q q q q q q q q q q q q q q qq q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q qq q qq q q q qq q qq q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q q qq q qq q q q q q q q q q q q q Scenario 1 Scenario 2 Scenario 3 Scenario 4 0.00 0.25 0.50 0.75 0.00 0.25 0.50 0.75 0.00 0.25 0.50 0.75 −0.3 0.0 0.3 0.6 l2svm ccif upliftRF dsm dsm−RF mom−RF mom mcm cknn mcm−RF int int−RF ccif upliftRF dsm−RF mom−RF cknn mcm−RF int−RF l2svm mom mcm dsm int ccif l2svm upliftRF mom−RF dsm−RF mom mcm dsm mcm−RF cknn int−RF int ccif upliftRF dsm−RF mom−RF mcm−RF cknn int−RF mom mcm l2svm dsm int Method Spearman'srankcorrelationcoefficient 15 / 22
  • 16. Numerical simulations – Performance comparison “Weak” treatment heterogeneity effects q q q q q qq q q q q q q q q q q q q q q q q q q q q q qq q q q qq q qq q qq q qq qq q q q q q q q q q q q q q qq q q q q q qq q q q q q q qq q q q q q q q q q q q q q q q q q q qq q q q q q q q q q q q qq q q q q q q q q q q q qq q q q qqq q q q q q q q q q q qq q q q qqq q q q q q q q q q q q q q q q qq q q q q qq q q q q q q q q q q q q Scenario 5 Scenario 6 Scenario 7 Scenario 8 0.00 0.25 0.50 0.75 −0.5 0.0 0.5 0.00 0.25 0.50 0.75 −0.25 0.00 0.25 0.50 dsm ccif upliftRF l2svm dsm−RF mom−RF int cknn mcm−RF int−RF mom mcm ccif upliftRF dsm−RF dsm mom−RF cknn mcm−RF int−RF l2svm mom mcm int dsm ccif upliftRF dsm−RF mom−RF mcm−RF cknn l2svm int−RF int mom mcm ccif upliftRF dsm−RF mom−RF mcm−RF cknn dsm int−RF l2svm mom mcm int Method Spearman'srankcorrelationcoefficient 16 / 22
  • 17. PTL with Observational Data An application to Auto Insurance Economic Price Optimization Background Objective: Determine the policyholder-level premium (playing the role of the treatment) that maximizes the expected profitability of an existing insurance portfolio, subject to a fixed overall retention rate. Requires estimating the expected client retention outcome under alternative insurance rates (price elasticity), and loss cost. Clients were historically exposed to rating actions based on a non-random assignment mechanism, which requires designing an observational study. Maximize an expected profit function Max Z a∀ ∀a ∀ ∀a Z a P (1 + RCa)(1 − ˆLR a)(1 − ˆˆr a) subject to a retention constraint ∀a Z a = 1 ∀ Z a ∈ {0, 1} ∀ a Z a ˆˆr a/L ≤ α. q Current state Efficie ntfrontie r A B C 0 10 20 30 0.90 0.92 0.94 0.96 Retention rate (1 − α) Expectedprofit(%) 17 / 22
  • 18. uplift Package Highlights First R package implementing PTL models Exploratory Data Analysis (EDA) tools customized for PTL models Check balance of covariates (checkBalance) Univariate uplift analysis (explore) Preliminary variable screening (niv) Estimating personalized treatment effects Causal conditional inference forests (ccif) Uplift random forests (upliftRF) Modified covariate method (tian_transf) Modified outcome method (rvtu) Uplift k-nearest neighbor (upliftKNN) Performance assessment for PTL models Uplift by decile (performance) Qini curve and Qini-coefficient (qini) Other functionality Profiling PTL models (modelProfile) Monte-Carlo simulations (sim_pte) 18 / 22
  • 19. Fitting a CCIF using uplift ccif implements recursive partitioning in a causal conditional inference framework. fit <- ccif(formula = Y ~ trt(A) + X1 + X2 + X3, data = mydata, ntree = 1000, split_method = "Int", distribution = approximate (B=999), pvalue = 0.05, verbose = TRUE) Table: Some ccif options ccif argument Description mtry Number of variables to be tested in each node ntree Number of trees in the forest split_method Split criteria: "KL", "ED", "Int" or "L1" interaction.depth The maximum depth of variable interactions pvalue Maximum acceptable p-value required to make a split bonferroni Apply Bonferroni adjustment to pvalue minsplit Minimum number of obs. for a split to be attempted ... Additional args. passed to coin::independence_test. 19 / 22
  • 20. Manuscripts Linked to Thesis [1] Guelman, L. (2014). uplift: Uplift modeling. R package version 0.3.5. [2] Guelman, L. and Guill´en, M. (2014). A causal inference approach to measure price elasticity in automobile insurance. Expert Systems with Applications, 41(2):387–396. [3] Guelman, L., Guill´en, M. and P´erez-Mar´ın, A. M. (2014). A survey of personalized treatment models for pricing strategies in insurance. Insurance: Mathematics and Economics, 58:68–76. [4] Guelman, L., Guill´en, M. and P´erez-Mar´ın, A. M. (2014). Uplift random forests. Cybernetics & Systems. Accepted. [5] Guelman, L., Guill´en, M. and P´erez-Mar´ın, A. M. (2014). A decision support framework to implement optimal personalized marketing interventions. Decision Support Systems, 72: 24–32. [6] Guelman, L. (2012). Gradient boosting trees for auto insurance loss cost modeling and prediction. Expert Systems with Applications, 39(3):3659–3667. [7] Guelman, L., Guill´en, M. and P´erez-Mar´ın, A. M. (2012). Random forests for uplift modeling: An insurance customer retention case. In Engemann, K. J., Lafuente, A. M. G., and Merig´o, J. M., editors, Modeling and Simulation in Engineering, Economics and Management, pages 123–133. Springer Berlin Heidelberg, New York, NY. 20 / 22
  • 21. Talks Linked to Thesis [1] Guill´en, M. and Guelman, L. (2014). “New trends in predictive modelling - the uplift models success story”. R in Insurance Conference, London, UK. (July 14, 2014). [2] Guelman, L. and Guill´en, M. (2014). “Actionable predictive learning for insurance profit maximization”. Casualty Actuarial Society, Ratemaking and Product Management Seminar, Washington, D.C., USA (April 1, 2014). [3] Guelman, L. (2013). “An introduction to causal learning with applications to price elasticity modeling in Casualty insurance”. University of Barcelona, UB Economics Seminars, Barcelona, Spain (November 28, 2013). [4] Guelman, L., Guill´en, M. and P´erez-Mar´ın, A.M. (2013). “Evaluating customer loyalty with advanced uplift models”. APRIA, Annual Conference, New York, USA (July 28-31, 2013). [5] Guill´en, M., Guelman, L., M. and P´erez-Mar´ın, A.M. (2013). “Customer retention and price elasticity. Are motor insurance policies homogeneous with respect to loyalty?”. 2013 Astin colloquium, The Hague, Netherlands (May 21-24, 2013). [6] Guelman, L. and Lee, S. (2013). “Balancing robust statistics - gradient boosting”. Casualty Actuarial Society, Ratemaking and Product Management Seminar, Los Angeles, USA (March 12-13, 2013). [7] Guelman, L., Guill´en, M. and P´erez-Mar´ın, A.M. (2012). “Random forests for uplift modeling: an insurance customer retention case”. Association of Modeling and Simulation in Enterprise (AMSE) - International Conference on Modeling and Simulation, New York, USA (May 30-June 1, 2012). – Outstanding Scholarly Research Contribution Award, AMSE. [8] Guelman, L. and Lee, S. (2012). “Balancing robust statistics and data mining in ratemaking: gradient boosting modeling”. Casualty Actuarial Society, Ratemaking and Product Management Seminar, Philadelphia, USA (March 20-21, 2012). 21 / 22
  • 22. Limitations and Future Work 1 Extensions to multi-category and continuous treatment settings. 2 Extensions to continuous uncensored and survival responses. 3 Extensions to dynamic treatment regimes: treatment type may be repeatedly adjusted according to an ongoing individual response. 4 Absolute vs. relative treatment effects – in some settings, defining the treatment effect in terms of the ratio of the expected responses under alternative treatment conditions, instead of the difference between the expected responses may be more appropriate. 22 / 22