Making artificial neural networks
more interpretable: a case study of
switching costs
Introduction
ANNs, recently, received more and more attention in marketing facet as a powerful statistical technique for market prediction. Many scholars today adopt ANNs instead of traditional statistical methods to solve customer churn prediction problems (e.g., Tsai, Chih-Fong, and Yu-Hsin Lu, 2009; Sharma, Anuj, Dr. Panigrahi, and Prabin Kumar, 2013).
“black box” problem: this technique provides little explanatory insight into the relative influence of independent variables in the predicting process.
There traditional methods for understanding the mechanics of ANNs: Garson algorithm Neural networks diagram sensitivity analysis
Empirical example
Throughout this paper, our research target is switching costs.
Dataset and variable
To test these hypotheses mentioned above, customer loyalty data from Bank of
America will be analyzed. The data is provided by Bank of America, which is a part of
"big four" banks. Take the reputation and high-quality performance of Bank of America
into consideration. The data can be supposed to be trustworthy, which is an essential
requirement for data analysis (Leeflang et al., 2015). The data collection process is
completed through surveys. The dataset includes individual-level data
.Before training the network, variables need to be transformed. For the continuous
dependent variable, they should be converted into variables with intervals from zero to
one so that the sigmoid function can be used. This process can be achieved by using
this formula:
For independent variable, conversion processing is also necessary because we
need to ensure that a similar percentage change in weighted sum of input leads
to similar change in the unit output (Olden, 2001). This process can be achieved
by using this formula:
Variable Definition measurements Pos SC To what extent do you agree with the statement? I am not changing
my incumbent bank since i feel uncertain about whether other suppliers can give the same service as this one.
Score of clients on this question from 0 to 5.( higher scores mean they agree more with this statement)
Neg SC To what extent do you agree with the statement? I feel locked into this supplier.
Score of clients on this question from 0 to 5.( higher scores mean they agree more with this statement)
Age the actual age of customer Younger than 20 1
21-30 2 31-40 3 41-50 4 51-60 5 61-70 6 Over 70 7
Gender The gender of clients Male 1
Female 2 Satisfaction What is your overall satisfaction with the service provider Score of clients on this variable from 0 to 10. Attitudinal loyalty To what extent do you agree with the statement? I will say positive
things about my current suppliers and recommend my current suppliers to my friends.
Score of clients on this variable from 0 to 10.
Behavioral loyalty Whether clients switch to another service provider at the end of the wave
Methodology
Garson algorithm
The variable Satisfaction*positive SC show the strongest relationship with predicted customer behavioral loyalty.
Neural network diagram
The thickness of the lines represents the
magnitude of the connection weight. (black
line means positive and gray lines mean
negative)
Disadvantages:
1
Additional hidden neuron would only
make the interpretation more difficult
2
A subjective choice must be made
regarding the magnitude at which
Sensitivity analysis
Understand the spectrum of input
variable contributions in neural
networks
the influence of positive switching costs
on behavioral loyalty show left-skewed
curve- independent variable has a
Randomization approach
Record initial connections weights used in constructing this networks
Calculate the product of input-hidden and hidden-output connection weights Randomly permute the original response variable
Construct a neural network using y-random( repeat this steps)
Results
To verify that the “coefficients” obtained by ANNs are credible, the outcomes obtained by ANNs and regression method are then compared. We compared the results obtained by artificial neural networks with the results obtained by linear regression model for predicting customer attitudinal loyalty (continuous dependent variable) and compare the results of neural networks with logistic regression model for predicting c u s t o m e r c h u r n ( b i n a r y dependent variable).
Hypothesis ANNs Regressi on Customer satisfaction positively affects customer loyalty Support Support
Positive switching costs positively affect attitudinal loyalty Support Support
Negative switching costs negatively affect attitudinal loyalty Support Support
Switching costs positively affect behavioral loyalty Support Support
The positive relationship between satisfaction and attitudinal loyalty will be stronger when clients perceive positive
switching costs
Support Support
The positive relationship between satisfaction and behavioral loyalty will be stronger when clients perceive positive
switching costs
Support Support
The positive relationship between satisfaction and attitudinal loyalty will be weaker when clients perceive negative
switching costs
Support Support
The positive relationship between satisfaction and behavioral loyalty will be weaker when clients perceive negative
switching costs
Rejected Rejected
The positive relationship between satisfaction and attitudinal loyalty will be stronger for senior citizens than for young
clients
Rejected Rejected
The positive relationship between satisfaction and behavioral loyalty will be stronger for senior citizens than for young
clients
Support( Neg SC)
Conclusion
The ANNs technique, combined explanatory insight with powerful predictive ability, can be considered as a promising method for understanding and predicting market phenomena. The ANNs technique can provide better decision support for managers.
Furthermore, several managerial implications generated from the empirical example. In line with the existing marketing literature (Cronin & Taylor, 1992; Fornell, 1992; Anderson & Sullivan, 1990; Boulding, Kalra, Staeling, & Zeithaml, 1993), this study revealed that customer satisfaction is positively related to customer loyalty.
Although, to some extent, high negative switching costs can prevents customers from leaving, it will reduce customer attitudinal loyalty, which means that clients are less likely to make positive recommendations. Thus, high negative switching costs may cause negative, long-term consequences for firms (Schurr, Dwyer, & Oh, 1987).
Limitations and further research
First of all, based on randomization approach, readers can understand how the explanatory variables affect the response variable in the ANNs model. However, the coefficients in the linear regression model can be interpreted directly, and the coefficients in the logistic regression can be interpreted by calculating odds ratio and marginal effect. Hence, how to interpret the connection weights in ANNs models deserve our further attention.
Furthermore, the dataset used in this study was based on American consumer. Hence, whether the results of this study can be generalized is debatable.
