Data Mining For CRM: One Way to reach the goals

Following the lecture by Dr. Ilona Jagielska, this week reading materials reveal several data mining techniques, such as neural network, decision tree and CART methodology, and association rules. The three reading materials illustrate how those techniques work, the strengths, weaknesses, and also describe a study case in predicting whether a certain visa cardholder is a good or bad customer.

After reading all those materials, I think there are several important issues to be considered:

First is about the techniques used for mining the customer data. In my opinion, there is no technique that can be claimed as the best method for all problem domains. All techniques have their own characteristic, strength and weaknesses. For that reason, it is important to choose the proper technique and then build a model. In order to do that, the problem should be addressed properly. A model has the same nature as technique; it might only work best on a certain problem. The best model can only be defined according to certain cost or risk acceptable by ones who implement it.

Second, besides technique and model, one thing that is crucial is data. There is a jargon about it, “garbage in garbage out”. No matter how good the model is, if the quality of data is poor, it would not give the expected result (but data with the good quality not merely guarantee the good result. There is a possibility that the model is not suitable). That’s one reason why we should prepare the data.

Nevertheless, those techniques are helping companies in many things related to building and retaining a good relationship with their customers. They help companies to get to know their customers, to predict what their new customers would be like, to scale up their sales by cross selling and up selling since they know the customers now, etc. Companies can also apply the data mining technique to build a tool that would support customers. For example, related to the problem of choice overload, one data mining technique such as clustering analysis can be used to group the customers based on their similarity and then suggesting the choice based on customers on the same cluster. It can be both beneficial to companies and customers. Then it would bring companies a step closer to the goal………

Choice Overload

(Paper by Sheena S. Iyengar and Mark R. Lepper: When Choice is Demotivating: Can One Desire Too Much of a Good Thing?, Journal of Personality and Social Psychology, 2000, Vol. 79, No. 6, pp. 995-1006)

Continuing the discussion whether “choice overload” makes people happy or creates people aversions to make decision, this paper supports Schwartz position as seen in his video on the last week’s lecture. The authors wanted to investigate more on the widespread perception in economic theories and marketing practices that the more choices, the better. They had performed three experimental studies which showed a contrary to the previous presumption: “although having more choices might appear desirable, it may sometimes have detrimental consequences for human motivation”.

There are several important findings from this paper:

• People with “extensive-choice contexts” relish the process of “choice-making” more than the counterpart group. It is probably because they have more options to choose that lead them to the idea that they should be able to make a better (if not the best) decision, so that they feel more responsible for the decision they make. This situation makes them frustrated and dissatisfied with their choices. Furthermore the authors stated that it is not the matter of people’s satisfaction or dissatisfaction of their choices, but they are loaded with the expectation that they should be able to differentiate good and bad choices, and they feel uncertain about it.

Perhaps, not only the burden to make a good decision out of so many options, but also the time pressure.

• It is found that there is no empirical support for the theory that choosers in extensive-choice contexts are more likely to use a satisfying heuristic, whereas choosers in a limited-choice context are more likely to use an optimizing heuristic.

I think, in the relation to the methods people used to make decisions, we should also see the domain of the decision, the risk of the decision, and probably the habit in making decision.

• The substantial discouraging effects can be even worse in a ‘serious’ choice-making situation where there are costs related to making the “wrong choice” or the it consumes times and needs effort to be able to evaluate options substantially.

I agree with this opinion. If I have to make a decision in a trivial situation where the risk is small or bearable, I would have more courage to do it. I perceive it as a learning stage where I can gain knowledge from the process, and then used the knowledge for future references. The same condition will not happen if the risk is unacceptable. I think it is natural since human tend to have risk-aversion behaviour.

• If people see that the choice-making process needs competent information, they would likely choose not to make a decision. They tend to hand over the task to someone else who is more capable in the field or an expert. This opinion is strengthened by Schwartz’s belief (1994) – as quoted in this paper – that is “as the freedom of individuals expands, so too does their dependence on institutions and other people”.

I also think this result is a normal thing to happen. It is common that people have someone to help them in making decision by giving opinions – general or expert opinions. As I wrote in my last blog about recommender system, it tries to accommodate this social behaviour into a computer system. I don’t suggest that the problem would instantly disappear. There are always good and bad thing about a particular issue. In my opinion, the good thing about this system is that it helps people in making choices in the face of abundant options by seeing other people opinions which may be based on their experience or expertise. The bad news is whether we trust or value their opinions. L

• Besides the preference-matching contexts, in which people wish to come across some particular product or service they already know themselves to prefer, there is another context where people would become contented with extensive choices – although it is still a paradox. That is when people already have expertise built from previous experiences; they tend to see extensive choices as limited in number.

I am used to observe my mother when she goes shopping in the supermarket. She doesn’t seem to have trouble in deciding which items should be bought nor the location of the items. Even tough, there are many brands that produce a certain item, she manages to choose one. And if I pay attention on her choice over time, she always chooses the same brands. When I ask her why she chooses that brand, she says that it is the best - according to her. Then I ask her again whether she wants to try other brands, she replies that she doesn’t have to. So besides the fact that she has the experience of the product and the location of the shelves, there is also another thing: a brand loyalty.

Although it is revealed now that the availability of extensive choices proves unexpectedly demotivating in the end, I think this condition is not going to stop. Proctor & Gamble may reduce the number of versions of its popular Head and Shoulders shampoo from 26 to 15, but there are still many competitors who produce the same items. Likely, we are – the customers – still facing this problem (as an example given by the authors on the part of their paper). Well, what do you think? Any comments are welcomed……