Sunday, February 23, 2014

Target markets and ANN

Once we, marketers, have determined our business products or services, we must accurately identify our target markets. The target market is the actual customer group, or audience, in which our business will attempt to sell its products and services. Target marketing tailors a marketing mix for one or more segments identified by market segmentation and usually contrasts with mass marketing, depending on the industry, the competition, the marketing budget of the business, NGO vs non-NGO, etcetera. Many techniques have been used in order to select the target markets, such as statistical regression (Bult&Wansbeek, 1995), neural computing (Zahavi&Levin, 1997) and fuzzy clustering (Setnes&Kaymak, 2001). Direct marketing is, off course, a well-known type of marketing, used by businesses, in order to target, call to action and increase profits. A well-executed direct advertising campaign can have a satisfying Return On Investment, since many potential customers responded to a clear call-to-action. The growing interest in direct marketing techniques has made it an important application field for marketers and data mining professionals.


Artificial neural networks (ANN) are "computational models inspired by animals' central nervous systems that are capable of machine learning and pattern recognition". They are presented as systems of interconnected neurons that can compute values from inputs by feeding information through the network. 
Commonly, a class of statistical models may be called "neural" if they
  1. consist of sets of adaptive weights, i.e. numerical parameters that are tuned by a learning algorithm, and
  2. are capable of approximating non-linear functions of their inputs.
The adaptive weights are conceptually connection strengths between neurons, which are activated during training and prediction.
As aforementioned, marketers should divide the market into segments. A product offer would then be made to those people who are considered to be in the market segment for which the product was meant. Automation segmentation techniques have been used to divide the customers into a number of segments, like CHi-squared Automatic Interaction Detection (CHAID)CHAID is a type of decision tree technique, that is used for prediction as well as classification and detection of interaction between marketing variables. In practice, CHAID is often used in the context of direct marketing to select groups of consumers and predict how their responses to some variables affect other variables.
When a segmentation method such as CHAID is used to determine target segments which are more likely to respond to marketing actions, the data set is split into disjoint groups and the groups that are considered to be most likely to respond are targeted through a marketing action, e.g. mailed preferentially. Neural networks, however, do not segment data into disjoint groups. That means, a different approach is needed to develop target selection models by using neural networks. Since target selection models try to differentiate responders from non-responders, marketers could consider formulating the problem as a classification problem and develop a network that classifies each input pattern as a responder or non-responder. However, the classes are not well separated in target selection problems.  
Furthermore, the miss-classification costs  are asymmetric. Miss-classifying a possible responder as a non-responder and not targeting that individual is more costly to the direct marketing company than miss-classifying a non-responder as a responder. Therefore, another method than pure classification should be used. One solution could be to define a measure for the "likelihood" of an individual to respond (call-to-action) via the marketing action, e.g. mailing. The individuals are then ordered according to this measure, and only the ones that score above a given threshold θj are targeted (target scoring). 
Artificial neural network models for target selection fall into this category. The output of the neural network is then a measure of likelihood of response (Potharst et al., 2001). Now, the goal of determining the neural network would be to determine a correct set of network parameters (weights) such that a good indication of the likelihood of response of the supporters is obtained, given the inputs to the network. Naturally, these inputs must convey information about the characteristics of the supporters, including demographic, geographic, or even psychographic and behavioral variables.
ANN configuration and analysis
In target selection problems we form the model of the likelihood of response at a single point in time, given various supporter characteristics and/or their past behavior. In real life, feed-forward neural networks are sufficient for target selection problems. The nonlinear activation function of the neurons also has an influence on the final neural network model for a given network structure and the number of neurons. The logistic sigmoid function:
is often used since the neural network output is expected to lie in the range [0,1] (likelihood of response). Thus, the neural network model can be analyzed as a generalized nonlinear regression model with the likelihood [0,1] of response to our marketing action as an output .
We may visualize our target selection model through a hit probability chart. 
Potharst et al. 2001
A hit probability chart exposes what percentage of a selected population may respond to our marketing action. The x-axis shows a percentage of the total group selected for targeting and the y-axis shows what percentage of that group is a responder to our call-to-action. The hit probability chart for a successful model starts with high values of hit probability. As the size of the selected group increases, the percentage of responders within the selected group will decrease until the hit percentage is equal to the percentage of responders within the total marketing action eg. mailing considered in the campaign.
In real life, after data preparation and data set selection, marketers may use IBM SPSS Neural Networks as a modern modelling tool.  

With SPSS Neural Networks, marketers may select either the Multilayer Perceptron (MLP) or Radial Basis Function (RBF) procedure. Both of these are map relationship techniques implied by the data. Both use feedforward architectures, meaning that data moves in only one direction, from the input nodes through the hidden layer of nodes to the output nodes. Prior research has indicated that neural network models may perform better than the CHAID model, while they perform on an equal level with the logistic regression models we aforementioned.
In general, ANN for Marketing can be viewed as a modelling tool that helps marketers to take decisions. ANN can recognize patterns, pick up key information that are not easily identifiable and develop relationships among them. Marketers are expected to fully take advantage of the ANN modeling in order to solve their target selection problem faster and more efficiently.

Saturday, February 15, 2014

Capitalistic materialism and happiness; an holistic approach

“The world says: "You have needs -- satisfy them. You have as much right as the rich and the mighty. Don't hesitate to satisfy your needs; indeed, expand your needs and demand more." This is the worldly doctrine of today. And they believe that this is freedom. The result for the rich is isolation and suicide, for the poor, envy and murder.” 

Fyodor DostoyevskyThe Brothers Karamazov: A Novel in Four Parts With Epilogue

Materialism, the forgotten child of monist ontology. The nature and definition of matter have occasioned much philosophical debate, even from ancient times.  

In ancient Greece, philosophers like Thales, Epicurus and Democritus prefigure later materialists; their theory mainly suggests that all that exists is matter and void, and all phenomena result from different motions of base material particles. During the Middle Ages, Pierre Gassendi represented the materialist tradition, as opposed to René Descartes' theory, according to which natural sciences may be explained with dualist foundations. In the 19th century, Karl Marx extended the concept of materialism to elaborate an alternative conception of history based on the empirical world of human activity, thus establishing the dialectical materialism. But, how is materialism perceived today, in a global playground? There are three ways of attaining happiness, according to Sartre: by having, doing and being. Over the next decades, sociologists and psychologists began to train their sights on the study of gaining external happiness, Sartre's concepts of having and doing had become the psychosocial ideas of materialism. Materialism may be nowadays described as a way of thinking that gives much importance to material possessions rather than intellectual things. That means, materialism is nowadays considered as a sociological tool in developing an understanding of modern capitalistic culture via referring to the desire of material needs, rather than a philosophical argument or a conception of history. But, would materialism and consumerism be accompanied by greater well-being?

Materialism and wealth are many times perceived as related terms. Actually, wealth may be an elusive as well as an extrinsic goal. Many people chase money; few achieve great wealth. Are rich people happier than poor people? In order to answer these fundamental questions, we will may try to explain materialism as a construct. Materialism, as the devotion to acquisition and possession, may be described as a defining characteristic of our age which has been criticized on religious, philosophical, and social grounds. Materialism as an individual variable has been effectively defined by Richins & Dawson (1992). Their scale measures three components of materialism: acquisition as the central goal in human life, including acquisition as the path to happiness and success in life as defined by possessions. High scorers, compared to low scorers, are in general less satisfied with life, want more money, are less likely to share, and seem to suffer from poor adjustment, much like those who are preoccupied with money. High scorers also value financial security, while low scorers give priority to interpersonal relationships and a sense of personal accomplishment. On the same basis, researchers have conceptualized materialism as the consumption style that results when consumers perceive that value inheres in consumption rather than in experiences and people. 

Well-being may be easily correlated with materialism. Well-being may assessed in terms of science as subjective well-being or SWB (Diener 1984), which encompasses the cognitive appraisal of one’s life as satisfactory. Given strong motives for acquiring money, with its promises of freedom, power, and even love, the actual impact of income on life satisfaction within a society seems unaccountably meager. Academic researchers such as Ahuvia and Friedman change the focus from objective wealth to subjective appraisals. For instance, they report a strong relationship between perception of income and subjective well-being. SWB increases as income increases from below average to above average within one’s home community. The subjective approach also helps us understand why financial goals seem to have an insatiable quality: as people acquire more, they seem to want even more, with dissatisfaction persisting along with apparent success. However modest the relationship between income and SWB, once the poverty threshold is passed, it is still a positive relationship. Money matter for well-being, but that money’s influence is mediated and limited by personality buffers (self-esteem, control and optimism). Individuals’ happiness level is more or less preset, going up a bit when we experience self-esteem, control, and optimism, and going down a bit when those qualities falter. Increased income has a positive effect all aforementioned buffers, and therefore the happiness level moves toward the upper end of the range. 

Materialism and SWB may be highly correlated. Initial evidence of the relationship between materialism and well-being was provided by Belk (1985), who associated materialism with such undesirable traits as non-generosity, envy, and greed and found that these traits have a significant negative correlation with both happiness and overall life satisfaction. Subsequent studies using Belk’s scale have found that materialism is negatively correlated with satisfaction with personal finances and career accomplishments and positively correlated with social anxiety, dependency or even self-criticism.

Well-being predictors may be categorized as genetically determined, circumstantial, or intentional positive behaviors and cognitions. Genetic factors, such as genes and personality traits, account for a large percentage of the variation in between-subject well-being, but they are very difficult, if not impossible, to alter. Circumstantial factors such as income, marital status, and employment account for only a smaller percentage of the variance in well-being levels due to the phenomenon of hedonic adaptation. Thus, positive behaviors offer the best potential route to longitudinal increases in well-being since people have considerable control over these activities. Hedonic products are those “whose consumption is primarily characterized by an affective and sensory experience of aesthetic or sensual pleasure, fantasy, and fun” (Dhar & Wertenbroch 2000). We may define hedonic consumption as a consumer's regular expenditures on specific hedonic products or services. It reflects how much of the hedonic experience consumers enjoy regularly. Hedonic product usage is positively associated with consumers' well-being, and experiential purchases may even make people happier than material purchases. However, as the human race grows richer, the problems associated with hedonic consumption, may result in negative effects on consumers' well-being. In general, consumers tend to maximize their satisfaction through economic activities that consist of the exchange and consumption of goods. Consumers may enhance their well-being by recognizing their own needs and satisfying them by engaging in consumption activity and attaining consumer products. Consumption, especially of hedonic consumer products, is highly important for happiness among modern consumers, which leads highly developed economies to tend to exhibit an increased emphasis on hedonic consumption. Thus, consumption appears necessary for overall and subjective well-being in modern societies. The possession and consumption of more hedonic products represents the cultural aspiration towards personal happiness and well-being.

We should also refer to materialism and strategic consumption as a means for social affiliation. Humans have an innate need to be a part of social relationships because a social group afforded survival and safety throughout evolutionary history. It is not surprising that people have developed psychological mechanisms that help them ensure that their need to belong is being met. More specifically, exclusion heightens people’s tendency to form new social connections. Excluded people are eager to work and play with others, and they tend to view new sources of social connection in a positive, optimistic light. Consumers use the symbolic ways of consumption as a way to communicate information about themselves to others. Such communication attempts are particularly prevalent when people want to make a good impression on others or facilitate social interaction. Thus, self-presentational motives guide consumption decisions, and people may use consumption as a way to communicate specific information about themselves to others. Excluded people strategically consume in the service of affiliation. Happiness in this case, may be correlated with consumption as a way to be socially accepted and avoid social exclusion.

Let's take for granted that, for the time being, in Western societies, capitalistic materialism cannot be avoided. Brands need to sell and consumers need to consume, at least for the time being. Academic researchers, brands and marketers, having understood how crucial the situational correlation between materialism and well-being may be, need to develop a general framework of mechanisms and ethics in order to make materialistic habits better influence consumers' lifes. For instance, they could provide external stimuli and motivation for emphasizing that materialism may improve social relationships. Actually, financial aspirations are often egocentrically motivated, to get ahead in life. But they can also be sociocentrically motivated. Materialism could be actually motivated to satisfy the need for relatedness. Possessions can be important stores of social memories, tools of social protection, connection, or production. People may cherish particular possessions for such sociocentric motivations, but they may also cherish possessions in general for these motivations, and this could directly improve their social relationships. Both academic research and brand positioning on this possibility would provide new insights about the virtuous, positive sides of materialism, and it would contribute to a different, more holistic outlook on people’s material and social relationships, for a better future.