5938329_Baillie_BUSI510_08A_Sept_6

5938329_Baillie_BUSI510_08A_Sept_6 - Running head: DATA...

Info iconThis preview shows pages 1–4. Sign up to view the full content.

View Full Document Right Arrow Icon
Running head: DATA MINING 1 Customer Relationship Management Role to Business Judith Baillie American Sentinel University
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
DATA MINING 2 Customer Relationship Management Role to Business 1. Introduction This paper will discuss t he term "lift" and it applications to business and data mining. Further evaluation of customer relationship management (CRM) and the benefits of its use in business, and scalability of the product to meet the needs of a company. This paper will additionally compare and contrast affinity positioning and cross-selling and real life examples and personal experiences. Lastly, identifying and discussing potential ethical issues regarding cross-selling, marketing to targeted demographic population more likely to accept the suggested purchase. 2. What is meant by the term "lift"? The author of the text Olson & Shi (2007) describe “lift” as “the marginal difference in a segment’s proportion of response to a promotion and the average rate of response.” (p. 262). The term “lift” is a concept that has an interpretive definition. When reviewing the literature this became more evident as the sources provided a variance in the definition, yet there is a basic premise. In data mining it is used in conjunction with other terms to explain the distribution of data (Olson et al., 2007). When evaluating a predictive model it is “the measure that compares the predictive ability of a model to randomness is called the lift”(Tsiptsis and Chorianopoulos, 2009, p. 6). It denotes how much better a classification in data mining model performs in comparison to a random selection. For instance, in a churn model gain, response and “lift” measures are the appropriate performance measures. In this case, “lift” is a performance measure and is used for model evaluation. It is defined as the ratio of the response percent to the prior probability (Tsiptsis and Chorianopoulos, 2009, p. 6). In other words, it compares the model quantiles, which “are points taken at regular intervals from the cumulative distribution of a random variable”, to a random list of the same size in terms of the probability of the target category (Weisstein, 2010). Therefore,
Background image of page 2
DATA MINING 3 it represents how much a data mining model exceeds the baseline model of random selection (Tsiptsis et al., 2009). Another source provided additional discussion of “lift”, which aids in the understanding of the concept. According to Han & Kamber (2006) “lift is a simple correlation measure that is derived through multiplication and division or it can be measured by computing, producing the degree correlation that is either negative, independent or positive correlated (between the occurrence between two items)” (p. 265). In other words, it determines the degree to which the event of one “lifts” the event of the other (Han et al., 2006). Han & Kamber (2006) provide the following example; if A corresponds to the sale of computer games and B corresponds to the sale of videos, then
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 4
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 10/30/2010 for the course BUSI 510 taught by Professor Rodreguiz during the Fall '10 term at ASU.

Page1 / 15

5938329_Baillie_BUSI510_08A_Sept_6 - Running head: DATA...

This preview shows document pages 1 - 4. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online