QNT 275 Business Decision Making Project Part 1

Data Mining

Abercrombie & Fitch Co.

Abercrombie & Fitch Co. is an older company that was founded in 1892 by David T. Abercrombie and Ezra Fitch. The company headquarters is located in New Albany, Ohio.  Abercrombie & Fitch has over 1000 stores located throughout the world.  Despite being much larger and more expensive than Aéropostale, Abercrombie & Fitch is in direct rivalry with Aéropostale (Lepore, 2011). Abercrombie & Fitch started as an “outdoor gear shop,” but over time it became a retail clothing store targeting teens (Lepore, 2011).

Abercrombie & Fitch fell into bankruptcy in 1977 and closed. In 1988 the company reopened with a new focus on selling trendy clothing for teens. This model worked and sales were extremely successful. Abercrombie & Fitch has expanded into several brands, including Hollister and Gilly Hicks (Lepore, 2011). Abercrombie has done well financially in recent years but being in a trendy clothing retail market, the company must continue to find the next most popular styles and products. The following report presents a means of marketing research that utilizes data mining to find patterns in the store’s current customer and sales base.

Market Research Issue

Gathering marketing data in a trend market is a serious issue.  This problem can be seen in the failure rate of products which approximately 75% in all markets (Solomon, Marshall, & Stuart, 2011).   Current methods of data gathering are inadequate due to the overreliance on surveys and focus groups. These sources of data collection can be easily manipulated or biased (Solomon, Marshall, & Stuart, 2011).  A relatively new method, born out of information technology, is the data mining tool. Data mining utilizes existing customer sales information and other information collected during the sales process, to identify statistical patterns (O’Brien, 2002).  These patterns in the data can be used to forecast sales and trends in buying.

Sales Information Variables

            The variables that need to be analyzed in the data mining method is customer spending on particular lines of clothing and apparel. By collecting what customers are buying, the data mining tools can identify which brands and styles are most popular.  The use of this information will provide marketing strategies.

Quantitative Data

Data mining provides quantitative data which is stronger than qualitative. The number of sales and sales in particular styles or products does not need interpretation. The strongest interests of customers is readily identified through the numbers. However, judging the strength of the consumer’s interest will likely require qualitative research. To understand the number of sales in relation to product marketing direction will require interpretation.

Data Collection Validity

Data mining using sales figures is highly accurate because it is derived directly from customer records. This data does not lie or require intensive interpretation. The real question will be which means of data mining will yield the best results (O’Brien 2002). The problem with data mining is that it requires computer software in order to handle the enormous volumes of data and to efficiently search this data for patterns (O’Brien, 2002).   The most effective method of statistical analysis can be obtained through rule induction data mining. Rule induction works based on the statistical significance of data. When data is mined areas of statistical significance are used to create if-then rules which provide decision making parameters. For example, if customer data shows that service failures are occurring on Friday evenings due to lack of personnel, then staff must be increased to compensate for this failure. If then logical statements can be linked creating complex decision making systems (Kroenke, 2013).  This method will yield the best results because the researcher can assign rules or conditions such as when certain clothes sell best during which seasons. As well, styles and brands can be applied to these rules. This system should provide the greatest amount of data that is able to provide marketing information.

References

Hone, F. “New strategies for progressive organizations. Market forces and the new focus on demand-driven health care.” Employee Benefit News 21, no. 1 (2007): 12.

Laudon, Kenneth C., and Jane Price Laudon. Management Information Systems: Managing the Digital Firm. NJ: Prentice Hall, 2005.

O’Brien, J. A. Management Information Systems: Managing Information Technology in the E-Business Enterprise, 5th ed. Boston: McGraw-Hill Irwin, 2002.

Solomon, M., G. Marshall, and E. Stuart. Marketing: Real People,Real Choices. Textbook. 7th edition. Prentice Hall: Pearson, 2011.

 

Leave a Reply

Your email address will not be published.