1. Identify additional identity reasons why Target might invest in predictive analytics.

Current submission below:

Data mining involves cleaning up raw data, looking for patterns, developing models, and testing those models. This process is known as data mining. It encompasses database systems, statistics, and machine learning. It's simple to mistake data mining for analytics, data governance, and other data processes because it frequently involves several data projects. This manual will describe data mining, discuss its advantages and disadvantages, and go over how it operates. Data mining is not a new concept. It became popular between the 1960s to 1980s as computing advanced. Data mining used to be a labor-intensive manual coding process, and now it still requires coding skills and qualified experts to clean, analyze, and understand the results. For data specialists to successfully finish data mining processes, they also need some programming language expertise.

Data mining is most effective when used strategically to support company objectives, provide answers to research or business problems, or contribute to the resolution of issues. Data mining helps identify trends and outliers, makes accurate forecasts, and frequently provides information for forecasting. Additionally, data mining aids businesses in finding process flaws and problems including supply chain bottlenecks and incorrect data entry.

Retailers and other companies have long tracked customer purchasing patterns and combed through public information, social media, and other sources to gain knowledge about how to increase consumer product sale. Many customers probably don't realize how much information a business may learn about them. Industry methods were exposed last month in a New York Times report on Target, which tracks customer buying habits and looks for pregnant customers. The statistician at Target, Andrew Pole, used personally identifiable information (PII) to identify pregnant women who were purchasing large amounts of unscented lotion at the start of their second trimester. The data also revealed that women made significant purchases of calcium, magnesium, and zinc at some point during the first 20 weeks. Without respect to baby registries, Pole was able to determine a customer's likelihood of becoming pregnant based on their in-store purchases of around 25 different items and their number of purchases.

The Target advertising team discovered over time that customers are extremely freaked out if the company knows too much about them, particularly personal information like being pregnant. To reduce the "creep effect," the marketing group realized they needed to mix in other commercials with these targeted ones. In their sales booklet, the same pregnant consumer is now exposed to advertisements for items such as various foods, household goods, lawn care equipment, and clothing in addition to diapers and cribs. Even if the mix and match is less direct and less invasive, proper targeting is still possible.

References:

Hill, K. (2012). Target Isn't Just Predicting Pregnancies: 'Expect More' Savvy Data-Mining Tricks. Retrieved https://www.forbes.com/sites/kashmirhill/2012/02/24/target-isnt-just-predicting-pregnancies-expect-more-savvy-data-mining-tricks/?sh=201bd6ed598aLinks to an external site.Lipka, M. (2014). What target Knows about you. Retrieved https://www.reuters.com/article/us-target-breach-datamining/what-target-knows-about-you-idUSBREA0M1JM20140123