Presentation is loading. Please wait.

Presentation is loading. Please wait.

DATA MINING REAL WORLD APPLICATIONS DIRECT QUOTES FROM SOURCE: RAINER, KELLY, PRINCE, BRAD AND WATSON, HUGH, MANAGEMENT INFORMATION SYSTEMS: MOVING BUSINESS.

Similar presentations


Presentation on theme: "DATA MINING REAL WORLD APPLICATIONS DIRECT QUOTES FROM SOURCE: RAINER, KELLY, PRINCE, BRAD AND WATSON, HUGH, MANAGEMENT INFORMATION SYSTEMS: MOVING BUSINESS."— Presentation transcript:

1 DATA MINING REAL WORLD APPLICATIONS DIRECT QUOTES FROM SOURCE: RAINER, KELLY, PRINCE, BRAD AND WATSON, HUGH, MANAGEMENT INFORMATION SYSTEMS: MOVING BUSINESS FORWARD, JOHN WILLEY & SONS, INC.: NEW JERSEY, 3RD EDITION, 2015 (FROM CHAPTER 5)

2 Travelers are accustomed to long flight delays and cancellations for any number of reasons. Few customers realize that airlines themselves are not particularly accurate at predicting when a flight will arrive at its destination even when it is ready to leave the gate. Making a pinpoint-accurate prediction on gate arrival times is notoriously tricky, because many factors alter flight times. Weather and wind are the most common, but there are also ground issues, such as the passenger who neglects to board his flight on time, causing his bags to have to be offloaded. As a result, airline predictions are off by an average of seven minutes across the industry. Alaska Airlines (www.alaskaair.com) and General Electric (Ge; www.ge.com) sponsored a Flight Quest contest aimed at developing an algorithm that could help airlines better predict flight arrival times and reduce passenger delays. The contest, which was set up on the contest Web site Kaggle (www.Kaggle.com), provided contestants with two months of flight data, such as arrivals, departures, weather, and latitudes and longitudes along the routes. Such data are typically not available to the public because they are owned by the airlines and manufacturers.www.alaskaair.comwww.ge.comwww.Kaggle.com PREDICTING AIRPLANE ARRIVALS MORE ACCURATELY

3 Card swipe data used to be an untapped source of data for banks. Banks wanted to use that data to increase their revenues and to attract loyalty by targeting deals to their customers. The banks, however, needed a “middleman” to analyze the data and actually deliver the offers. Cardlytics has helped pioneer a data-driven advertising niche called merchant-funded rewards. The company collects data from 70 percent of U.S. transactions in 2013, amounting to $500 billion in spending. Cardlytics tracks and understands consumer buying behaviors. That is, the company targets people based on what they buy, not on who they are. Cardlytics works on the principle that if you know where and how people are spending money, then you know many thins about them even if you can’t access their personally identifying information. For example, if a woman is going to McDonald’s and then to Target and finally to Babies “R” Us, then she would probably be young mother. Likewise, if a man makes his purchases at bars and Taco Bell, he is probably single. CARDLYTICS ANALYZES CUSTOMER BUYING BEHAVIORS

4 Cardlytics tracks and understands consumer buying behaviors. That is, the company targets people based on what they buy, not on who they are. Cardlytics works on the principle that if you know where and how people are spending money, then you know many thins about them even if you can’t access their personally identifying information. For example, if a woman is going to McDonald’s and then to Target and finally to Babies “R” Us, then she would probably be young mother. Likewise, if a man makes his purchases at bars and Taco Bell, he is probably single. Merchants can utilize Cardlytics data analyses based on actual customer buying behaviors to present precisely targeted, relevant advertisements to clients of financial institutions. These ads also include offers to participate in merchant rewards programs. Offers are distributed via secure bank channels including online banking, mobile banking, secure text, e-mail, and/or ATM machines. CARDLYTICS ANALYZES CUSTOMER BUYING BEHAVIORS

5 DATA MINING APPLICATION AREAS (1) In most cases the purpose of data mining is to identify a business opportunity in order to create a sustainable competitive advantage. Retailing and sales. Predicting sales, preventing theft and fraud, and determining correct inventory levels and distribution schedules among outlets. Banking. Forecasting levels of bad loans and fraudulent credit card use, predicting credit card spending by new customers, and determining which kinds of customers will best respond to (and qualify for) new loan offers. Manufacturing and production. Predicting machinery failures, and finding key factors that help optimize manufacturing capacity. Insurance. Forecasting claim amounts and medical coverage costs, classifying the most important elements that affect medical coverage, and predicting which customers will buy new insurance policies.

6 DATA MINING APPLICATION AREAS (2) In most cases the purpose of data mining is to identify a business opportunity in order to create a sustainable competitive advantage. Policework. Tracking crime patterns, locations, and criminal behavior; identifying attributes to assist in solving criminal case. Several cities have teamed up with IBM to analyze crime history and to strategically deploy police officers. Memphis, which reduced its crime rate by 14 percent in 2013, employed this system. Chicago adopted the “predictive policing” system in 2013 in hopes of reducing the city’s 500 homicides in 2012. Chicago reported 415 homicides in 2013, but there is disagreement about the causes of the decrease. Healthcare. Correlating demographics of patients with critical illnesses, and developing better insights on how to identify and treat symptoms and their causes. In March 2013, Microsoft and Stanford University announced that they had mined the search data of millions of users to successfully identify unreported side effects of certain medications. Marketing. Classifying customer demographics that can be used to predict which customers will respond to a mailing or buy a particular product.

7 DATA MINING APPLICATION AREAS (3) In most cases the purpose of data mining is to identify a business opportunity in order to create a sustainable competitive advantage. Politics. In his FiveThirtyEight blog, Nate Silver famously analyzed polling and economic data to predict the results of the 2008 presidential election, calling 49 out of 50 states correctly. He then correctly predicted all 50 states in the 2012 presidential election. Weather. The National Weather Service is predicting weather with increasing accuracy and precision. Higher education. Desire2Learn (www.desire2learn.com) provides an application called Degree Compass that recommends courses based on students’ majors, transcripts, and past course success rates. In March 2013, Degree Compass reported a 92 percent accuracy rate across four universities in predicting the grade that a student would receive in a course.www.desire2learn.com


Download ppt "DATA MINING REAL WORLD APPLICATIONS DIRECT QUOTES FROM SOURCE: RAINER, KELLY, PRINCE, BRAD AND WATSON, HUGH, MANAGEMENT INFORMATION SYSTEMS: MOVING BUSINESS."

Similar presentations


Ads by Google