Predictive Analytics 357 IT's About Business 12.3 Simpa Networks Provide Solar Energy to India's Poor ective is to provide the most appropriate services and su at is, the model enable POM ing customers. The pimpa to bed become more savvy in choos- he model also enables Simpa to take risks when Worldwide, approximately 1.6 billion people do not have electric lending to rural farmers who cannot turn to banks for loan ity, and another 1 billion have only unreliable access. Many of these Simp as created huge time savings for ple depend on kerosene lanterns and battery powered flash ase doing farming and domesticta the system al ks such as cooking and cleaning. lights for light. Moreover, these same people often earn less thai also has health benefits, including better quality of light. $10 per day, and they spend up to 30 percent of their incom and better air quality, thanks to reduced kerosene fumes and wood inefficient and of pensive means of accessing B electric Before Simpa's tely 8 in 10 energy-poor The of electricity is especi cially act lion fa 1475 mil- dividuals experienced eye irritation from fumes. After customers gues not having aco deployed the system, that number fell to about 3 in 10. Furthermore, "dirt fuel Such these people rely on twosend fire accidents plunged to zero. they use in lamps. There is also helps boo shops th awwwever, There are effective alternatives to elec reyopen score thanks to cheaper en woven that can pow At the end of 2016, almost 40% ower homestar ll businesses. s of smallbill Ple a ns of thou needs, Simpa Networks (www Simpa's clean, reliable en simpanetwork om), a startup technology company scoring model helped Simpa provide its system to 2010, sells ar power, not as a system but as rival pumal mix of customers. In that way, the company was able homes a businesses Its busing nodel to receive an excellent return on its invest sustainable and in turn, help who currently do onalfamilies ar no businesses. or theirenergy n Simpa's Sources: Compiled from R. Bean, "Another Side of Big Data: Big Data for mers use the "pi agressive asmodel. Unde Purchase" pricing Social Good," Forbes ptember 23, 2016: M. Barlow, "Data er this model, the consum 14, 2015; Simpa Networks: Making So ments, each of which unlocks the Macmakes a s able in Rural India," OPIC, 2014; J. Novet "De d's Do-Good ount of energy Data Science Projects Arrive in 5 M when the prepaid consum at August 21, the solar Home until the July 12:2014 Watch How Solar Power Is Transforming Run omer makes another p werogress, July 10, 2014; "We Envision a World without Ene nd the total purchase price of the product Stores furs Po Poverty by 2030: Bijli Program Update, The Climate Group, July 3, 2012 functionality. The system is Affordable Pay-As-You-Go Solar Power for Ind daces pHomes," ADB Knowledge Showcases, Augus energy for fre www.datakind.org, www m accessed August 28, 2016. problem is that, because Questions laessestosu port a result the com 1. Describe how Simpa Networks uses descriptive analytics to spyfurther its miss Scientists below 2. How does predictive analytics help Simpa Networks provide on customer solar energy to India's un erved population? ener 3. Describe how Simpa Networks could use prescriptive ana- model that helps lytics to further its mission. riairlw loudnow 219 IT's About Business 12.4 Analytics in the National Basketball Association Furthermore, each play has an obvious start point and end point. POM In statistical terms, each event is called a "state." In contrast to the discrete play in baseball, basketball is one Historically, the primary method of assessing player or team per- continuous state. Players move instantly from offense to defense. formance was the "eye test." This term refers to the intuitive feeling Moreover, regardless of a player's position, he or she can be at any that people with long experience in a sport acquired from watching spot on the court at any time. Analysts could not statistically cal- games and practices. Today, professional sports teams are utilizing culate the odds of (i.e., predict) a particular result occurring (e.g., a analytics to provide data-driven judgments. player making a shot). The analytics revolution in professional sports started in base- Consequently, modern analytics revolves around the loca- ball, as highlighted in the book and the movie Moneyball. Baseball tions and trajectories of the players and the ball. Essentially, ana- is a fairly easy sport to analyze statistically because it involves a lytics in the National Basketball Association (NBA; www.nba.com) series of one-on-one match-ups between a batter and a pitcher. is a mapping and data visualization challenge. The challenge is toCamline Exam 358 CHAPTER 12 Business Analytics graphically represent information about movement through space and time; that is, to make data observable. In other words, they decreased "shooting efficiency." In the 2014 NBA season, for example, Indiana Pacers center Roy Hibbert and The First System. Kirk Goldsberry, a longtime basketball fan Milwaukee Bucks center Larry Sanders led the NBA, reduced oppo- with a PhD in geography, undertook the task of developing ana- nents' shooting efficiency to 38 percent. lytics software for professional basketball. First, he imposed a grid In the second category of defenders, Goldsberry found that over the usable area of the court where players actually shoot-the they decreased the frequency of their opponents' shots, in addition area that stretches from just outside the three-point line (roughly to their efficiency. He examined the average rate of shots versus 25 feet) to the basket. Then he searched for data in each cell of that the rate when certain players were defending the area. This way, 1,284-square-foot grid. he could see who was in play when the number of shots decreased. Obtaining the data needed for accurate analysis was difficult. Again in the 2014 NBA season, the best player at this type of de- Mapping 10 constantly moving players is not a simple process. fense was Houston Rockets center Dwight Howard, who decreased On ESPN.com, Goldsberry grabbed statistics for all 700,000 shots opponents' shooting frequency by 9 percent. As opponents shot taken in every NBA game from 2006 to 2011. The site had such char- less often around the basket, they took more mid-range shots, acteristics as the player name, where he took the shot from, and which are the least successful shots in the league. whether it went in the basket. Goldsberry then developed a data- Because basketball has no states, Goldsberry essentially cre- base mapping the coordinates for all the shots taken in that period. ated them by dividing games into slices of time. He then employed Goldsberry next analyzed his data to graph shot statistics for in- the same types of analyses that had been applied to the states dividual players, including where a given player shot, how often, and in baseball. He could then enumerate-in terms of points-every whether or not the shot was good. This system, called CourtVision, player's every move, from an entry pass into the post (the area revealed player differences that had not been previously detected. close to the basket) to a drive to the basket. These analyses created For example, Ray Allen, one of the league's top shooters, had several a new method to assess everything a player and team does. areas from which he made a high percentage of his shots from the Let's consider one example, the Houston Rockets. Utilizing the three-point range. However, he rarely tried any mid-range shots. results of its analytics software, its players almost never attempt CourtVision enabled fans, and the league, to visualize their long-range two-point jump shots because the Rockets feel this type favorite players' shot patterns. However, CourtVision did not con- of shot is among the worst plays. The position is too far from the sider factors such as who the defender was or other events going on basket to have a high likelihood of going in, but it's not far enough around the shot. Nevertheless, Goldsberry's system provided team (behind the three-point line) to gain an extra point for the risk in management with an initial player assessment tool. taking an even longer shot. Analytics are impacting not only the Rockets, but the entire Today's System. The next opportunity to collect data came when NBA as well. For example, in one particular month, NBA data anal- a company called Stats (www.stats.com) developed a six-camera ysis revealed that players attempted more three-point shots than system for basketball. The camera system, which is now employed free throws. In fact, the three-point shot defines the shift to analyt- in all 29 NBA arenas, tracks each player on the court throughout ev- ics in the NBA. It is not a coincidence that the Golden State Warriors, ery game. It therefore provides a complete view of the entire game, who won the 2015 championship, were the NBA's top three-point including tracking individual players and ball possession. shooting team in the regular season.g Stats offered its data to Goldsberry. The data were more spe- cific than what Goldsberry had obtained from ESPN.com. Once Sources: Compiled from "NBA Teams That Have Analytics Department," NBAStuffer.com, February 18, 2017; T. Ross, "Welcome to Smarter Basket- Goldsberry had the data, he could analyze them to answer any ball," The Atlantic, June 25, 2015; K. Mehta, "Data and the NBA: A Slam number of questions. Dunk Approach to Basketball," Umbel, June 22, 2015; C. Benjamin, "The 4 Fallacies of NBA Analytics," Men's Journal, June 3, 2015; S. Hammer, . Players who "draw the defense" can be quantified as ones "Analytics Key to Modern NBA Success," The Miscellany News, May 6, 2015; who pass the ball effectively when two or more players are M. Lawrence, "Big Data's Air-Ball: Five Questions about Players that NBA guarding them. Analytics Can't Answer," Forbes, February 27, 2015; B. Alamar, "The Inside Man: NBA Analytics," ESPN.com, February 19, 2015; M. Mcclusky, "One "Getting good spacing" visualizes which players control which Man's Quest to Track Every NBA Remade Basketball," Wired, October 28, parts of the court. 2014; T. Moynihan, "The NBA's New High-Tech Control Center Is a Hoops . "On-ball defense" assesses how effectively a player defending Fan's Dream," Wired, October 28, 2014; R. Simmons, "Golden State Warriors at the Forefront of NBA Data Analysis," SFGate, September 14, 2014; B. the ball decreases his opponent's chance of scoring. Holmes, "New Age of NBA Analytics: Advantage or Overload?" Boston Globe, Analyzing the camera data also helped Goldsberry better grasp March 30, 2014; D. Oliver, "How Numbers Have Changed the NBA," ESPN.com, November 15, 2013; www.nba.com, accessed August 25, 2016. one of the most difficult parts of analyzing a basketball game: defense. Historically, teams had used basic numbers-for example, how many Questions steals, how many blocks-to evaluate a player's defensive game. The 1. Provide an example of the use of descriptive analytics for an new system provided a much more refined view of the game. NBA team using Goldberry's system. Goldsberry began by noticing that the space around the bas- 2. Provide an example of the use of predictive analytics for an ket is the most crucial to defend because this area is where offen- NBA team using Goldberry's system. sive players shoot the highest percentage. Therefore, he analyzed how effectively defenders could stop opponents from making the 3. Provide an example of the use of prescriptive analytics for shot within five feet of the basket. He found that NBA defenders an NBA team using Goldberry's system. allowed an average shooting percentage of 49.7 in that area. 4. What are the advantages and disadvantages of Goldsberry's Utilizing his new data, Goldsberry categorized defenders into system to NBA players? Provide specific examples to sup- two types. The first category blocked or altered their rivals' shots. port your answer. newled aqu-raism sno-no-sno to 29hsa