In 2002, Oakland Athletics’ general manager Billy Beane changed the game of baseball. He used data to pick a team of “undervalued” players and turned it into a 20-game winning streak. With a budget far less than the New York Yankees, Beane picked a competing group of players by using statistics that were “highly predictive” of a player’s future behavior. In subsequent years, the A’s averaged 95 wins per season, captured four division titles, and made five playoff appearances. His journey and success is told in the 2011 big budget Hollywood movie, Moneyball, starring Brad Pitt.
Beane changed the structure of baseball as his strategy gave teams with a lower budget a shot to compete with the “big market teams.” One critical misconception is that Bean was the first to use this past data. Of course, teams used data before, but Bean taught us a valuable lesson about how he extracted value from his data. Before Bean, teams often suffered from affirmation bias and allowed emotion to get in the way of their decisions. Beane stripped this away and saw it without prejudice.
The book “Moneyball: The Art of Winning an Unfair Game” (which was later made into the famous Brad Pitt film) tells the story of just one example of the importance predictability plays in big data and how it can increase profits. Like a baseball team, predictability analysis can make a company more profitable, this time predicting company behavior rather than player performance. Predictive analysis is a technique used to forecast trends and behaviors in an industry by optimizing marketing productivity, gaining a competitive advantage, understanding customers better, locating areas of attrition, and identifying new revenue opportunities.