评论
打印
The American college basketball tournaments known as "March Madness" begin this week.
被称为“疯狂三月”的美国大学篮球锦标赛于本周拉开帷幕。
College basketball, or National Collegiate Athletic Association (N.C.A.A.) basketball, is very popular in the United States.
大学篮球赛或美国全国大学体育协会（N.C.A.A.）篮球锦标赛在美国非常受欢迎。
In parts of the country it is even more popular than professional basketball.
在美国部分地区，它甚至比职业篮球赛更受欢迎。
And, many people like to try to guess who will win the many games played over the next few weeks of competition.
很多人都喜欢预测在接下来几周的比赛中，谁会赢得比赛。
Sixty-seven games will be held for both men and women.
共将举行67场男子比赛和女子比赛。
A chart that shows the sequence of games is called a bracket.
显示比赛顺序的图表被称为“对阵表”。
Thousands of fans in the U.S. compete with each other to correctly predict the most outcomes of each game.
美国成千上万的球迷相互竞争，力图正确预测每场比赛的最多结果。
Today, more people are using artificial intelligence, or AI, to help them fill their brackets.
如今，越来越多的人开始使用人工智能（AI）来帮助他们填写对阵表。
Using AI for bracketing in the tournament is not so new.
使用人工智能预测入围赛结果并不是什么新鲜事。
Even so, the yearly bracket competitions still provide many surprises for computer science experts who have spent years creating their models using past tournament results.
即便如此，每年的对阵表预测赛仍然会给计算机科学专家带来许多惊喜，这些专家花费了数年时间利用过去的比赛结果创建模型。
The researchers have found that machine learning alone cannot quite solve for the limited data and unpredictable human elements of the tournament.
研究人员发现，仅靠机器学习并不能完全解决比赛中有限的数据和不可预测的人为因素。
A normal fan may spend a few days this week deciding which team might win a few games in the tournament.
普通球迷可能会在本周花几天时间决定哪支球队可能会在锦标赛中赢得几场比赛。
But some computer experts are going after even more detailed information.
但一些计算机专家正在研究更详细的信息。
They are using complex math to find the best model for predicting success in the tournament.
他们正在使用复杂的数学方法来找到预测比赛胜负的最佳模型。
Some are using AI to perfect their codes or decide which qualities of the team can best predict their competitive future.
有些人正在使用人工智能来完善他们的代码，或者决定一支球队的哪些特质最能预测他们未来的竞争力。
The chances of creating a perfect bracket are extremely low for any competitor, however advanced their tools may be.
对于任何竞争者来说，无论他们的工具多么先进，创建一个完美对阵表的可能性都非常低。
An "informed fan" making choices based on past results has a 1 in 2 billion chance at perfection, says Ezra Miller.
埃兹拉·米勒（Ezra Miller）表示，一位“内行球迷”根据过去的比赛结果做出完美预测的几率是20亿分之一。
He is a mathematics professor at Duke University.
米勒是杜克大学的数学教授。
Artificial intelligence is likely very good at determining the probability that a team wins, Miller said.
米勒说，人工智能可能非常擅长判断一支球队获胜的概率。
But even with the models, he added that the "random choice of who's going to win a game that's evenly matched" is still a random choice.
但他补充说，即使有了这些模型，“随机选择谁将从一场势均力敌的比赛中获胜”仍然是一种随机选择的结果。
For the 10th straight year, the data science community Kaggle is hosting "Machine Learning Madness."
数据科学社区Kaggle连续第十年举办“疯狂机器学习”赛。
In traditional bracket competitions, people simply write each team they think will win.
在传统的对阵表预测赛中，人们只需写下自己认为会获胜的每支队伍。
But "Machine Learning Madness" requires users to enter a percentage representing their level of confidence that a team will advance.
但“疯狂机器学习”赛要求用户输入一个百分比，代表他们对某支队伍晋级的信心程度。
Kaggle provides a large data set from past results for people to develop their algorithms.
Kaggle从过去的比赛结果中提供了大量数据集，供人们开发算法。
That includes information on a team's free-throw percentage, turnovers and assists.
其中包括一支球队的罚球命中率、失误率和助攻率等信息。
Users can then turn that information over to an algorithm to find the statistics most predictive of tournament success.
然后，用户可以将这些信息交给算法，得出最能预测比赛胜负的统计数据。
"It's a fair fight. There's people who know a lot about basketball and can use what they know," said Jeff Sonas.
杰夫·索纳斯说：“这是一场公平的较量。有些人对篮球非常了解，他们可以利用自己的知识。”
He is a statistical chess analyst who helped found the competition.
他是一名国际象棋统计分析师，他帮助创办了这项比赛。
"It is also possible for someone who doesn't know a lot about basketball but is good at learning how to use data to make predictions."
“对篮球了解不多，但善于学习如何利用数据进行预测的人也有可能获胜。”
No method will include every element at play on the court.
任何方法都不可能囊括球场上的所有因素。
There is a balance between modeling and intuition, said Tim Chartier, a Davidson University bracket expert.
戴维森大学（Davidson University）的对阵表专家蒂姆·查蒂尔（Tim Chartier）说，建模和直觉之间需要一种平衡。
Chartier has studied brackets since 2009.
查蒂尔自2009年起就开始研究对阵表。
He developed a method that largely depends on team success on home court and away, performance in the second half of the season and difficulty of schedule.
他开发的方法主要取决于球队在主场和客场的成绩、赛季后半段的表现以及赛程难度。
But he said the NCAA Tournament's historical results provide an unpredictable and small sample size.
但他说，NCAA锦标赛的历史成绩提供了一个小的、不可预测的样本量。
That is a difficulty for machine learning models, which use large sample sizes.
这对于使用大样本量的机器学习模型来说是个难题。
Chartier's goal is never for his students to reach perfection in their brackets.
查蒂尔的目标从来不是让他的学生完美预测出对阵表的结果。
His own model still cannot account for Davidson's 2008 unexpected admission into the "Elite Eight" level of the tournament.
他自己的模型仍然无法解释戴维森队2008年意外杀入“八强”的原因。
In that mystery, Chartier finds a useful reminder from March Madness: "The beauty of sports, and the beauty of life itself, is the randomness that we can't predict."
在这个谜团中，查蒂尔从“疯狂三月”中找到了一个有用的启示：“体育的魅力，以及生活本身的魅力，就在于我们无法预测的随机性。”
I'm Dan Novak.
丹·诺瓦克为您播报。
译文为可可英语翻译，未经授权请勿转载！
