The LRMS: Logistic Regression Markov Chain
Computers are better than humans at yet another thing: predicting sports results.
Designed and maintained by Joel Sokol, Paul Kyam and George Nemhauser, who are three Engineering Professors at the Georgia Institute of Technology, LRMC is set apart from other computer rankings systems in its method of determining the value of home court advantage. LRMC considers how much playing at home helps a team win rather than how many points playing on a home court is worth…
“Our system objectively measures each team’s performance in every game it plays, and mathematically balances all of those outcomes to determine an overall ranking.”
I guess it is able to predict results with 83 percent accuracy, which is currently better than any other machine or human. They should try hooking it up to the stock market.
