English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

During the last few sports seasons a lot of discussion has been generated forthe several, high-profile, "comebacks" that were observed in almost all sports.The Cavaliers won the championship after being down 3-1 in the 2016 NBA finals'series against the Golden State Warriors, which was exactly the case forChicago Cubs and the World Series. The Patriots won the Super Bowl in 2016 eventhough they were trailing by 25 points late in the third quarter, while FCBarcelona in the top-16 round of the 2016-17 Champions League scored 3 goalsduring the last 7 minutes of the game (including stoppage time) against PSG toadvance in the tournament. This has brought the robustness and accuracy of thevarious probabilistic prediction models under high scrutiny. Many of thesemodels are proprietary, which makes it hard to evaluate. In this paper, webuild a simple and open, yet robust and well-calibrated, in-game probabilitymodel for predicting the winner in an NFL (iWinRNFL) game. In particular, webuild a logistic regression model that utilizes a set of 10 variables topredict the running win probability for the home team. We train our model usingdetailed play-by-play data from the last 7 NFL seasons obtained through theleague's API. Our results indicate that in 75% of the cases iWinRNFL providesan accurate winner projection, as compared to a 63% accuracy of a baselinepre-game win probability model. Most importantly the probabilities thatiWinRNFL provides are well-calibrated. Finally, we have also evaluated morecomplex, non-linear, models using the same set of features, without anysignificant improvement in performance.

iWinRNFL: A Simple, Interpretable & Well-Calibrated In-Game Win Probability Model for NFL