Skip to content

Latest commit

 

History

History
9 lines (8 loc) · 542 Bytes

README.md

File metadata and controls

9 lines (8 loc) · 542 Bytes

Tennis

- Pre-processing stage:

  • Created data frames by combining multiple data sources.
  • Data analysis in order to find the best features for the task.

- Compared multiple ML algorithms predicting results with each other and with baseline predictors.

- Analysis of results and fine tuning for the best Hyper-parameters.

- Implemented robust model that achieved better results than similar projects from Stanford.

- The model achieved around 10% improvement in comparison to the baseline models on close matches.