Daily Plus-Minus (DPM), aka DARKO or DPM is a composite plus-minus metric which is invented by Kostya Medvedovsky. In his own words, DARKO is a “machine learning-driven basketball player box-score score projection system”. Their DARKO.app updates daily for every player by collecting data from NBA, Basketball-Reference, and PBPStats to account for time series and sample size using the complex methods of “exponential decay” and “Kalman filters”. DARKO.app website also offers great data visualization tools.
The main difference between DPM and the other player impact metrics is that DPM solely looks forward by giving the results in a Bayesian model which projects all elements of the box score.
Based on root mean square error, DPM is better than any impact metric in terms of predictive analytics where EPM ranks second and LEBRON third.