Quote:
Originally Posted by Zunaid
That's not quite a valid assertion because the assumption being made here is that all opponents are of equal strength. For a better predictive power, we will need to factor in the strength of the opposition at the very least.
Looks like a simple machine learning model could be constructed. For simplicity, we can start with the following features:
- Oponent strength - we can use ICC rating as a value
- Type of match (ODI/TEST/T20I)
- Ground
Of course, we can start more and more features such as month of match, who batted first, team compositions (how many spinners vs pacers), etc etc.
Of course, the more features we have, we need to come up with some feature selection algorithm - or we may be in danger over fitting.
I just have a gut feeling that we might get best results with an SVM. But YMMV.
|
We also need to give players of both teams some ranking
For example Shakib +5
Gazi +4 (considering he'll learn dusra ,tisra from saqlain)
Tamim +3
Junaid 0
Ashraful -2
SN -3
Razzak (+3 for spin friendly pitch, -2 for unfriendly pitch)
If you want to find out expected result/outcome than yes SVM is my guess too, but if you want to choose players based on opponents, ground, month of the year, recent performance etc, I would suggest Rule based learning C4.5 (decision tree).
May be something our selectors and team management can consider.