I think so. To be more specific: argmin_p sum_i (c_i * (p - r_i)^2 )
And I would call the different r_i "observed" rather than "true" ratings and note that they are plural (English is ambiguous there). On Tue, Feb 23, 2010 at 6:39 PM, Tamas Jambor <[email protected]>wrote: > argmin sum(c*(p-r)^2) > > where c is the correlation, p is the prediction and r is the true rating. > -- Ted Dunning, CTO DeepDyve
