Squared Log Error (per observation)Source:
Calculates the per-observation squared error as $$ \left( \ln (1 + t_i) - \ln (1 + r_i) \right)^2. $$
Measure to compare true observed response with predicted response in regression tasks.
Note that this is an unaggregated measure, returning the losses per observation.
Range (per observation): \([0, \infty)\)
Minimize (per observation):