We provide a unified overview of methods that currently are widely used to
assess the accuracy of prediction algorithms, from raw percentages, quadrat
ic error measures and other distances, ann correlation coefficients, and to
information theoretic measures such as relative entropy and mutual informa
tion. We briefly discuss the advantages and disadvantages of each approach.
For classification tasks, we derive new learning algorithms for the design
of prediction systems by directly optimising the correlation coefficient.
We observe and prove several results relating sensitivity nod specificity o
f optimal systems. While the principles are general, we illustrate the appl
icability on specific problems such as protein secondary structure and sign
al peptide prediction.