We develop a procedure and the requisite theory for incorporating preferenc
e information in a novel way in the efficiency analysis of Decision Making
Units. The efficiency of Decision Making Units is defined in the spirit of
Data Envelopment Analysis (DEA), complemented with Decision Maker's prefere
nce information concerning the desirable structure of inputs and outputs. O
ur procedure begins by aiding the Decision Maker in searching for the most
preferred combination of inputs and outputs of Decision Making Units (for s
hort, Most Preferred Solution) which are efficient in DEA. Then, assuming t
hat the Decision Maker's Most Preferred Solution maximizes his/her underlyi
ng (unknown) value function, we approximate the indifference contour of the
value function at this point with its possible tangent hyperplanes. Value
Efficiency scores are then calculated for each Decision Making Unit compari
ng the inefficient units to units having the same value as the Most Preferr
ed Solution. The resulting Value Efficiency scores are optimistic approxima
tions of the true scores. The procedure and the resulting efficiency scores
are immediately applicable to solving practical problems.