Performance of Taiwan hotel industry using a new Data Envelopment Analysis model

There are several techniques in the performance evaluation of the hotels, but Data Envelopment Analysis (DEA) is one of the most frequently used methods. Most of researches on hotel performance employed the traditional DEA model. However, the traditional DEA model only cares about how to maximize the efficiency of the units under evaluation. This usually generates that very small weights (or zero weights) are assigned to some inputs or outputs. Then, these inputs or outputs would have little or even no contribution to the efficiency results. This is unfair and irrational. The purpose of this paper is to solve this problem and a new DEA model is proposed. A real case involving 21 Taiwan hotels is also provided to examine the validity of the proposed method. The results demonstrate that the model proposed in this paper not only shows the superiority in effectively avoiding zero weights, but also offers unique ranking for all hotels.