Until now, the works regarding the relationships between corporate operating performance and corporate social responsibility (CSR) could not reach a conclusive result (positive, natural, and negative). This circumstance can be attributed to two main reasons: (1) inadequate performance measurement and (2) ignoring the multi-dimensional nature of CSR. To combat this, we provided a hybrid decision framework that consisted of two main procedures: (1) performance measurement via linear programming algorithm and (2) CSR’s multi-dimensional nature extraction via text mining. By joint utilization of a linear programming algorithm and text mining, we could gain more insights from the outcome. The proposed decision framework, tested by real cases, is a promising alternative method for performance prediction. Managers can take this model as a roadmap and allocate resources to suitable places, as well as reach the goal of sustainable development.

Measuring financial performance has become an essential topic due to the potential decimating impacts on the corporation itself as well as to whole societies during financial turmoil. In order to provide an overarching description of the multidimensional nature for measuring a corporation’s operations, it is preferable to employ data envelopment analysis (DEA). Different from prior research that merely focuses on a singular DEA performance rank, this study extends it to multiple DEA specifications (i.e., it combines inputs and outputs in several different ways) so as to make judgments more complete and robust. We also execute fuzzy visualization technique (i.e., nonlinear fuzzy robust principal component analysis, NFRPCA) to represent the main characteristics of data so that non-specialists can have better access to the results. The analyzed result is then fed into the restricted Boltzmann machine (RBM) to establish a model to forecast a firm’s operating performance. Even a fraction of accuracy improvement can result in considerable future savings to a firm and investors. When examined using real cases, the model is a promising alternative for operating performance forecasting and can assist both internal and external market participants.

The exact prediction of financial crises is an essential research task for decision makers. In recent years, data mining techniques have been used to tackle the related problems and perform a satisfactory job in various domains. However, in the information age, utilizing straightforward data mining techniques to predict financial crises has many shortcomings and limitations. Thus, this investigation utilized the random forest (RF) technique as a pre-processing procedure to determine the most representative features. Then, the selected features were fed into rough set theory to yield interpretable information for decision makers, who can use it to make suitable judgments in a turbulent economic climate. The proposed model is a promising alternative for predicting financial crisis, and it can assist in regard to both taxation and financial institutions.