A Novel Machine Learning Approach Combined with Optimization Models for Eco-efficiency Evaluation

Abstract

Machine learning approaches have been developed rapidly and also they have been involved in many academic findings and discoveries. Additionally, they are widely assessed in numerous industries such as cement companies. Cement companies in developing countries, despite many profits such as valuable mines, face many challenges. Optimization, as a key part of machine learning, has attracted more attention. The main purpose of this paper is to combine a novel Data Envelopment Analysis (DEA) approach in optimization at the first step to find the Decision-Making Unit (DMU) with innovative clustering algorithms in machine learning at the second step introduce the model and algorithm with higher accuracy. At the optimization section with converting two-stage to a simple standard single-stage model, 24 cement companies from five developing countries over 2014–2019 are compared. Window-DEA analysis is used since it leads to increase judgment on the consequences, mainly when applied to small samples followed by allowing year-by-year comparisons of the results. Applying window analysis can be beneficial for managers to expand their comparison and evaluation. To find the most accurate model CCR (Charnes, Cooper and Rhodes model), BBC (Banker, Charnes and Cooper model) and Free Disposal Hull (FDH) DEA model for measuring the efficiency of decision processes are used. FDH model allows the free disposability to construct the production possibility set. At the machine learning section, a novel three-layers data mining filtering pre-processes proposed by expert judgment for clustering algorithms to increase the accuracy and to eliminate unrelated attributes and data. Finally, the most efficient company, best performance model and the most accurate algorithm are introduced. The results indicate that the 22nd company has the highest efficiency score with an efficiency score of 1 for all years. FDH model has the highest efficiency scores during all periods compared with other suggested models. K-means algorithm receives the highest accuracy in all three suggested filtering layers. The BCC and CCR models have the second and third places, respectively. The hierarchical clustering and density-based clustering algorithms have the second and third places, correspondingly.

Optimization of Solar CCHP Systems with Collector Enhanced by Porous Media and Nanofluid

“…We may also investigate the application of machine learning paradigms [31][32][33][34][35][36][37][38][39][40][41] and various hybrid, advanced optimization approaches that are enhanced in terms of exploration and intensification [42][43][44][45][46][47][48][49][50][51][52][53][54][55], and intelligent model studies [56][57][58][59][60][61] as well, for example, methods such as particle swarm optimizer (PSO) [60,62], differential search (DS) [63], ant colony optimizer (ACO) [61,64,65], Harris hawks optimizer (HHO) [66], grey wolf optimizer (GWO) [53,67], differential evolution (DE) [68,69], and other fusion and boosted systems [41,46,48,50,54,…”

A novel artificial intelligent approach: comparison of machine learning tools and algorithms based on optimization DEA Malmquist productivity index for eco-efficiency evaluation

“…This efficient use contributes a relative advantage to developed countries such as India and China, which are encouraged to renovate their production processes. In terms of CO 2 emissions, DEA and eco-efficiency, some outstanding recent studies can be addressed in the literature (Grigoroudis and Petridis, 2019; Wang et al , 2011; Almutairi and Elhedhli, 2014; Bi et al , 2014; Zeng et al , 2016a; Li and Lin, 2016; Jiang et al , 2016; Zeng and Chen, 2016; Zeng et al , 2016b; Mahmoudi et al , 2019b; Jin et al , 2018; Khoshroo et al , 2018; Arabi et al , 2017; Boyd and Pang, 2000; Wei et al , 2007; Azadeh et al , 2007; Angulo-Meza et al , 2019; Balitskiy et al , 2016; Bian et al , 2016; Moya et al , 2016; Mirmozaffari, 2019; Mirmozaffari, 2020; Mirmozaffari et al , 2017; Mirmozaffari et al , 2020; Lee and Park, 2017; Taleghani and Taleghani, 2020; Yu et al , 2014; Malakoutian and Khalsar, 2020; Khaksar and Malakoutian, 2020).…”

“…It is a non-parametric frontier technique where the efficiency of a specific entity is calculated by its distance from the highest performance practice frontier created by the most exceptional performance entities inside the group. DEA is a general method for assessing the efficiency of ecological systems (Li et al , 2019; Mirmozaffari et al , 2020).…”

Machine Learning Algorithms Based on an Optimization Model

“…Once input/output selection is not right thereafter the score will not be valid anymore [10]. On the other hand, the DEA model does not have these kinds of drawbacks, and also there are no random errors in this model [11][12][13][14][15]. Thus, these two methods have both advantageous and disadvantageous [16].…”

“…Lots of the researchers are of the opinion that choosing a proper data mining method is dependent to the analyst's experience [12,38]. Ozekes and Camurcu [39], proposed an application for classification and prediction in the data mining field in which the decision tree will be created by the credits which the bank gives to the customers.…”