A combined machine learning algorithms and DEA method for measuring and predicting the efficiency of Chinese manufacturing listed companies

Zhu, Nan; Zhu, Chuanjin; Emrouznejad, Ali

doi:10.1016/j.jmse.2020.10.001

Cited by 55 publications

(57 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ML can be applied to various disciplines e.g., statistics, convex analysis, probability, approximation, and algorithm complexity theory. ML algorithms focus on how computers implement and simulate the learning behaviors of humans, in order to obtain new knowledge and constantly enhance prediction performance [7]. As a branch of Artificial Intelligence (AI), ML models entail many principles by exploiting the rapid growth of data [7].…”

Section: ML In Risk Managementmentioning

confidence: 99%

“…ML algorithms focus on how computers implement and simulate the learning behaviors of humans, in order to obtain new knowledge and constantly enhance prediction performance [7]. As a branch of Artificial Intelligence (AI), ML models entail many principles by exploiting the rapid growth of data [7]. Predictive or classification analytics is a crucial capability of ML [39].…”

Section: ML In Risk Managementmentioning

confidence: 99%

“…ML algorithms cover unsupervised learning, semi-supervised learning, supervised learning, and intensive learning. One of the broadly utilized ML algorithms is supervised learning, which are useful for classification and prediction (or regression) tasks [7]. In prediction, the ML algorithms use previous data to predict the future, and their predictive power grow with additional data, accordingly, improving their prediction accuracy over time [40].…”

Section: ML In Risk Managementmentioning

confidence: 99%

“…In Fig. 1(b), a simple ANN structure is shown, covering the neuron connections, biases allocated to neurons, and weights designated to the connections, depicting a multi-layer model [7]. A neuron can be identified by two equations, as follows [54]:…”

Section: B ML Application In Risk Management Contextmentioning

confidence: 99%

“…Indeed, DEA (DEA extension or DEA integrated with other methods) offers a logical approach to analyze and determine the risk level of activities in an organization. Nonetheless, when a set of new DMUs is available for analyzing its performance level (represented by the efficiency scores), it is necessary to re-compute the DEA procedure [7]. When applying the DEA to risk management in the situation where an organization has already evaluated the current level of risk for a sizable number of DMUs, the subsequent reapplication of DEA for risk evaluation renders different results.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

An Application of Data Envelopment Analysis and Machine Learning Approach to Risk Management

2021

View full text Add to dashboard Cite

An integrated method comprising Data Envelopment Analysis (DEA) and machine learning (ML) for risk management is proposed in this paper. Initially, in the process of risk assessment, the DEA cross-efficiency method is used to evaluate a set of risk factors obtained from the Failure Mode and Effect Analysis (FMEA). This FMEA-DEA cross-efficiency method not only overcomes some drawbacks of FMEA, but also eliminates several limitations of DEA to offer a high discrimination capability of decision units. For risk treatment and monitoring processes, an ML mechanism is utilized to predict the degree of remaining risk depending on simulated data corresponding to the risk treatment scenario. Prediction using ML is more accurate since the predictive power of this model is better than that of DEA which potentially contains errors. Based on a case study with a group of logistics service providers, the results ascertain that the combined DEA and ML approach offers a flexible and reasonable alternative in risk management. The approach allow decision-makers or managers to assess and monitor the risk level for handling forthcoming events in unusual conditions. It also serves as a useful knowledge repository such that appropriate risk mitigation strategies can be planned, along with the predicted results. The outcome of our empirical evaluation indicates that the proposed approach contributes towards robustness in sustainable business operations.

show abstract

Section: ML In Risk Managementmentioning

confidence: 99%