Predicting the performance of MSMEs: a hybrid DEA-machine learning approach

Abstract

Micro, small and medium enterprises (MSMEs) dominate the business landscape and create more than half of employment worldwide. How we can apply big data analytical tools such as machine learning to examine the performance of MSMEs has become an important question to provide quicker results and recommend better and more reliable solutions that improve performance. This paper proposes a novel method for estimating a common set of weights (CSW) based on regression analysis for data envelopment analysis (DEA) as an important analytical and operational research technique, which (i) allows for measurement evaluations and ranking comparisons of the MSMEs, and (ii) helps overcome the time-consuming non-convexity issues of other CSW DEA methodologies. Our hybrid approach used several econometric and machine learning techniques (such as Tobit, least absolute shrinkage and selection operator, and Random Forest regression) to empirically explain and predict the performance of more than 5400 Vietnamese MSMEs (2010‒2016), and showed that the machine learning techniques are more efficient and accurate than the econometric ones. Our study, therefore, sheds new light on the two-stage DEA literature, especially in terms of predicting performance in the era of big data to strengthen the role of analytics in business and management.

Estimating the productivity of US agriculture: The Fisher total factor productivity index for time series data with unknown prices

“…Future research can extend our approach by examining the SPFI in other fields such as banking and finance, health care and transportation where the structure of prices is complicated and often unknown (Alexakis et al., 2019; Boubaker et al., 2024; Liu et al., 2013; Oh et al., 2017). It would be interesting to include more advanced DEA models, such as the variable returns to scale assumption (Banker et al., 1984), the slack‐based measures (Tone, 2001), the common set of weights (Hammami et al., 2022), inverse DEA (Boubaker et al., 2022) or DEA‐machine learning (Boubaker et al., 2023). One could also decompose the SPFI to provide better insights into different aspects of changes in productivity over time, such as technical changes, technological changes or changes in scale efficiency (Färe et al., 1994; Ngo & Nguyen, 2012).…”

Pro-Environmental MSMES Performance: The Role of Green it Adoption, Green Innovative Behavior, and Financial Accounting Resources

“…Company performance is actually not only measured by financial performance but also non-financial ones such as reputation, customer loyalty, employee morale and other measures (Larios-Francia & Ferasso, 2023;Boubaker et al, 2023). MSMEs must be able to maintain good relations with stakeholders and not only with their customers (Hang et al, 2022;Nadanyiova, 2021).…”

“…Performance can be seen as bad when there are problems in financial performance such as decreased income, low ROI, or losses. Good or bad performance can also be identified by looking at market share or the company's position in the industry, the level of consumer satisfaction, or employee welfare (Larios-Francia & Ferasso, 2023;Boubaker et al, 2023).…”

Algorithm for Application of a Basic Model for the Data Envelopment Analysis Method in Technical Systems

“…The latest developments in this direction are described in various scientific sources [41][42][43]. Recently, modifications of some models have also been presented to solve certain practical problems in various industries [44][45][46]. Despite the interest of certain scientific groups, the popularization of the method, publications, and new developments in this field, the DEA method is still in the formation stage.…”