A Snapshot Survey of Data Acquisition Forms in Multi-Attribute Decision-Making Studies

Introduction

With the rapid development of emerging technologies such as Internet technology, cloud computing, and the Internet of Things, the scale of data has grown explosively. The accumulation and storage of massive amounts of data provide huge opportunities and challenges for national decision-making and enterprise operations. This data contains a wealth of information in various fields that can help people better understand how the real world works and evolves. Big data dynamically reflect the development trend of various economic and social indicators, and reflects the effect of policy implementation in multiple dimensions and levels, making social management more refined and intelligent, and providing people with a more scientific and data-based decision-making thinking (Yaqoob et al., 2016; Zhang et al., 2024). MADM is an important part of decision science, which refers to the decision-making process that requires comprehensive consideration of multiple attribute factors in the decision-making process to achieve the optimal decision-making goal (Zanakis et al., 1998). Decision-making problems in real life are often affected by multiple attribute factors, and the influence of multiple attributes needs to be considered comprehensively (Zhang, 2008a; Wang et al., 2021). By comprehensively considering multiple attribute factors, we can evaluate the decision-making object more comprehensively, grasp the decision-making environment more accurately, and make more scientific and reasonable decisions, which is helpful to improve the accuracy and effectiveness of decision-making (Zhang & Yager, 2008b; Zhang et al., 2023).

Data collection is a crucial part of MADM research, as its quality and comprehensiveness directly affect the final decision outcome (Platts et al., 2002). At present, there are five main data collection methods commonly used in academia: