Research on the recommendation framework of foreign enterprises from the perspective of multidimensional proximity

2025-06-21

AI Summary

This study addresses the low matching accuracy and imprecision in local governments’ foreign investment attraction efforts. We propose an intelligent foreign enterprise recommendation framework grounded in multidimensional proximity theory—encompassing industrial, market, geographical, institutional, and cognitive dimensions. For the first time, we systematically embed this theoretical framework into foreign investment decision-making, integrating heterogeneous data sources—including Wind/Osiris databases, policy text mining, the Herfindahl–Hirschman Index, Haversine distance metrics, and multi-criteria decision analysis (e.g., TOPSIS)—to quantitatively assess firm–region fit. Empirical validation in a Beijing district identified five high-fit foreign enterprises, markedly enhancing both recruitment efficiency and industrial alignment. Our contributions are threefold: theoretically, extending the applicability of proximity theory to international investment contexts; methodologically, establishing a computable, multi-source, heterogeneous-data-driven recommendation paradigm; and practically, delivering a replicable, evidence-based technical pathway for precision-oriented, science-informed investment promotion.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Search and Optimization: Local Search
• Intelligent Robots: Other Foundations and Applications

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

As global economic integration progresses, foreign-funded enterprises play an increasingly crucial role in fostering local economic growth and enhancing industrial development. However, there are not many researches to deal with this aspect in recent years. This study utilizes the multidimensional proximity theory to thoroughly examine the criteria for selecting high-quality foreign-funded companies that are likely to invest in and establish factories in accordance with local conditions during the investment attraction process.First, this study leverages databases such as Wind and Osiris, along with government policy documents, to investigate foreign-funded enterprises and establish a high-quality database. Second, using a two-step method, enterprises aligned with local industrial strategies are identified. Third, a detailed analysis is conducted on key metrics, including industry revenue, concentration (measured by the Herfindahl-Hirschman Index), and geographical distance (calculated using the Haversine formula). Finally, a multi-criteria decision analysis ranks the top five companies as the most suitable candidates for local investment, with the methodology validated through a case study in a district of Beijing.The example results show that the established framework helps local governments identify high-quality foreign-funded enterprises.

Problem

• Identifying high-quality foreign-funded enterprises for local investment
• Applying multidimensional proximity theory to investment criteria
• Ranking top companies using multi-criteria decision analysis

Innovation

• Uses multidimensional proximity theory for selection
• Combines Wind, Osiris databases with policy documents
• Applies multi-criteria decision analysis for ranking