publications

2026

1. AOR

   Enhancing deep learning with data envelopment analysis: market-oriented recommendation system for non-fungible tokens

   Kexin Lin and Joe Zhu

   Annals of Operations Research, Mar 2026

   Abs DOI Bib HTML

   Non-Fungible Tokens (NFTs) are unique digital assets authenticated via blockchain and have emerged as transformative instruments for representing ownership across diverse sectors such as art, gaming, and decentralized finance. The rapid expansion of the NFT market, however, brings critical challenges into establishing purchase recommendation systems that reconciliate artistic appeal with financial value, extract insight from sparse and noisy interaction data, and match user preferences to market performance. To tackle these challenges and assist users in identifying valuable NFTs to purchase, this study develops a recommendation system that employs Data Envelopment Analysis (DEA) to assess NFTs’ ability to convert intrinsic characteristics into market success. The DEA model generates market performance scores and establishes reference relationships among NFTs. Using DEA results with NFTs’ intrinsic attributes, our new recommendation system DEA-Enhanced Transformer Network (DETN) is then built upon three complementary graphs to capture multifaceted relationships: a DEA-reference-based graph that links each NFT to its performance benchmarks, a DEA-performance-cluster-based graph that connects NFTs in the same DEA performance cluster, and a trait-similarity graph that groups NFTs with similar traits. A temporal Transformer uses these graph embeddings, DEA scores, and each user’s interaction history to produce NFT purchase recommendations that simultaneously align with user preferences and exhibit strong market performance. Applications on CryptoPunks dataset demonstrate that our proposed DETN outperforms existing recommendation systems such as collaborative filtering, graph-based models, and Transformer-based models. By integrating DEA with deep learning methods, DETN enhances recommendation precision and supports better informed decision-making processes.

   @article{Lin2026nft,
     title = {Enhancing deep learning with data envelopment analysis: market-oriented recommendation system for non-fungible tokens},
     author = {Lin, Kexin and Zhu, Joe},
     journal = {Annals of Operations Research},
     year = {2026},
     month = mar,
     day = {15},
     publisher = {Springer},
     doi = {10.1007/s10479-026-07129-6},
     keywords = {Data envelopment analysis; Deep learning; Non-fungible token; Recommendation system; Transformer},
     dimensions = {true},
   }

2024

1. EDS

   The impact of smart city construction on urban energy efficiency: evidence from China

   Jie Wu, Kexin Lin, and Jiasen Sun

   Environment, Development and Sustainability, Apr 2024

   Abs DOI Bib HTML

   Smart city construction (SCC) has emerged as an innovative approach to address the challenges of urbanization by reconciling economic development and energy utilization. This study employs the difference-in-differences method using data from 284 Chinese cities from 2005 to 2019 to investigate the impact of SCC on energy efficiency and the mediating role of technological innovation. This empirical analysis yields valuable conclusions. First, the SCC in China has significantly improved urban energy efficiency. Second, the driving effect of SCC on energy efficiency gradually increases over time and produces clustered shaded areas. Third, SCC improves urban energy efficiency through green, configuration, and infrastructure effects derived from technological innovation. Finally, SCC has a positive impact on moderately sized cities enriched with human, material, and financial capital.

   @article{Wu2024smart,
     title = {The impact of smart city construction on urban energy efficiency: evidence from China},
     author = {Wu, Jie and Lin, Kexin and Sun, Jiasen},
     journal = {Environment, Development and Sustainability},
     volume = {27},
     pages = {1--24},
     year = {2024},
     month = apr,
     day = {20},
     publisher = {Springer Netherlands},
     doi = {10.1007/s10668-024-04916-8},
     keywords = {Smart city construction; Energy efficiency; Technological innovation; Sustainable urban development},
     dimensions = {true},
   }

2023

1. JCP

   Improving urban energy efficiency: What role does the digital economy play?

   Jie Wu, Kexin Lin, and Jiasen Sun

   Journal of Cleaner Production, Dec 2023

   Abs DOI Bib HTML

   The digital economy (DEY) has emerged as a critical tool for promoting sustainable urban development through digital transformation. This study examines the effect of DEY on urban energy efficiency in China, employing data from 279 cities between 2011 and 2019. The estimation results reveal a U-shaped relationship between DEY and urban energy efficiency. Specifically, in its initial development stage, DEY reduces energy efficiency, but as it matures, DEY ultimately leads to an improvement in energy efficiency. Moreover, the dynamic threshold model indicates that the U-shaped effects of DEY on energy efficiency depend on industrial structure upgrading, greening urban areas, and the financial support of governments. The results of the Spatial Durbin model confirm that DEY has a spatial spillover effect on urban energy efficiency. Finally, the results of the panel vector autoregression model illustrate a long-term bidirectional causality between DEY and urban energy efficiency.

   @article{wu2023digital,
     title = {Improving urban energy efficiency: What role does the digital economy play?},
     author = {Wu, Jie and Lin, Kexin and Sun, Jiasen},
     journal = {Journal of Cleaner Production},
     volume = {418},
     pages = {138104},
     year = {2023},
     month = dec,
     issn = {0959-6526},
     doi = {10.1016/j.jclepro.2023.138104},
     keywords = {Digital economy; Energy efficiency; Nonlinear effect; Spatial spillover effect},
     dimensions = {true},
   }

2. CIE

   Pressure or motivation? The effects of low-carbon city pilot policy on China’s smart manufacturing

   Jie Wu, Kexin Lin, and Jiasen Sun

   Computers & Industrial Engineering, Sep 2023

   Abs DOI Bib HTML

   In the pursuit of carbon neutrality goals, the manufacturing industry is compelled to adopt smart manufacturing practices to comply with environmental regulations. Smart manufacturing, characterized by the integration of Industry 4.0 technologies, offers the potential to reduce energy consumption, emissions, and enhance productivity. This study investigates the influence of the low-carbon city pilot (LCP) policy on smart manufacturing and its underlying mechanisms. Leveraging data spanning 2003 to 2020 from China’s A-share-listed manufacturing companies, several key findings emerge. First, the LCP policy exerts a significant positive impact on the smart manufacturing capabilities of companies operating within LCPs, and this impact strengthens over time. Second, a company’s innovation and effective resource allocation act as active mediators in the correlation between the LCP policy and smart manufacturing, whereas government intervention plays a positive moderating role. Lastly, state-owned manufacturing companies exhibit a lesser positive effect from the LCP policy compared with their non-state-owned counterparts.

   @article{wu2023pressure,
     title = {Pressure or motivation? The effects of low-carbon city pilot policy on China's smart manufacturing},
     author = {Wu, Jie and Lin, Kexin and Sun, Jiasen},
     journal = {Computers \& Industrial Engineering},
     volume = {183},
     pages = {109512},
     year = {2023},
     month = sep,
     issn = {0360-8352},
     doi = {10.1016/j.cie.2023.109512},
     keywords = {Smart manufacturing; Low-carbon city; Innovation; Resource allocation; Difference-in-differences},
     dimensions = {true},
   }