About

Professor Zheng Sun joined the Paul Merage School of Business as an Assistant Professor of Finance in July 2007. She was promoted to Associate Professor in July 2015 and to Professor in July 2023. She teaches core courses in the Master of Finance (MFIN) curriculum and currently serves as the faculty director of the MFIN program. Her primary research interests are empirical investments, institutional investors, mutual funds, hedge funds, bonds, and loans. Professor Sun has published in several top finance and economics journals, including the Journal of Financial Economics, Review of Financial Studies, Journal of Financial and Quantitative Analysis, Journal of Monetary Economics, and SIAM Journal on Financial Mathematics. She has presented her research at major finance and economic conferences such as the American Finance Association meetings, Western Finance Association meetings, NBER, and European Finance Association meetings, and has been invited to present at regulatory agencies including the SEC, Federal Reserve Board, Federal Reserve New York, and FINRA.

Research topics

• Artificial Intelligence
• Computer Science
• Data Mining
• Economics
• Monetary economics
• Financial system
• Finance
• Geography
• Remote sensing
• Business
• Cartography
• Financial economics

Selected publications

• Loss Characteristics and Quantitative Restoration Model of Light Hydrocarbons in Shale Oil from the Chang 73 Submember of the Ordos Basin

  Processes · 2026-04-22

  articleOpen access1st authorCorresponding

  Light hydrocarbons in shale oil readily volatilize during conventional coring, surface handling, storage, and laboratory preparation. The resulting evaporative loss causes systematic underestimation of Rock-Eval S1 peak (free hydrocarbons measured by programmed pyrolysis), which can bias oil-bearing evaluation, sweet-spot delineation, and resource assessment. Here we investigate Chang 73 lacustrine shale oil in the Ordos Basin (China) using frozen cores recovered by pressure-retained coring from four wells. Time-series Rock-Eval pyrolysis and thermal desorption–gas chromatography (TD–GC) were used to quantify the magnitude, temporal evolution, and practical equilibrium time of light-hydrocarbon loss and to establish a practical restoration model. S1 decreases with storage time and exhibits a clear two-stage behavior. Shale shows a rapid-loss stage during 0–90 days, followed by a practical equilibrium stage after 90 days (S1 change less than 5%). Sandstone interbeds lose light hydrocarbons faster and more completely, reaching practical equilibrium after 60 days. TD–GC indicates that the lost fraction is dominated by n-alkane components lighter than C13, with gaseous hydrocarbons showing the greatest depletion; medium and heavy fractions decrease modestly. Loss is coupled with progressive desorption from kerogen and clays, leading to enrichment of heavier components in the residual free hydrocarbons and a shift of the modal carbon number toward higher values. At the shale equilibrium time, total organic carbon (TOC) and vitrinite reflectance (Ro) jointly control the restoration factor K. We propose a two-parameter restoration model: K = (0.4024·ln (TOC) + 0.821)·(0.652·Ro + 0.4292). Applying the model to more than 50 conventionally cored wells reveals that the Qingyang–Zhengning area in the southwestern basin is the principal enrichment zone of original free hydrocarbons, followed by the Jiyuan area in the north and the Huachi area in the central basin, whereas the eastern basin is relatively depleted. The workflow provides a robust and transferable approach for correcting S1 and improving shale-oil evaluation in lacustrine systems.

  PublisherOA PDFDOI

• Generative AI and Asset Management

  Review of Financial Studies · 2026-05-11

  article

  Abstract Using a novel measure of investment companies’ reliance on generative artificial intelligence (GenAI), we document a sharp increase in GenAI usage by hedge funds after ChatGPT’s 2022 launch. A difference-in-differences test shows that hedge funds adopting GenAI earn 2-4% higher annualized abnormal returns than nonadopters, while non-hedge funds do not benefit. The outperformance originates from funds’ AI talent and ChatGPT’s strength in analyzing firm-specific information. We conduct a new survey of fund managers’ GenAI usage to provide direct validation of our measure and offer additional new insights on how managers adopt GenAI tools in their practice. (JEL C81, G11, G14, G23)

  PublisherDOI

• Limits to Diversification: Passive Investing and Market Risk 

  SSRN Electronic Journal · 2024-01-01

  preprintOpen access
  PublisherDOI

• FCIL-MSN: A Federated Class-Incremental Learning Method for Multisatellite Networks

  IEEE Transactions on Geoscience and Remote Sensing · 2024-01-01 · 8 citations

  article

  Multi-satellite networks have become the prevalent mode for remote sensing intelligent interpretation, with the onboard models requiring class-incremental updates to accommodate the new categories emerging in evolving data and tasks. Traditional model updating methods, which involve uploading models separately after ground-based updating, are inefficient due to limited uplink bandwidth and cumbersome ground update processes while underutilizing potential computing resources on satellites. To address the aforementioned problems, this paper innovatively proposes a collaborative in-orbit incremental update method termed FCIL-MSN, which leverages observational information and computing resources from multi-satellite networks. Firstly, FCIL-MSN achieves collaborative onboard model updates by introducing federated class-incremental learning into multi-satellite networks. Secondly, a bias calibration-guided relationship distillation module constructs a pseudo-feature set by collaborative multi-satellite networks, which alleviates the model bias caused by class imbalance from a global perspective, thereby enhancing model performance. Finally, a gradient information aggregation module is designed to facilitate the exclusion of unfavorable local updates by measuring the contribution of each terminal, thereby accelerating the convergence while obtaining the global model. We conduct extensive experiments on two datasets for scene classification tasks to verify the effectiveness of our proposed method. Experimental results demonstrate that FCIL-MSN outperforms existing general FCIL methods, improving average classification accuracy by 1.45% and decreasing the performance degradation rate by 6.40%.

  PublisherDOI

• Intangible heritage restoration of damaged tomb murals through augmented reality technology: A case study of Zhao Yigong Tomb murals in Tang Dynasty of China

  Journal of Cultural Heritage · 2024-08-31 · 16 citations

  article1st authorCorresponding
  PublisherDOI

• The start matters: time-varying investor demand, hedge fund inceptions, and performance

  European Finance Review · 2023-09-13 · 4 citations

  articleOpen access

  Abstract We examine whether time-varying investor demand affects hedge fund companies’ decision to start new funds. We find significantly more fund inceptions in hot markets than in cold markets. Funds opened in hot markets exhibit weaker long-term performance, shorter survival time, and greater fraud risk. Investor clientele also varies with market conditions. Investors in hot markets appear to be less sophisticated, which may provide opportunities for more low-quality funds to enter the industry. Overall, inceptions due to high investor demand are not in the best interest of investors.

  PublisherOA PDFDOI

• Sedimentary sequence and evolutionary characteristics of the rift system of Neoproterozoic Nanhua System and Doushantuo Formation: A case study from the northeastern margin of Sichuan Basin

  Geological Journal · 2023-10-26 · 1 citations

  articleOpen accessCorresponding

  Neoproterozoic strata are widely developed in the Upper Yangtze region of South China, among which the Sinian Dengying Formation has been discovered with numerous large gas fields in the Sichuan Basin, and hence they have become an essential domain for natural gas exploration and development. The early‐to‐middle Neoproterozoic Nanhua System and Doushantuo Formation are characterized by rifting deposits in the northeastern margin of Sichuan Basin, but their depositional succession and sequence architectures are still unclear, which has largely restricted our understanding of the resource potential of these strata. In this paper, based on the outcrops of the Neoproterozoic Nanhua System and Doushantuo Formation in the northeastern margin of Sichuan Basin, we describe the stratigraphic distribution and sedimentary evolutionary characteristics, and establish the regional stratigraphic framework, sedimentary cycle and evolutionary sequence of the Nanhua System and Doushantuo Formation. The results show that the lithology of the Nanhua System and Doushantuo Formation is primarily composed of conglomerate, conglomeratic sandstone, medium‐fine sandstone, siltstone, mudstone, shale and tillite; a variety of sedimentary facies including alluvial fan, river, delta, coastal shore, shelf, basin and tillite were developed; five third‐order sequences could be identified, representing multiple cycles of marine transgression and regression. The climate during the deposition of the Nanhua System and Doushantuo Formation underwent from a warm and humid pre‐glacial period through cold and arid multiple glacial periods to a warm and humid interglacial period, which consequently formed a sedimentary sequence of alluvial fan and fluvial delta to tillite during the early period, shelf basin to tillite during the middle period and slope basin to delta facies during the late period. In terms of a plan view, the depositional pattern is composed of alluvial fans and deltas at the proximal part of the rift, deep‐water shelf to slope at the middle part of the rift and slope to basin facies at the central part of the rift. Finally, we propose that large‐scale distribution of high‐quality source rocks developed in the interglacial Datangpo and Doushantuo formations, while fluvial‐deltaic reservoirs occurred in the Gucheng, Nantuo and Doushantuo formations, thus showing favourable resource potential and exploration prospects within the Sichuan Basin.

  PublisherOA PDFDOI

• Author response for "Sedimentary sequence and evolutionary characteristics of the rift system of Neoproterozoic Nanhua System and Doushantuo Formation: A case study from the northeastern margin of Sichuan Basin"

  2023-09-21

  peer-review
  PublisherDOI

• Capitalizing on Retail Investor Sentiment: Evidence from FinTech ETFs

  SSRN Electronic Journal · 2023-01-01

  articleOpen accessSenior author
  PublisherDOI

• Urban Building Classification (UBC) V2—A Benchmark for Global Building Detection and Fine-Grained Classification From Satellite Imagery

  IEEE Transactions on Geoscience and Remote Sensing · 2023 · 20 citations

  • Computer Science
  • Computer Science
  • Data Mining

  Datasets play a key role in developing superior building detection approaches. However, most of the previous work focuses on accurate building masks and scale expansion, while the categories are always missing, which hinders the further analysis of urban development and cultures. Therefore, we propose a benchmark for building detection and fine-grained classification from very high-resolution (VHR) satellite imagery. An extensive annotation is performed for about 0.5 million building instances with 12 fine-grained roof types and individual polygons. The annotation of building functions of two cities in the previous version (UBCv1) [1] is also integrated. To ensure the building variety, it consists of VHR optical images of 20 unique cities worldwide with various landforms and styles of architecture. Its variety and fine-grained categories pose great challenges and meanwhile provide a foundation for the building extraction and fine-grained classification on a global scale. Besides, 17 cities are provided with finely aligned Synthetic Aperture Radar (SAR) images, which can be employed for the development and evaluation of approaches optionally based on optical, SAR, or multi-modal images. Significantly, the proposed benchmark is used as the base of the 2023 IEEE GRSS Data Fusion Contest [2]. The dataset and codes of the baseline methods are available at: https://github.com/AICyberTeam/UBC-dataset/tree/UBCv2.

  PublisherDOI

Frequent coauthors

• Ashley Wang

  158 shared

• Zheng Lu

  Sichuan University

  146 shared

• Mohammad A. S. Masoum

  Utah Valley University

  24 shared

• Taher Deemyad

  Idaho State University

  16 shared

• John Edwards

  Utah State University

  16 shared

• Cherif Seibi

  Utah Valley University

  16 shared

• Guthrie Utah

  Utah State University

  16 shared

• Bradley M. Whitaker

  Montana State University

  16 shared