About

Dr. Shijie Deng is an Associate Professor in the H. Milton Stewart School of Industrial and Systems Engineering at Georgia Tech. His research centers on financial engineering, stochastic optimization, data-driven decision-making, and risk analysis in complex systems. His work develops robust and efficient methodologies for financial asset pricing and managing uncertainty in operations and supply chains. His expertise includes economic decision analysis, financial asset pricing, real options valuation, energy markets, electricity transmission pricing, auction design, and risk management in supply chains. Dr. Deng has consulted with several private and public companies on issues related to pricing, risk management, and asset valuation in energy and finance industries. His research spans asset pricing, portfolio optimization, energy storage valuation, energy risk management, electricity market design, and statistical learning with applications in energy and healthcare. He emphasizes foundational concepts in quantitative finance, data analytics, stochastic modeling, and decision analysis under uncertainty, integrating mathematical modeling and computational methods to enhance students' analytical and problem-solving skills. His contributions have been recognized with awards such as the NSF CAREER Award in 2002.

Research topics

• Computer Science
• Econometrics
• Financial economics
• Economics
• Artificial Intelligence
• Physics
• Marketing
• Mathematics
• Mathematical economics
• Business
• Statistics
• Geography

Selected publications

• Advanced microfluidic systems with integrated microstructures for enhanced exosome isolation and analysis

  TrAC Trends in Analytical Chemistry · 2026-04-24

  articleCorresponding
  PublisherDOI

• Deep Domain Decomposition Method for Solving the Variational Inequality Problems

  arXiv (Cornell University) · 2026-03-12

  preprintOpen access

  By integrating physics-informed neural network (PINN) techniques with domain decomposition method, a deep domain decomposition method is presented for solving elliptic variational inequality problems. Based on the Ritz variation method, the elliptic variational inequality problem is firstly reformulated as an optimization problem, and then the subproblem in each subdomain is solved by using the Ritz-PINN method, which the parameters in the network are updated by the Adam optimizer, and the residual-adaptive training by introducing a residual-adaptive dataset update strategy to gradually guide the model to learn more complex regions. Additionally, the impact of overlapping regions on the performance of the new algorithm is explored. Numerical results demonstrate the effectiveness of the proposed algorithm, the mean square error can be reached 1.0e-07, and the number of iterations is independent of grid length h under uniform overlap conditions.

  PublisherDOI

• Deep Domain Decomposition Method for Solving the Variational Inequality Problems

  Journal of big data and computing. · 2025-03-01

  articleOpen access

  By integrating physics-informed neural network (PINN) techniques with domain decomposition method, a deep domain decomposition method is presented for solving elliptic variational inequality problems. Based on the Ritz variation method, the elliptic variational inequality problem is firstly reformulated as an optimization problem, and then the subproblem in each subdomain is solved by using the Ritz-PINN method, which the parameters in the network are updated by the Adam optimizer, and the residual-adaptive training by introducing a residual-adaptive dataset update strategy to gradually guide the model to learn more complex regions. Additionally, the impact of overlapping regions on the performance of the new algorithm is explored. Numerical results demonstrate the effectiveness of the proposed algorithm, the mean square error can be reached O (1.0e-07), and the number of iterations is independent of grid length h under uniform overlap conditions.

  PublisherOA PDFDOI

• 26‐2: Research on Image Quality Evaluation Standard for LCD Display

  SID Symposium Digest of Technical Papers · 2025-06-01

  article

  To meet the extreme cost reduction needs of the TFT‐LCD display market, more and more extreme architecture displays and high refresh rate displays with competitive prices have been developed. Displays such as extreme architecture of Triple‐gate and Dual‐gate are prone to image quality problems related to color bias and poor color uniformity due to charging reasons. This paper proposes a charging image quality evaluation standard, which can be used to objectively evaluate the image quality of displays such as Triple‐gate and Dual‐gate, so as to get rid of the shortcomings of image quality evaluation limited by subjective human factors and low evaluation efficiency.

  PublisherDOI

• Marketing Strategies for Tourism along the Yunnan Section of the China-Laos Railway

  Technium Social Sciences Journal · 2025-07-09 · 1 citations

  articleOpen access1st authorCorresponding

  As a core corridor of the Pan-Asian Railway, the full operation of the China-Laos Railway has restructured the logistics network of the Indochina Peninsula and reshaped Yunnan’s tourism economic landscape, driving the integrated development of cross-border cultural tourism. The railway has significantly enhanced transportation accessibility along Yunnan’s route, stimulated short-distance tourism demand, and spurred development in traditionally non-hotspot regions, while facing challenges such as insufficient resource integration and ambiguous branding. This study employs qualitative research methods to examine the current tourism conditions and the optimization of marketing strategies for cities along the Yunnan section of the China-Laos Railway. Findings reveal that the railway has profoundly restructured Yunnan’s tourism economic landscape, forming an integrated tourism economic belt that combines natural ecology, cultural heritage, and cross-border resources. Cities along the route, including Kunming, Yuxi, Pu’er, and Xishuangbanna, have experienced varying degrees of tourism development opportunities. The proposed 4P marketing strategies include: a product strategy centered on "high-speed rail + culture" thematic routes; a pricing strategy balancing supply-demand dynamics through dynamic pricing and bundled offers; a channel strategy emphasizing dual-channel coordination between digital platforms and physical service outlets; and a promotion strategy focused on content marketing and precision targeting. These strategies aim to transform the China-Laos Railway from a transportation artery into a "cross-regional cultural tourism economic corridor," injecting new momentum into regional sustainable development.

  PublisherDOI

• Three wave solution and lump-type solution to a (3+1)-dimensional Date-Jimbo-Kashiwara-Miwa equation with some variable coefficients in inhomogeneous media

  Networks and Heterogeneous Media · 2025-01-01 · 2 citations

  articleOpen access

  This paper focuses on the new (3+1)-dimensional Date-Jimbo-Kashiwara-Miwa (DJKM) equation with some variable coefficients and derives its new analytical solutions. Based on the (2+1)-dimensional DJKM equation, this equation adds an additional spatial dimension (z) and introduces time-dependent coefficients. Therefore, it is more suitable for describing dynamic wave behaviors in inhomogeneous media. Firstly, by virtue of the Hirota method, we derive the Hirota bilinear form of the equation. Secondly, based on the bilinear form, we present three types of solutions, including the three wave solution and lump-type solution. Finally, by choosing appropriate parameters, we plot some graphs to intuitively display the physical characteristics of these solutions.

  PublisherDOI

• Clean Energy Premium and Cross-section of Stock Returns

  SSRN Electronic Journal · 2024-01-01 · 1 citations

  articleOpen accessSenior author
  PublisherDOI

• Long-range dependence and asset return anomaly

  Annals of Operations Research · 2024-11-20 · 1 citations

  articleSenior authorCorresponding
  PublisherDOI

• P‐126: Research on adaptive voltage regulation algorithm on TFT‐LCD

  SID Symposium Digest of Technical Papers · 2024-06-01

  article1st authorCorresponding

  In the current global promotion of environmental protection and low‐carbon, in order to further reduce the power consumption of TFT‐LCD, this paper proposes an algorithm based on image detection for adaptive adjustment of panel voltage, and tests the algorithm on the monitor. The test results shows that the algorithm can achieve power reduction while maintaining image quality.

  PublisherDOI

• Optimal stop-loss rules in markets with long-range dependence

  Quantitative Finance · 2024-02-01 · 1 citations

  articleSenior authorCorresponding

  Stop-loss is a common risk management tool for limiting risks and improving trading strategy performance. The effectiveness of stop-loss depends critically on asset price characteristics. This study is the first to analyze stop-loss strategy incorporating long-range dependence of asset prices through a fractional Brownian motion-based market model. It is shown that stop-loss strategy yields a positive return premium over the buy-and-hold return when asset price exhibits long-range dependence. The efficacy of stop-loss strategies and the determining criterions are investigated through both theoretical analysis and simulation studies. The performance of a stop-loss rule depends on the Hurst parameter, mean and volatility of the asset returns. The optimal stop-loss threshold model in a chosen strategy class is fitted by polynomial regression. Empirical analysis demonstrates that the class-specific optimal rules outperform stop-loss rules under alternative asset return-generating models.

  PublisherDOI

Recent grants

• CAREER: Integrated Engineering and Economic Modeling of Problems in Deregulated Electricity Networks

  NSF · $375k · 2002–2008

Frequent coauthors

• Shmuel S. Oren

  University of California, Berkeley

  8 shared

• D. Dauvergne

  Laboratoire de Physique Subatomique et de Cosmologie

  8 shared

• H. Mathez

  Centre National de la Recherche Scientifique

  7 shared

• Yun Xiang

  Southwestern University of Finance and Economics

  7 shared

• C. Ray

  Colorado School of Mines

  6 shared

• J. Krimmer

  6 shared

• Min Kyu Sim

  Seoul National University of Science and Technology

  6 shared

• V. Reithinger

  Institute of Nuclear Physics of Lyon

  6 shared

Awards & honors

• NSF CAREER Award, National Science Foundation, 2002