About

Michael Watson is an Associate Professor of Instruction at Northwestern University, affiliated with the Industrial Engineering and Management Sciences department. He has been teaching at Northwestern as an adjunct since 1999 and joined the faculty full-time in 2023. His career has been centered on implementing ideas from industrial engineering, management, and machine learning for Fortune 500 companies through software, consulting, and start-up ventures. Watson co-founded and served as CEO of Opex Analytics, an AI company specializing in data science and optimization, which was sold to LLamasoft and subsequently to Coupa. Prior to his full-time academic appointment, he worked extensively in industry, applying his expertise in supply chain analytics, network design, and operations optimization. His research interests include AI frameworks and business applications, supply chain analytics with a focus on network design, optimization, and operations. Watson has authored books on supply chain network design and managerial analytics and maintains a blog titled 'Mike Talks AI.' He is committed to bringing his industry experience into the classroom to benefit students, offering insights into careers in software, consulting, and Fortune 500 companies, as well as start-ups. Additionally, he works to maintain strong connections between Northwestern's industrial engineering programs and industry partners, contributing to projects that optimize hospital scheduling, court system biases, logistics networks, and wind turbine power prediction.

Research topics

• Computer Science
• Artificial Intelligence
• Physics
• Mathematical analysis
• Chemistry
• Statistics
• Econometrics
• Mathematics
• Biochemistry

Selected publications

• Forecasting Related Time Series

  Journal of Applied Econometrics · 2026-03-11

  articleOpen accessSenior authorCorresponding

  ABSTRACT A collection of time series are “related” if they follow similar stochastic processes and/or they are statistically dependent. This paper proposes a related time series (RTS) forecasting model that exploits these relationships. The model's foundation is a set of univariate Gaussian autoregressions, one for each series, which are then augmented to incorporate stochastic volatility, heavy‐tailed innovations, additive outliers, time‐varying parameters and common factors. The model is estimated and forecasts are computed using Bayesian methods with hierarchical priors that pool information across series. Computationally efficient MCMC methods are proposed. The RTS model is applied to three datasets and yields encouraging pseudo‐out‐of‐sample forecasting results.

  PublisherDOI

• Comment

  NBER Macroeconomics Annual · 2026-01-01

  article1st authorCorresponding
  PublisherDOI

• The Past and Future of U.S. Structural Change: Compositional Accounting and Forecasting

  SSRN Electronic Journal · 2025-01-01

  articleOpen accessSenior author
  PublisherDOI

• Testing Coefficient Variability in Spatial Regression

  SSRN Electronic Journal · 2025-01-01

  preprintOpen accessSenior author
  PublisherDOI

• The Past and Future of U.S. Structural Change: Compositional Accounting and Forecasting

  Federal Reserve Bank of San Francisco, Working Paper Series · 2025-10-14

  articleOpen accessSenior author

  We explore the evolving significance of different production sectors within the U.S. economy since World War II and provide methods for estimating and forecasting these shifts. Using a compositional accounting approach, we find that the well-documented transition from goods to services is primarily driven by two compositional changes: 1) the rise of Intellectual Property Products (IPP) as an input producer, replacing Durable Goods almost one-for-one in terms of input shares in virtually all sectors; and 2) a shift in consumer spending from Nondurable Goods to Services. A structural model replicating these shifts reveals that the rise of IPP at the expense of Durable Goods is largely explained by increases in the efficiency of IPP inputs used in production: input-biased technical change. Trend variations in sectoral total factor productivity, and their attendant effects on relative prices and income, are the main driver of evolving consumption patterns. Both reduced-form and structural forecasts project these trends to continue over the next two decades, albeit at lower rates, indicating a slower pace of structural change.

  PublisherOA PDFDOI

• Time Varying Extremes

  The Review of Economics and Statistics · 2024-10-29 · 4 citations

  articleSenior author

  Abstract Standard extreme value theory implies that the distribution of the largest observations of a large cross section is well approximated by a parametric model, governed by a location, scale and shape parameter. The extremes of a panel of independent cross sections are all governed by the same parameters as long as the underlying distribution as well as the size of the cross sections are time invariant. We derive inference about these parameters, and tests of the null hypothesis of time invariance, under asymptotics that do not require the number of extremes or the number of time periods to increase. We further apply Hamiltonian Monte Carlo techniques to estimate the path of time-varying parameters. We illustrate the approach in four examples of U.S. data: damages from weather-related disasters, financial returns, city sizes and firm sizes.

  PublisherDOI

• Spatial Unit Roots and Spurious Regression

  Econometrica · 2024-01-01 · 21 citations

  articleSenior author

  This paper proposes a model for, and investigates the consequences of, strong spatial dependence in economic variables. Our findings echo those of the corresponding “unit root” time series literature: Spatial unit root processes induce spuriously significant regression results, even with clustered standard errors or spatial HAC corrections. We develop large‐sample valid unit root and stationarity tests that can detect such strong spatial dependence. Finally, we use simulations to study strategies for valid inference in regressions with persistent spatial data, such as spatial analogues of first‐differencing transformations. Regressions from Chetty, Hendren, Kline, and Saez (2014) are used to illustrate the issues and methods.

  PublisherDOI

• Comment

  NBER Macroeconomics Annual · 2023-05-01

  article1st authorCorresponding
  PublisherDOI

• Aggregate Implications of Changing Sectoral Trends

  Journal of Political Economy · 2022-05-09 · 32 citations

  articleSenior author

  We describe how capital accumulation and the network structure of US production interact to amplify the effects of sectoral trend growth rates in total factor productivity and labor on trend GDP (gross domestic product) growth. We derive expressions that conveniently summarize this long-run amplification effect by way of sectoral multipliers. We estimate that sector-specific factors have historically accounted for approximately three-fourths of long-run changes in GDP growth. Trend GDP growth fell by nearly 3 percentage points over the postwar period, with especially significant contributions from the Construction sector in 1950–80 and the Durable Goods sector in 2000–2018. No sector has contributed any steady significant increase to the trend growth rate of GDP in the past 70 years.

  PublisherDOI

• Spatial Correlation Robust Inference in Linear Regression and Panel Models

  Journal of Business and Economic Statistics · 2022-09-23 · 12 citations

  articleOpen accessSenior authorCorresponding

  We consider inference about a scalar coefficient in a linear regression with spatially correlated errors. Recent suggestions for more robust inference require stationarity of both regressors and dependent variables for their large sample validity. This rules out many empirically relevant applications, such as difference-in-difference designs. We develop a robustified version of the SCPC method of Müller and Watson (2022a) that addresses this challenge. We find that the method has good size properties in a wide range of Monte Carlo designs that are calibrated to real world applications, both in a pure cross sectional setting, but also for spatially correlated panel data. We provide numerically efficient methods for computing the associated spatial-correlation robust test statistics, critical values and confidence intervals.

  PublisherOA PDFDOI

Frequent coauthors

• James H. Stock

  Harvard University

  315 shared

• John G. Fernald

  University of Groningen

  67 shared

• Robert E. Hall

  67 shared

• Ricardo Reis

  52 shared

• Robert G. King

  Boston University

  34 shared

• Ulrich K. Müller

  24 shared

• Andrew T. Foerster

  20 shared

• Pierre-Daniel G. Sarte

  Federal Reserve Bank of Richmond

  17 shared