战略管理研究中的机器学习:研究述评与展望

Machine Learning in Strategic Management Research: A Review and Prospects

吴建祖,郑朝杰

2025 第 47 卷 第 03 期 页码 119-136

DOI: 10.16538/j.cnki.fem.20240409.101

PDF全文下载 HTML全文

摘要

机器学习为战略管理研究带来了新的方法论和机遇。本文基于1999—2022年间发表在国际顶尖战略管理期刊的27篇文献,系统梳理了机器学习在战略管理研究中的四个应用:变量测量、特征选择、模型估计和因果推断。本文分析了每个维度的代表性文献,详述了其所用机器学习算法的原理和应用,并探讨了未来的研究方向。研究发现,自然语言处理技术和分类算法不仅提高了变量测量精度,也增强了特征选择方面的能力,从而加深了研究者对战略管理研究对象的理解。同时,随机森林、支持向量机等机器学习算法,在提升模型估计的稳健性方面有显著效果。另外,双重套索、双重机器学习和广义随机森林等方法,为因果关系推断提供了技术支持。本文旨在为运用机器学习技术深化战略管理研究提供指导和建议,同时为战略管理领域的未来研究奠定了方法论基础。

Machine learning brings new methodologies and opportunities to strategic management research. Based on 27 papers published in top international strategic management journals between 1999 and 2022, this paper systematically summarizes four dimensions of machine learning applications in strategic management research: variable measurement, feature selection, model estimation, and causal inference. This paper analyzes representative literature on each dimension, describes the machine learning algorithms, principles, and steps they employ, and explores future directions for strategic management scholars to utilize machine learning for empirical research. It is found that natural language processing techniques and classification algorithm not only improve the accuracy of quantifying key variables, but also enhance the capabilities of variable selection, topic extraction, and pattern recognition, thus deepening the understanding of the object of strategic management research. In addition, machine learning algorithms, such as random forests and support vector machine, have significant application value in improving the validity and robustness of model estimation. Methods such as double lasso, double machine learning, and generalized random forest provide strong technical support for causal inferences. The purpose of this paper is to provide guidance and suggestions for using machine learning techniques to deepen strategic management research, as well as laying a theoretical and methodological foundation for future research and applications in the field of strategic management.

参考文献

1 陈冬梅, 王俐珍, 陈安霓. 数字化与战略管理理论——回顾、挑战与展望[J]. 管理世界, 2020, 36(5): 220-236. DOI:10.3969/j.issn.1002-5502.2020.05.016
2 洪永淼, 汪寿阳. 大数据、机器学习与统计学: 挑战与机遇[J]. 计量经济学报, 2021, 1(1): 17-35. DOI:10.12012/T03-19
4 Aceves, P, Evans, J A. Mobilizing Conceptual Spaces: How Word Embedding Models Can Inform Measurement and Theory Within Organization Science[J]. Organization Science, 2023, https://doi.org/10.1287/orsc.2023.1686.
5 Alley, M, Biggs, M, Hariss, R, et al. Pricing for Heterogeneous Products: Analytics for Ticket Reselling[J]. Manufacturing & Service Operations Management, 2022, 25(2): 409-426.
6 Athey, S. The Impact of Machine Learning on Economics[M]. The Economics of Artificial Intelligence. University of Chicago Press, 2019.
7 Athey, S, Imbens, G W. Machine Learning Methods That Economists Should Know About[J]. Annual Review of Economics, 2019, 11(1): 685-725. DOI:10.1146/annurev-economics-080217-053433
8 Athey, S, Tibshirani, J, Wager, S. Generalized random forests[J]. The Annals of Statistics, 2019, 47(2): 1148-1178.
9 Belloni, A, Chernozhukov, V, Hansen, C. Inference on Treatment Effects after Selection among High-Dimensional Controls[J]. The Review of Economic Studies, 2014, 81(2): 608-650. DOI:10.1093/restud/rdt044
10 Bellstam, G, Bhagat, S, Cookson, J A. A Text-Based Analysis of Corporate Innovation[J]. Management Science, 2021, 67(7): 4004-4031. DOI:10.1287/mnsc.2020.3682
11 Bhatia, S, Olivola, C Y, Bhatia, N, et al. Predicting leadership perception with large-scale natural language data[J]. The Leadership Quarterly, 2022, 33(5): 101535. DOI:10.1016/j.leaqua.2021.101535
12 Blei, D, NG, A, Jordan, M. Latent Dirichlet Allocation[J]. Journal of Machine Learning Research, 2003, 14: 601-608.
13 Boudt, K, Thewissen, J. Jockeying for Position in CEO Letters: Impression Management and Senti ment Analytics[J]. Financial Management, 2019, 48(1): 77-115. DOI:10.1111/fima.12219
14 Breiman, L, Friedman, J H, Olshen, R A. et al. Classification and Regression Trees[J]. Biometrics, 1984, https://doi.org/10.1201/9781315139470.
15 Chen, Y, Iyengar, R, Iyengar, G. Modeling Multimodal Continuous Heterogeneity in Conjoint Analysis - A Sparse Learning Approach[J]. Marketing Science, 2017, 36(1): 140-156. DOI:10.1287/mksc.2016.0992
16 Chernozhukov, V, Chetverikov, D, Demirer, M, et al. Double machine learning for treatment and causal parameters, 2016, https://doi.org/10.48550/arXiv.1608.00060.
17 Chernozhukov, V, Demirer, M, Duflo, E, et al. Generic Machine Learning Inference on Heterogeneous Treatment Effects in Randomized Experiments, with an Application to Immunization in India[R]. Working Paper, 2018.
18 Choi, J, Menon, A, Tabakovic, H. Using machine learning to revisit the diversification–performance relationship[J]. Strategic Management Journal, 2021, 42(9): 1632-1661. DOI:10.1002/smj.3317
19 Chou, Y-C, Chuang, H H C, Chou, P-F, et al. Supervised machine learning for theory building and testing: Opportunities in operations management[J]. Journal of Operations Management, 2023, 69(4): 643-675. DOI:10.1002/joom.1228
20 Choudhury, P, Allen, R, Endres, M. Machine learning for pattern discovery in management research[J]. Strategic Management Journal, 2021, a,42(1): 30-57.
21 Choudhury, P, Foroughi, C, Larson, B. Work-from-anywhere: The productivity effects of geographic flexibility[J]. Strategic Management Journal, 2021, b,42(4): 655-683.
22 Choudhury, P, Kim, D Y. The ethnic migrant inventor effect: Codification and recombination of knowledge across borders[J]. Strategic Management Journal, 2019, 40(2): 203-229. DOI:10.1002/smj.2977
23 Choudhury, P, Wang, D, Carlson, N, et al. Machine Learning Approaches to Facial and Text Analysis: Discovering CEO Oral Communication Styles[J]. Strategic Management Journal, 2019, 40(11): 1705-1732. DOI:10.1002/smj.3067
24 Ciocan, D F & Misic, V V. Interpretable Optimal Stopping[J]. Management Science, 2022, 68(3): 1616-1638. DOI:10.1287/mnsc.2020.3592
25 Cortes, C, Vapnik, V. Support-vector networks[J]. Machine Learning, 1995, 20: 273-297.
26 Cover, T, Hart, P. Nearest neighbor pattern classification[J]. IEEE Transactions on Information Theory, 1967, 13(1): 21-27. DOI:10.1109/TIT.1967.1053964
27 Ding, K, Lev, B, Peng, X, et al. Machine learning improves accounting estimates: evidence from insurance payments[J]. Review of Accounting Studies, 2020, 25(3): 1098-1134. DOI:10.1007/s11142-020-09546-9
28 Domingos, P, Pazzani, M. On the Optimality of the Simple Bayesian Classifier under Zero-One Loss[J]. Machine Learning, 1997, 29(2): 103-130.
29 Dutta, H A Consensus Algorithm for Linear Support Vector Machines[J]. Management Science, 2022, 68 (5): 3703-3725.
30 Eklund, J C, Mannor, M J. Keep Your Eye on the Ball or on the Field? Exploring the Performance Implications of Executive Strategic Attention[J]. Academy of Management Journal, 2021, 64(6): 1685-1713. DOI:10.5465/amj.2019.0156
31 Feng, G, Giglio, S, Xiu, D. Taming the Factor Zoo: A Test of New Factors[J]. The Journal of Finance, 2020, 75(3): 1327-1370. DOI:10.1111/jofi.12883
32 Gaber, M M, Zaslavsky, A, Krishnaswamy, S. A Survey of Classification Methods in Data Streams[M]. Data Streams. Advances in Database Systems, Springer, Boston, MA, 2007.
33 Gamache, D, Mcnamara, G, Mannor, M J, et al. Motivated to acquire? The impact of ceo regulatory focus on firm acquisitions[J]. Academy of Management Journal, 2014, 58(4): 1261-1282.
34 Ghoddusi, H, Creamer, G G, Rafizadeh, N. Machine learning in energy economics and finance: A review[J]. Energy Economics, 2019, 81: 709-727. DOI:10.1016/j.eneco.2019.05.006
35 Giardili, S, Ramdas, K, Williams, J W Leadership and Productivity: A Study of US Automobile Assembly Plants[J]. Management Science, 2022, 69 (3): 1500-1517.
36 Guzman, J, Li, A. Measuring Founding Strategy[J]. Management Science, 2022, 69(1): 101-118.
37 Guzman, J, Stern, S. The State of American Entrepreneurship: New Estimates of the Quality and Quantity of Entrepreneurship for 32 US States, 1988-2014. Working Paper, 2020.
38 Haans, R. What's the value of being different when everyone is? The effects of distinctiveness on performance in homogeneous versus heterogeneous categories[J]. Strategic Management Journal, 2019, 40(1): 3-27. DOI:10.1002/smj.2978
39 Hambrick, D C Upper echelons theory: An update[J]. Academy of Management Review, 2007, 32 (2): 334-343.
40 Harrison, J, Josefy, M, Kalm, M, et al. Using supervised machine learning to scale human-coded data: A method and dataset in the board leadership context[J]. Strategic Management Journal, 2022, 44(7): 1780-1802.
41 Harrison, J S, Thurgood, G R, Boivie, S, et al. Measuring CEO personality: Developing, validating, and testing a linguistic tool[J]. Strategic Management Journal, 2019, 40(8): 1316-1330. DOI:10.1002/smj.3023
42 Hasan, M M, Taylor, G, Richardson, G. Brand Capital and Stock Price Crash Risk[J]. Management Science, 2022, 68(10): 7221-7247. DOI:10.1287/mnsc.2021.4197
43 He, V, Puranam, P, Shrestha, Y, et al. Resolving governance disputes in communities: A study of software license decisions[J]. Strategic Management Journal, 2020, 41(10): 1837-1868. DOI:10.1002/smj.3181
44 Hoehn, W, Koenig, F G, Moehring, R H, et al. Integrated Sequencing and Scheduling in Coil Coating[J]. Management Science, 2011, 57(4): 647-666. DOI:10.1287/mnsc.1100.1302
45 Hofman, J M, Sharma, A, Watts, D J. Prediction and explanation in social systems[J]. Science, 2017, 355(6324): 486-488. DOI:10.1126/science.aal3856
46 Joachims, T. Text categorization with Support Vector Machines: Learning with many relevant features. In Proceedings of the ECML. Chemnitz, Germany, 1998, 137-142.
47 Jones, G, Khanna, T. Bringing history (back) into international business[J]. Journal of International Business Studies, 2006, 37(4): 453-468. DOI:10.1057/palgrave.jibs.8400198
48 Jones, S. Corporate bankruptcy prediction: a high dimensional analysis[J]. Review of Accounting Studies, 2017, 22(3): 1366-1422. DOI:10.1007/s11142-017-9407-1
49 Joseph, J, Borland, H, Orlitzky, M, et al. Seeing Versus Doing: How Businesses Manage Tensions in Pursuit of Sustainability[J]. Journal of Business Ethics, 2020, 164(2): 349-370. DOI:10.1007/s10551-018-4065-1
50 Kaplan, S, Vakili, K. The double-edged sword of recombination in breakthrough innovation[J]. Strategic Management Journal, 2015, 36(10): 1435-1457. DOI:10.1002/smj.2294
51 Kotsiantis, S B. Decision trees: a recent overview[J]. Artificial Intelligence Review, 2013, 39(4): 261-283. DOI:10.1007/s10462-011-9272-4
52 Krogh, G, Roberson, Q, Gruber, M. Recognizing and Utilizing Novel Research Opportunities with Artificial Intelligence[J]. Academy of Management Journal, 2023, 66(2): 367-373. DOI:10.5465/amj.2023.4002
53 Lee, A L, Inceoglu, I, Hauser, O, et al. Determining causal relationships in leadership research using Machine Learning: The powerful synergy of experiments and data science[J]. Leadership Quarterly, 2022, 33(5): 101426. DOI:10.1016/j.leaqua.2020.101426
54 Maron, M E, Kuhns, J L. On Relevance, Probabilistic Indexing and Information Retrieval[J]. Journal of the Acm, 1960, 7(3): 216-244. DOI:10.1145/321033.321035
55 Menon, A, Nave, G, bhatia, S. Emotional Expressions Predict Risky Decisions by S&P 500 Executives. SSRN Electronic Journal, 2018, 10.2139/ssrn. 3303000.
56 Miric, M, Boudreau, K J, Jeppesen, L, B. Protecting their digital assets: The use of formal & informal appropriability strategies by App developers[J]. Research Policy, 2019, 48(8): 103738. DOI:10.1016/j.respol.2019.01.012
57 Miric, M, Jeppesen, L B. Does piracy lead to product abandonment or stimulate new product development?: Evidence from mobileplatform-baseddeveloper firms[J]. Strategic Management Journal, 2020, 41(12): 2155-2184. DOI:10.1002/smj.3208
58 Miric, M, Jia, N, Huang, K. Using Supervised Machine Learning for Large-scale Classification in Management Research: The Case of Identifying Artificial Intelligence Patents[J]. Strategic Management Journal, 2023, 44(2): 491-519. DOI:10.1002/smj.3441
59 Miric, M, Pagani, M, Sawy, O. When and Who Do Platform Companies Acquire? Understanding the Role of Acquisitions in the Growth of Platform Companies[J]. MIS Quarterly, 2021, 45(4): 2159-2174. DOI:10.25300/MISQ/2022/16374
60 Mitchell, T M. Machine Learning, McGraw-Hill, Inc, 1997.
61 Mullainathan, S, Spiess, J. Machine Learning: An Applied Econometric Approach[J]. Journal of Economic Perspectives, 2017, 31(2): 87-106. DOI:10.1257/jep.31.2.87
62 Nauhaus, S, Luger, J, Raisch, S. Strategic Decision Making in the Digital Age: Expert Sentiment and Corporate Capital Allocation[J]. Journal of Management Studies, 2021, 58(7): 1933-1961. DOI:10.1111/joms.12742
63 Ng, A, Jordan, M I. On Discriminative vs. Generative Classifiers: A comparison of logistic regression and naive Bayes[J]. Neural Information Processing Systems, 2001, 2: 841-848.
64 Ng, W, Sherman, E L. In Search of Inspiration: External Mobility and the Emergence of Technology Intrapreneurs[J]. Organization Science, 2022, 33(6): 2300-2321. DOI:10.1287/orsc.2021.1530
65 Ngai, E W T, Wu, Y Y. Machine learning in marketing: A literature review, conceptual framework, and research agenda[J]. Journal of Business Research, 2022, 145(2): 35-48.
66 Rathje, J M, Katila, R. Enabling Technologies and the Role of Private Firms: A Machine Learning Matching Analysis[J]. Strategy Science, 2021, 6(1): 5-21. DOI:10.1287/stsc.2020.0112
67 Sen, P, Puranam, P. Do Alliance Portfolios Encourage or Impede New Business Practice Adoption? Theory and Evidence from the Private Equity Industry[J]. Strategic Management Journal, 2022, 43(11): 2279-2312. DOI:10.1002/smj.3399
68 Tidhar, R, Eisenhardt, K. Get Rich or Die Trying… Finding Revenue Model fit Using Machine Learning and Multiple Cases[J]. Strategic Management Journal, 2020, 41(7): 1245-1273. DOI:10.1002/smj.3142
69 Wager, S, Athey, S. Estimation and Inference of Heterogeneous Treatment Effects using Random Forests[J]. Journal of the American Statistical Association, 2018, 113(523): 1228-1242. DOI:10.1080/01621459.2017.1319839
70 Yang, J-C, Chuang, H-C, Kuan, C-M. Double machine learning with gradient boosting and its application to the Big N audit quality effect[J]. Journal of Econometrics, 2020, 216(1): 268-283. DOI:10.1016/j.jeconom.2020.01.018