Papers
Topics
Authors
Recent
Search
2000 character limit reached

Large (and Deep) Factor Models

Published 20 Jan 2024 in q-fin.ST, cs.CE, and cs.LG | (2402.06635v1)

Abstract: We open up the black box behind Deep Learning for portfolio optimization and prove that a sufficiently wide and arbitrarily deep neural network (DNN) trained to maximize the Sharpe ratio of the Stochastic Discount Factor (SDF) is equivalent to a large factor model (LFM): A linear factor pricing model that uses many non-linear characteristics. The nature of these characteristics depends on the architecture of the DNN in an explicit, tractable fashion. This makes it possible to derive end-to-end trained DNN-based SDFs in closed form for the first time. We evaluate LFMs empirically and show how various architectural choices impact SDF performance. We document the virtue of depth complexity: With enough data, the out-of-sample performance of DNN-SDF is increasing in the NN depth, saturating at huge depths of around 100 hidden layers.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (66)
  1. Adlam, Ben and Jeffrey Pennington, “The neural tangent kernel in high dimensions: Triple descent and a multi-scale theory of generalization,” in “International Conference on Machine Learning” PMLR 2020, pp. 74–84.
  2. Andreini, Paolo, Cosimo Izzo, and Giovanni Ricco, “Deep dynamic factor models,” arXiv preprint arXiv:2007.11887, 2020.
  3. Arora, Sanjeev, Simon S Du, Wei Hu, Zhiyuan Li, Russ R Salakhutdinov, and Ruosong Wang, “On exact computation with an infinitely wide neural net,” Advances in neural information processing systems, 2019, 32.
  4. Avramov, Doron, Si Cheng, and Lior Metzker, “Machine learning vs. economic restrictions: Evidence from stock return predictability,” Management Science, 2023, 69 (5), 2587–2619.
  5. Bartlett, Peter, “Reproducing kernel Hilbert spaces,” Lecture Notes, CS281B/Stat241B, Statistical Learning Theory, 2003.
  6. Belkin, M, D Hsu, S Ma, and S Mandal, “Reconciling modern machine learning and the bias-variance trade-off. arXiv e-prints,” 2018.
  7. Belkin, Mikhail, “Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation,” Acta Numerica, 2021, 30, 203–248.
  8. Britten-Jones, Mark, “The Sampling Error in Estimates of Mean-Variance Efficient Portfolio Weights,” Journal of Finance, 1999, 54 (2), 655–670.
  9.   , “The sampling error in estimates of mean-variance efficient portfolio weights,” The Journal of Finance, 1999, 54 (2), 655–671.
  10. Bryzgalova, Svetlana, Markus Pelger, and Jason Zhu, “Forest through the trees: Building cross-sections of stock returns,” Available at SSRN 3493458, 2020.
  11. Chen, Luyang, Markus Pelger, and Jason Zhu, “Deep learning in asset pricing,” Management Science, 2023.
  12. Chinco, Alex, Adam D Clark-Joseph, and Mao Ye, “Sparse signals in the cross-section of returns,” The Journal of Finance, 2019, 74 (1), 449–492.
  13. Cochrane, John H, “Presidential address: Discount rates,” The Journal of finance, 2011, 66 (4), 1047–1108.
  14. Didisheim, Antoine, Shikun Ke, Bryan T Kelly, and Semyon Malamud, “Complexity in Factor Pricing Models,” Swiss Finance Institute Research Paper, 2023, (23-19).
  15. Dixon, Matthew and Nick Polson, “Deep fundamental factor models,” SIAM Journal on Financial Mathematics, 2020, 11 (3), SC26–SC37.
  16. Fan, Jianqing, Zheng Tracy Ke, Yuan Liao, and Andreas Neuhierl, “Structural Deep Learning in Conditional Asset Pricing,” Available at SSRN 4117882, 2022.
  17. Feng, Guanhao, Jingyu He, Nicholas G Polson, and Jianeng Xu, “Deep learning in characteristics-sorted factor models,” arXiv preprint arXiv:1805.01104, 2018.
  18.   , Liang Jiang, Junye Li, and Yizhi Song, “Deep Tangency Portfolios,” Available at SSRN 3971274, 2023.
  19.   , Stefano Giglio, and Dacheng Xiu, “Taming the factor zoo: A test of new factors,” The Journal of Finance, 2020, 75 (3), 1327–1370.
  20. Filipović, Damir and Puneet Pasricha, “Empirical Asset Pricing via Ensemble Gaussian Process Regression,” arXiv preprint arXiv:2212.01048, 2022.
  21. Freyberger, Joachim, Andreas Neuhierl, and Michael Weber, “Dissecting characteristics nonparametrically,” The Review of Financial Studies, 2020, 33 (5), 2326–2377.
  22. Ghorbani, Behrooz, Song Mei, Theodor Misiakiewicz, and Andrea Montanari, “When do neural networks outperform kernel methods?,” Advances in Neural Information Processing Systems, 2020, 33, 14820–14830.
  23. Giglio, Stefano, Bryan Kelly, and Dacheng Xiu, “Factor models, machine learning, and asset pricing,” Annual Review of Financial Economics, 2022, 14, 337–368.
  24. Gu, Shihao, Bryan Kelly, and Dacheng Xiu, “Autoencoder Asset Pricing Models,” Journal of Econometrics, 2020.
  25.   ,   , and   , “Empirical asset pricing via machine learning,” The Review of Financial Studies, 2020, 33 (5), 2223–2273.
  26. Guijarro-Ordonez, Jorge, Markus Pelger, and Greg Zanotti, “Deep learning statistical arbitrage,” arXiv preprint arXiv:2106.04028, 2021.
  27. Han, Insu, Amir Zandieh, Jaehoon Lee, Roman Novak, Lechao Xiao, and Amin Karbasi, “Fast Neural Kernel Embeddings for General Activations,” in “Advances in Neural Information Processing Systems” 2022.
  28. Han, Yufeng, Ai He, David Rapach, and Guofu Zhou, “Expected stock returns and firm characteristics: E-LASSO, assessment, and implications,” SSRN, 2019.
  29. Harvey, Campbell R, Yan Liu, and Heqing Zhu, “… and the cross-section of expected returns,” The Review of Financial Studies, 2016, 29 (1), 5–68.
  30. Hastie, Trevor, Andrea Montanari, Saharon Rosset, and Ryan J Tibshirani, “Surprises in high-dimensional ridgeless least squares interpolation,” Annals of statistics, 2022, 50 (2), 949.
  31. Hou, Kewei, Chen Xue, and Lu Zhang, “Replicating anomalies,” The Review of Financial Studies, 2020, 33 (5), 2019–2133.
  32. Hron, Jiri, Yasaman Bahri, Jascha Sohl-Dickstein, and Roman Novak, “Infinite attention: NNGP and NTK for deep attention networks,” in “International Conference on Machine Learning” 2020.
  33. Jacot, Arthur, Franck Gabriel, and Clément Hongler, “Neural tangent kernel: Convergence and generalization in neural networks,” Advances in neural information processing systems, 2018, 31.
  34. Jensen, Theis Ingerslev, Bryan Kelly, and Lasse Heje Pedersen, “Is there a replication crisis in finance?,” The Journal of Finance, 2023, 78 (5), 2465–2518.
  35. Jumper, John, Richard Evans, Alexander Pritzel, Tim Green, Michael Figurnov, Olaf Ronneberger, Kathryn Tunyasuvunakool, Russ Bates, Augustin Žídek, Anna Potapenko et al., “Highly accurate protein structure prediction with AlphaFold,” Nature, 2021, 596 (7873), 583–589.
  36. Kelly, Bryan and Dacheng Xiu, “Financial Machine Learning,” Working Paper, 2023.
  37.   , Seth Pruitt, and Yinan Su, “Characteristics are Covariances: A Unified Model of Risk and Return,” Journal of Financial Economics, 2020.
  38. Kelly, Bryan T, Boris Kuznetsov, Semyon Malamud, and Teng Andrea Xu, “Deep Learning from Implied Volatility Surfaces,” Swiss Finance Institute Research Paper, 2023, (23-60).
  39.   , Semyon Malamud, and Kangying Zhou, “The Virtue of Complexity Everywhere,” Available at SSRN, 2022.
  40.   ,   , Mohammad Pourmohammadi, and Fabio Trojani, “Universal Portfolio Shrinkage,” Swiss Finance Institute Research Paper, 2023.
  41. Kingma, Diederik P and Jimmy Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
  42. Kozak, Serhiy, “Kernel trick for the cross-section,” Available at SSRN 3307895, 2020.
  43.    and Stefan Nagel, “When do cross-sectional asset pricing factors span the stochastic discount factor?,” Technical Report, National Bureau of Economic Research 2023.
  44.   ,   , and Shrihari Santosh, “Shrinking the cross-section,” Journal of Financial Economics, 2020, 135 (2), 271–292.
  45.   ,   , and   , “Shrinking the cross-section,” Journal of Financial Economics, 2020, 135 (2), 271–292.
  46. Kozak, Serhyi and Nagel, “When do cross-sectional asset pricing factors span the stochastic discount factor?,” Working Paper, 2023.
  47. Lee, Jaehoon, Samuel Schoenholz, Jeffrey Pennington, Ben Adlam, Lechao Xiao, Roman Novak, and Jascha Sohl-Dickstein, “Finite versus infinite neural networks: an empirical study,” Advances in Neural Information Processing Systems, 2020, 33, 15156–15172.
  48. Leippold, Markus, Qian Wang, and Wenyu Zhou, “Machine learning in the Chinese stock market,” Journal of Financial Economics, 2022, 145 (2), 64–82.
  49. Lettau, Martin and Markus Pelger, “Factors that fit the time series and cross-section of stock returns,” The Review of Financial Studies, 2020, 33 (5), 2274–2325.
  50. McLean, R David and Jeffrey Pontiff, “Does academic research destroy stock return predictability?,” The Journal of Finance, 2016, 71 (1), 5–32.
  51. Meng, Xuran, Jianfeng Yao, and Yuan Cao, “Multiple descent in the multiple random feature model,” arXiv preprint arXiv:2208.09897, 2022.
  52. Merchant, Amil, Simon Batzner, Samuel S Schoenholz, Muratahan Aykol, Gowoon Cheon, and Ekin Dogus Cubuk, “Scaling deep learning for materials discovery,” Nature, 2023, pp. 1–6.
  53. Moritz, Benjamin and Tom Zimmermann, “Tree-based conditional portfolio sorts: The relation between past and future stock returns,” Available at SSRN 2740751, 2016.
  54. Nakkiran, Preetum, Gal Kaplun, Yamini Bansal, Tristan Yang, Boaz Barak, and Ilya Sutskever, “Deep double descent: Where bigger models and more data hurt,” Journal of Statistical Mechanics: Theory and Experiment, 2021, 2021 (12), 124003.
  55. Novak, Roman, Jascha Sohl-Dickstein, and Samuel S. Schoenholz, “Fast Finite Width Neural Tangent Kernel,” in “International Conference on Machine Learning” 2022.
  56.   , Lechao Xiao, Jiri Hron, Jaehoon Lee, Alexander A Alemi, Jascha Sohl-Dickstein, and Samuel S Schoenholz, “Neural tangents: Fast and easy infinite neural networks in python,” arXiv preprint arXiv:1912.02803, 2019.
  57.   ,   ,   ,   , Alexander A. Alemi, Jascha Sohl-Dickstein, and Samuel S. Schoenholz, “Neural Tangents: Fast and Easy Infinite Neural Networks in Python,” in “International Conference on Learning Representations” 2020.
  58. Preite, Massimo Dello, Raman Uppal, Paolo Zaffaroni, and Irina Zviadadze, “What is Missing in Asset-Pricing Factor Models?,” 2022.
  59. Rahimi, Ali and Benjamin Recht, “Random Features for Large-Scale Kernel Machines.,” in “NIPS,” Vol. 3 Citeseer 2007, p. 5.
  60. Ross, Stephen A., “The Arbitrage Theory of Capital Asset Pricing,” Journal of Economic Theory, 1976, 13, 341–360.
  61. Simon, Frederik, Sebastian Weibels, and Tom Zimmermann, “Deep Parametric Portfolio Policies,” Available at SSRN 4150292, 2022.
  62. Sohl-Dickstein, Jascha, Roman Novak, Samuel S. Schoenholz, and Jaehoon Lee, “On the infinite width limit of neural networks with a standard parameterization,” 2020.
  63. Yang, Greg, “Tensor programs ii: Neural tangent kernel for any architecture,” arXiv preprint arXiv:2006.14548, 2020.
  64.    and Edward J Hu, “Tensor programs iv: Feature learning in infinite-width neural networks,” in “International Conference on Machine Learning” PMLR 2021, pp. 11727–11737.
  65.   , Dingli Yu, Chen Zhu, and Soufiane Hayou, “Tensor Programs VI: Feature Learning in Infinite-Depth Neural Networks,” arXiv preprint arXiv:2310.02244, 2023.
  66. Zhou, Yefan, Tianyu Pang, Keqin Liu, Charles H Martin, Michael W Mahoney, and Yaoqing Yang, “Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training,” arXiv preprint arXiv:2312.00359, 2023.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up