Nonlinear Pricing Mechanism of China's Public REITs: A Study on Predicting REITs Returns Based on Explainable Machine Learning

Haibo  Liao

doi:10.54691/xxg2fe69

Authors

Haibo Liao

DOI:

https://doi.org/10.54691/xxg2fe69

Keywords:

Public REITs, Explainable Machine Learning, Return Prediction, Nonlinear Pricing, Interaction Effect.

Abstract

To address the research gap where the nonlinear pricing mechanism of China's public REITs market remains unelucidated, this study constructs an explainable machine learning (XAI) analytical framework, innovatively realizing a full-process research of "prediction-attribution-discovery". Based on the daily trading data (2021-2024) of 40 public REITs, the XGBoost algorithm is adopted to build a return prediction model. The pure long-only portfolio (ML_top20) constructed from this model achieved a cumulative return of 41.29% (Sharpe ratio = 0.12) during the out-of-sample testing period (2022-2024), significantly outperforming the market benchmark portfolio which recorded a cumulative return of -9.51% (Sharpe ratio = -0.03). Comprehensive analysis using machine learning interpretation tools reveals that stock market return, momentum effect, Treasury bond yield, and daily price range constitute the core driving factors, while feature interaction and nonlinear effects dominate the REITs price formation mechanism. The findings of this study suggest that a new generation of pricing models integrating interaction factors and nonlinear responses should be developed, providing support for the establishment of cross-market risk early warning mechanisms.

Downloads

Download data is not yet available.

References

[1] CHEN J H, CHANG T T, HO C R, et al. Grey Relational Analysis and Neural Network Forecasting of REIT Returns, Quantitative Finance, Vol. 14 (2014) No.14, p.2033-2044.

[2] CHAN S H, CHEN J, WANG K. Are REIT IPOs Unique? The Global Evidence, The Journal of Real Estate Finance and Economics, Vol. 47 (2013) No.4, p.719-759.

[3] DERWALL J, MARQUERING W. REIT Momentum and the Performance of Real Estate Mutual Funds, Financial Analysts Journal, Vol. 65 (2009) No.5, p.24-34.

[4] LIU C H, HARTZELL D J, HOESLI M E. International Evidence on Real Estate Securities as an Inflation Hedge, Real Estate Economics, Vol. 25 (1997) No.2, p.193-221.

[5] HUANG S D. Analysis of Influencing Factors of REITs Investment Return Rate, Journal of Xinjiang University of Finance and Economics, (2015) No.4, p.5-14. (In Chinese)

[6] DU Y H, WU D, WANG S Q, et al. Analysis of Key Risks in Industrial Park REITs Returns, Construction Economy, Vol. 43 (2022) No.1, p.32-38. (In Chinese)

[7] MA S C, LI T T. Study on the Correlation Between Infrastructure Public REITs Price Index and Stock Market Price, Price: Theory & Practice, (2023) No.11, p.197-201, 216. (In Chinese)

[8] YI D H. Empirical Analysis of Influencing Factors on the Price of China's Expressway Public REITs, Investment Research, Vol. 43 (2024) No.4, p.25-36. (In Chinese)

[9] HABBAB F Z, KAMPOURIDIS M. An In-depth Investigation of Five Machine Learning Algorithms for Optimizing Mixed-Asset REITs, Expert Systems with Applications, Vol. 235 (2024), p. (to be supplemented if available).

[10] GU Z Y. Study on Market Price and Investor Structure of China's Public REITs, Management Modernization, Vol. 44 (2024) No.3, p.57-65. (In Chinese)

[11] LUNDBERG S M, ERION G, CHEN H, et al. From Local Explanations to Global Understanding with Explainable AI for Trees, Nature Machine Intelligence, Vol. 2 (2020), p.56-67.

[12] CHEN T, GUESTRIN C. XGBoost: A Scalable Tree Boosting System, Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (New York, USA, 2016), p.785-794.

[13] LUNDBERG S, LEE S. A Unified Approach to Interpreting Model Predictions, Proc. 31st International Conference on Neural Information Processing Systems (Long Beach, USA, 2017), p. (to be supplemented if available).

[14] BALI T G, BECKMEYER H, MOERKE M, et al. Option Return Predictability with Machine Learning and Big Data, Review of Financial Studies, Vol. 36 (2023) No.9, p.3548-3602.

[16] GU S, KELLY B, XIU D. Empirical Asset Pricing via Machine Learning, Review of Financial Studies, Vol. 33 (2020) No.5, p.2223-2273.

[17] DEMIGUEL V, GIL-BAZO J, NOGALES F J, et al. Machine Learning and Fund Characteristics Help to Select Mutual Funds with Positive Alpha, Journal of Financial Economics, Vol. 150 (2023) No.3, p. (to be supplemented if available).

[18] APLEY D W, ZHU J. Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Models, Journal of the Royal Statistical Society: Series B (Statistical Methodology), Vol. (to be supplemented if available) (2020), p. (to be supplemented if available).

[19] LI Z Z, SHENG L. Study on the Return and Risk Characteristics of China's Infrastructure REITs, Macroeconomic Research, (2022) No.9, p.97-105. (In Chinese)