Machine Learning Based Portfolio Analysis

Authors

  • Yingjie Han

DOI:

https://doi.org/10.54097/wc6epk11

Keywords:

Machine Learning, Profit Forecast, Portfolio Analysis.

Abstract

This paper investigates the effectiveness of machine learning methods in predicting stock returns in China. In this paper, we use 16 liquidity, momentum, market risk and macro fundamentals indicators, as well as 112 interaction terms between indicators and macro variables with monthly stock excess returns for the lagged period from January 2000 to November 2015 as the sample set, train elasticity networks, gradient boosting, random forests, neural networks, and simple linear regression models, and based on the data of December 2015, predict the January 2016 returns, form portfolios based on the predictions and hold them for 12 months, and thereafter roll over the extended sample period to form new portfolios, and evaluate the performance of the portfolios based on out-of-sample alpha versus the estimated shap value to assess the significance of the metrics. The results show that the machine learning approach significantly outperforms the simple linear regression model and performs better in terms of weighted portfolio returns. The portfolio constructed based on the neural network model (NN1) achieves the lowest mean square error and the highest model fit, and NN3 achieves the highest out-of-sample alpha, suggesting that the model is able to achieve higher risk-adjusted returns when risk factors are taken into account. Further analysis shows that the NN3 model is able to effectively identify high-yielding stocks and control portfolio risk, making it a preferred strategy for investment portfolios in the Chinese equity market. This paper still supports Leippold's (2022) view that liquidity indicators are most important after excluding fundamental indicators.

Downloads

Download data is not yet available.

References

[1] Ali A, Hwang L S, Trombley M A. Arbitrage risk and the book-to-market anomaly [J]. Journal of Financial Economics, 2003, 69 (2): 355-373.

[2] Amihud Y. Illiquidity and stock returns: cross-section and time-series effects [J]. Journal of Financial Markets, 2002, 5 (1): 31-56.

[3] Ang A, Hodrick R J, Xing Y, et al. The cross‐section of volatility and expected returns [J]. The Fournal of Finance, 2006, 61 (1): 259-299.

[4] Baker M, Stein J C. Market liquidity as a sentiment indicator [J]. Journal of Financial Markets, 2004, 7 (3): 271-299.

[5] Bali T G, Brown S J, Murray S, et al. A lottery-demand-based explanation of the beta anomaly [J]. Journal of Financial and Quantitative Analysis, 2017, 52 (6): 2369-2397.

[6] Bali T G, Cakici N, Whitelaw R F. Maxing out: Stocks as lotteries and the cross-section of expected returns [J]. Journal of Financial Economics, 2011, 99 (2): 427-446.

[7] Carhart M M. On persistence in mutual fund performance [J]. The Journal of Finance, 1997, 52 (1): 57-82.

[8] Chen A Y, McCoy J. Missing values handling for machine learning portfolios [J]. Journal of Financial Economics, 2024, 155: 103815.

[9] Chordia T, Subrahmanyam A, Anshuman V R. Trading activity and expected stock returns [J]. Journal of Financial Economics, 2001, 59 (1): 3-32.

[10] Daniel K, Hirshleifer D, Sun L. Short-and long-horizon behavioral factors [J]. The Review of Financial Studies, 2020, 33 (4): 1673-1736.

[11] Datar V T, Naik N Y, Radcliffe R. Liquidity and stock returns: An alternative test [J]. Journal of Financial Markets, 1998, 1 (2): 203-219.

[12] DeMiguel V, Gil-Bazo J, Nogales F J, et al. Machine learning and fund characteristics help to select mutual funds with positive alpha [J]. Journal of Financial Economics, 2023, 150 (3): 103737.

[13] Eugene F, French K. The cross-section of expected stock returns [J]. Journal of Finance, 1992, 47 (2): 427-465.

[14] Fama E F, French K R. A five-factor asset pricing model [J]. Journal of Financial Economics, 2015, 116 (1): 1-22.

[15] Fama E F, MacBeth J D. Risk, return, and equilibrium: Empirical tests [J]. Journal of Political Economy, 1973, 81 (3): 607-636.

[16] Green J, Hand J R M, Zhang X F. The characteristics that provide independent information about average US monthly stock returns [J]. The Review of Financial Studies, 2017, 30 (12): 4389-4436.

[17] Gu S, Kelly B, Xiu D. Autoencoder asset pricing models [J]. Journal of Econometrics, 2021, 222 (1): 429-450.

[18] Gu S, Kelly B, Xiu D. Empirical asset pricing via machine learning [J]. The Review of Financial Studies, 2020, 33 (5): 2223-2273.

[19] Gul F A, Kim J B, Qiu A A. Ownership concentration, foreign shareholding, audit quality, and stock price synchronicity: Evidence from China [J]. Journal of Financial Economics, 2010, 95 (3): 425-442.

[20] Hou K, Xue C, Zhang L. Digesting anomalies: An investment approach [J]. The Review of Financial Studies, 2015, 28 (3): 650-705.

[21] Jegadeesh N, Titman S. Returns to buying winners and selling losers: Implications for stock market efficiency [J]. The Journal of Finance, 1993, 48 (1): 65-91.

[22] Leippold M, Wang Q, Zhou W. Machine learning in the Chinese stock market [J]. Journal of Financial Economics, 2022, 145 (2): 64-82.

[23] Liu W. A liquidity-augmented capital asset pricing model [J]. Journal of Financial Economics, 2006, 82 (3): 631-671.

[24] Novy-Marx R. The other side of value: The gross profitability premium [J]. Journal of Financial Economics, 2013, 108 (1): 1-28.

[25] Rapach D, Zhou G. Forecasting stock returns [M] Handbook of Economic Forecasting, 2013, 2: 328-383.

[26] Saffi P A C, Sigurdsson K. Price efficiency and short selling [J]. The Review of Financial Studies, 2011, 24 (3): 821-852.

[27] Stambaugh R F, Yuan Y. Mispricing factors [J]. The Review of Financial Studies, 2017, 30 (4): 1270-1315.

[28] Welch I. The link between fama-french time-series tests and fama-macbeth cross-sectional tests [J]. Available at SSRN 1271935, 2008.

Downloads

Published

25-11-2024

How to Cite

Han, Y. (2024). Machine Learning Based Portfolio Analysis. Highlights in Business, Economics and Management, 44, 135-147. https://doi.org/10.54097/wc6epk11