Performing technical analysis to predict Japan REITs' movement through ensemble learning
| Published date | 24 April 2020 |
| Date | 24 April 2020 |
| DOI | https://doi.org/10.1108/JPIF-01-2020-0007 |
| Pages | 551-562 |
| Author | Wei Kang Loo |
| Subject Matter | Property management & built environment,Real estate & property,Property valuation & finance |
Performing technical analysis to
predict Japan REITs’movement
through ensemble learning
Wei Kang Loo
James Cook University Australia–Singapore Campus, Singapore, Singapore
Abstract
Purpose –The purpose of this study is to evaluate the performance of the ensemble learning models, such as
the Random Forest and Extreme Gradient Boosting models, in predicting the direction of the Japan real estate
investment trusts (J-REITs) at different return horizons, based on input obtained from various technical
indicators.
Design/methodology/approach –This study measures the predictability of J-REITs with technical
indicators by using different horizons of REITs’return and machine learning models. The ensemble learning
models includes Random Forest and Extreme Gradient Boosting models while the return horizons of REITs
ranging from 1 to 300 days. The results were further split into individual years to check for the consistency of
the performance across time.
Findings –The Extreme Gradient Boosting appears to be the best method in improving forecast accuracy but
not the trading return. A wider return horizons platform seemed to deliver a relatively better performance in
both forecast accuracy and trading return, when compared to the return horizon of one.
Practical implications –It is recommended that the Extreme Gradient Boosting and Random Forest model
be considered by practitioners for back-testing trading model. In addition, selecting different return horizons so
as to achieve a better performance in trading/investment should also be considered.
Originality/value –The predictability of J-REITs using technical indicators was compared among different
returns horizons and the models (Extreme Gradient Boosting and Random Forest).
Keywords Japan, Random Forest, Extreme Gradient Boosting, Real estate investment trust, Return horizons,
Technical analysis
Paper type Research paper
Introduction
Studies looking at technical trading have documented using technical analysis as a means to
analyze the trading. Some recent studies have also generated their evidence of trading based
on technical analysis (Baetje and Menkhoff, 2016;Liu, 2019;Yin and Yang, 2016). In their
study, Baetje and Menkhoff (2016) noted that technical analysis deliver a stable economic
value for predicting the US equity premium from 1966 to 2014. On the other hand, the
economic indicators used were only effective until the 1970s. This phenomenon was also
noted by Liu (2019) who mentioned that technical indicators could be utilized to enhance
positive returns on bitcoin prices.
Different technical indicators have been utilized in technical analysis as a means to
generate different trading signals. This showed that relying on a single technical indicator for
the analysis may not deliver the best trading result. With signals taken from multiple
technical indicators, Basak et al. (2019) then engaged the ensemble machine learning method,
such as Random Forest and Extreme Gradient Boosting as a measure to predict the direction
of the movement of the stock prices. These methods combined different algorithms in order to
portray a better predictive power of the model. Such methods had also been applied in the
field of finance, for instance, to examine bank failures (Carmona et al., 2019;Climent et al.,
2019;Tanaka et al., 2016), classification of intraday stock returns (Lohrmann and Luukka,
2019) and predicting financial distress (Jabeur and Fahmi, 2018).
Despite its advantage, technical analysis may not be able to generate profits for all
countries (Alhashel et al., 2018). This was verified by Alhashel et al. (2018) who found that
Prediction of
Japan REITs’
movement
551
The current issue and full text archive of this journal is available on Emerald Insight at:
https://www.emerald.com/insight/1463-578X.htm
Received 20 January 2020
Revised 11 March 2020
Accepted 12 March 2020
Journal of Property Investment &
Finance
Vol. 38 No. 6, 2020
pp. 551-562
© Emerald Publishing Limited
1463-578X
DOI 10.1108/JPIF-01-2020-0007
To continue reading
Request your trial