Predictability of HK-REITs returns using artificial neural network

Publication Date14 November 2019
Date14 November 2019
AuthorWei Kang Loo
SubjectProperty management & built environment,Real estate & property,Property valuation & finance
Predictability of HK-REITs returns
using artificial neural network
Wei Kang Loo
James Cook University Australia Singapore Campus, Singapore
Purpose The purpose of this paper is to determine if artificial neural network (ANN) works better than
linear regression in predicting Hong Kong real estate investment trusts(REITs) excess return.
Design/methodology/approach Both ANN and the regression were applied in this study to forecast
the Hong Kong REITs(HK-REITs) return using the capital asset pricing model and Fama and Frenchs
three-factor models. Each result was further split into annual time series as a measure to investigate the
consistency of the performance across time.
Findings ANN had produced a better forecasting results than the regression based on their trading
performance. However, the forecasting performance varied across individual REITs and time periods.
Practical implications ANN should be considered for use when one were to attempt forecasting the
HK-REITs excess returns. However, the trading performance should be always compared with buy and hold
strategy prior to make any investment decisions.
Originality/value This paper tested the predicting power of ANN on the HK-REITs and the consistency of
its predicting power.
Keywords Investment, Artificial neural network, Real estate investment trust, Hong Kong REITs,
Real estate investment, Return forecasting
Paper type Research paper
In finance literature, the predictability of stock returns has remained an important area of
research. Several key variables which can influence stock returns have been identified. For
instance, market risk, size risk and value risk have been observed to affect stock returns.
This outcome is as stipulated by the capital asset pricing model (CAPM) (Sharpe, 1964;
Lintner, 1965), and Fama and Frenchs three-factor model (Fama and French, 1992).
Previous studies (Gaunt, 2004; Soumaré et al., 2013) have used the linear regression method
to model the linear relationship among the variables. Due to the complex nature of the equity
market, more complex techniques like the ANN have also been used to model stock returns
(Cao et al., 2005; Kryzanowski et al., 1993; McNelis, 1996).
Apart from being used to predict stock market returns, the ANN method has also been
applied on indirect real estate investment. Brooks and Tsolacos (2003) used the ANN to
assess real estate stocks, while Serrano and Hoesli (2007) engaged it to assess the equity real
estate investment trusts(REITs) returns. Both were attempting to verify the suitability of
the different models. Eventually, the ANN method had been noted as a model which
produced better forecast results than other conventional regression methods.
Given that the ANN method can potentially work better on indirect real estate markets in
forecasting returns when compared to the regression method. Based on this, it is thus worth
evaluating how the ANN method can predict different REIT markets, besides the equity
REITs, since each of these REIT markets carry different market structures. For instance, the
Asian REITs are different from each other in terms of dividend payouts, regulators,
geographic locations and a few other features (Newell, 2012). Evidence from past literature
(Loo et al., 2016) had also indicated that different REIT markets produce different results,
even within the same research, due to their respective market structure variations.
The complexity of the REIT marketsstructure suggests that the ANN method could be a
more suitable modeling technique for generating the REIT returns. In itself, the ANN
method can address the non-linear and non-stationary characteristics of the data which
Received 9 July 2019
Revised 14 October 2019
Accepted 18 October 2019
The current issue and full text archive of this journal is available on Emerald Insight at:
JournalofProperty Investment&
Vol.38 No. 4, 2020
potentially exist in the financial time series. This is also one of the reasons why many
machine learning techniques are gaining popularity in modeling financial time series
(Kazem et al., 2013; Matías and Reboredo, 2012; Yu et al., 2009).
Despite its advantages, the ANN also carries some drawbacks, such as overfitting issues
(Tu, 1996). For instance, if the ANN estimation produced a function that is too closely fitted
to the training data set, it could lead to substantially large errors when making predictions
through a new set of observation. Therefore, it is helpful to compare the ANN method
against the regression method so as to determine whether the ANN is outperforming.
There are estimation parameters in the ANN method it has to be pre-determined before
it can run the neural network estimation, such as the number of hidden neurons, hidden
layers, learning rate and others. There are no fixed rules on how to determine a
configuration of the ANN that could produce the best forecast. Although it has been said
that one single hidden layer is enough to explain the relationship between the variables, this
is on the condition that sufficient numbers of hidden neurons were used (Hornik et al., 1989;
Masters, 1993). Nonetheless, it is still worth examining how a neural network with different
numbers of hidden layers, and hidden neurons perform, given that the sufficient number of
hidden neurons remained uncertain.
This study was performed for the purpose of determining the forecasting performance of
the ANN on the Hong Kong REITs(HK-REITs) returns. Hong Kong is one of the most
dynamic commercial property markets in Asia (Newell et al., 2010). The HK-REITs carry a
certain attractiveness for investors. For instance, the GZI REITs provide investors with an
exposure to the China property holdings while the Link REITs serve as one of the biggest
retail REITs in Asia (APREA, 2009). As each HK-REIT has different asset holding
compositions in theirportfolio, it would be worthwhile to investigate how the accuracy could
be different across theHK-REITs, and also how the results can be differentacross time since
the portfolio holding the REITs can changeover time. Therefore, it is beneficialto investigate
whether the same ANN method can produce the same forecasting performance across
different HK-REITs when it involved a variety of asset holdings among the HK-REITs.
This study used two common models to predict the HK-REIT returns the CAPM, and
Fama and French three-factor model. The CAPM was chosen due to its capability to
explain the relationship between the risk, andexpectedreturnswithonlyonefactor.
However, one factor might not be enough to explain all the variations of the excess returns
(Fama and French, 2004). Past studies (Chiang et al., 2005; Peterson and Hsieh, 1997) have
shown that Fama and French three-factor model is better than the CAPM in explaining
the EREITs returns. Thus, Fama and French three-factor model was also employed in
this study.
Further to the above, the accuracy of the ANN forecast when used with different
configurations of parameters on the models were also compared with the regression method.
The comparison was made based on all the HK-REITs involved and also based on
individual HK-REITs separately. Each set of comparison was further split into the annual
time series so as to investigate the consistency of the performance across time. Finally, each
result will be compared against the buy and hold strategies so as to determine their returns
performance. This study employed the rolling sample approach in calculating the forecast
because it takes the latest available data in calculating the forecast. This mimics the
practical situation since investors were more likely to use the most recent data from time to
time to predict the nearest future returns of the REITs rather than doing a one-off prediction
to obtain all the forecast. Finally, each result will also be compared against the buy and hold
strategies so as to determine their returns performance. As contribution, the current study
highlights the importance of testing a technique first before applying it, and to seek the
truth of the technique via further testing rather than merely drawing conclusions based on
similar studies.

To continue reading

Request your trial

VLEX uses login cookies to provide you with a better browsing experience. If you click on 'Accept' or continue browsing this site we consider that you accept our cookie policy. ACCEPT