Performing technical analysis to predict Japan REITs' movement through ensemble learning

Abstract

PurposeThe 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/approachThis 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.FindingsThe 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 implicationsIt 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/valueThe predictability of J-REITs using technical indicators was compared among different returns horizons and the models (Extreme Gradient Boosting and Random Forest).

Applications, Opportunities and Challenges of AI in the Real Estate Sector

“…Results show that the location of the properties is a decisive factor in the renting strategy used: properties located in historical centers, tourist attractions, in neighborhoods with lower minority rates and higher nightlife vibe are those that have higher returns in using a short-term renting strategy. [39] focuses on RE investment trusts (REIT) in Japan. The author proposes to evaluate the performance of joint learning models such as RF and XGBoost when the REITs' return expectations are between 1 and 300 days.…”

The Performance and Diversification Potential of Non-Listed Value-Add Real Estate Funds in Japan

“…Even though the Japanese commercial real estate investment market has in general seen a number of scholarly papers in the past, they are concentrated largely on its listed real estate investment segment (e.g., J-REITs and real estate operating companies (REOCs)). These studies have empirically investigated the listed real estate sector (J-REITs in particular) across a wide range of topics, related to its investment performance characteristics (Newell and Peng 2012) including its various sub-sectors (Cho 2017;Lin et al 2019), the application of machine learning forecasting models (Loo 2020), the impact of seasoned issuance of shares (Ong et al 2011), J-REIT takeovers (Ma and Michayluk 2015), J-REIT IPO pricing (Kutsuma et al 2008), sponsor ownership (Tang and Mori 2017), and debt information and refinancing activities on their performance (Tang et al 2011).…”

Soil Infiltration Rate Impact on Water Quality Modeled Using Random Forest Regression

“…The M5 tree model may be thought of as the binary decision tree is built on top of a linear regression function as its foundation (leaf) that is capable of predicting continuous numeric characteristics [13]. For the purpose of building the tree-based model, the approach of divide and conquer is used.…”