Enhancing a Multi-Factor Equity Strategy via Artificial Intelligence and Technical Indicators

Daiya Mita and Akihiko Takahashi
Additional contact information
Daiya Mita: Nomura Asset Management Co, ltd.,
Akihiko Takahashi: School of Interdisciplinary Mathematical Sciences, Meiji University /Center for Advanced Research in Finance (CARF), The University of Tokyo

No CARF-F-632, CARF F-Series from Center for Advanced Research in Finance, Faculty of Economics, The University of Tokyo

Abstract: This study proposes a novel equity investment strategy that effectively integrates artificial intelligence techniques, multi factor models and financial technical indicators. In investment-related finance research, there exists a serious problem that many actively managed funds fail to outperform simple index buy-and-hold strategies. Our objective is to address this issue by designing a strategy that not only delivers high investment performance but also maintains interpretability, an often-overlooked aspect in complex models based on artificial intelligence. Specifically, as an equity long (buying) strategy, this paper extends a Five Factor model, a well-known finance model for its theoretical grounding in financial economics and its high accountability, to predict future returns by using a gradient boosting machine and a state space model. In addition, an index futures short (selling) strategy for downside hedging is developed with IF-THEN rules and three technical indicators. To the best of our knowledge, this is the first study to develop an equity investment framework based on a new, more predictable Five Factor model, enhanced by artificial intelligence techniques and technical indicators. Finally, empirical analysis is conducted using the data on the Japanese stock market from 1/04/2010 to 12/29/2023 and shows that the proposed strategy outperforms not only the baseline buy-and-hold strategy, but also typical mutual funds for the Japanese equities. Furthermore, statistical tests for Sharpe and Sortino ratios reveal that while the baseline strategy fails to reject the null hypothesis, particularly in the most recent period, our proposed strategy exhibits statistically significant performance across all subperiods, underscoring its robustness.

Pages: 30 pages
Date: 2026-10-23
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.carf.e.u-tokyo.ac.jp/wp/wp-content/uploads/2026/10/F632.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cfi:fseres:cf632

Access Statistics for this paper

More papers in CARF F-Series from Center for Advanced Research in Finance, Faculty of Economics, The University of Tokyo Contact information at EDIRC.
Bibliographic data for series maintained by ().