Adjustable cash inflows based online investment decision making

Benmeng Lyu; Sini Guo; Jia Wen Gu; Wai Ki Ching

doi:10.1016/j.eswa.2025.127940

Adjustable cash inflows based online investment decision making

Benmeng Lyu
, Sini Guo^*
, Jia Wen Gu
, Wai Ki Ching

^*此作品的通讯作者

The University of Hong Kong
Southern University of Science and Technology
Beijing Institute of Technology

科研成果: 期刊稿件 › 文章 › 同行评审

1 引用（Scopus）

摘要

Online portfolio selection tackles the sequential investment decision making and optimization issues with the market information updated constantly. In this work, we propose two novel online portfolio selection algorithms, ACIE and ACIE2, for online investment with dynamically adjustable cash inflows. Unlike traditional models that assume a fixed capital base, our framework allows investors to flexibly adjust capital injection levels over time, guided by return forecasting. ACIE optimizes portfolio weights and cash inflow proportion in a single-period setting, while ACIE2 extends this to a two-period lookahead optimization, offering improved stability and foresight. Both models are formulated as nonlinear constrained optimization problems, which can be solved by trust region interior point methods. Extensive experiments across four real-world datasets validate that our methods outperform a broad range of baseline strategies in terms of cumulative wealth, Sharpe ratio, and Calmar ratio. Additionally, we demonstrate that the dynamic cash inflow mechanism enhances risk control and adapts effectively to different market environments, making our approach practical and effective for real-world investment management.

源语言	英语
期刊论文编号	127940
期刊	Expert Systems with Applications
卷	284
DOI	https://doi.org/10.1016/j.eswa.2025.127940
出版状态	已出版 - 25 7月 2025
已对外发布	是

访问文件

10.1016/j.eswa.2025.127940

其它文件与链接

链接到 Scopus 的出版物

引用此

@article{5727df60f90b4623bb343282a1c39a86,

title = "Adjustable cash inflows based online investment decision making",

abstract = "Online portfolio selection tackles the sequential investment decision making and optimization issues with the market information updated constantly. In this work, we propose two novel online portfolio selection algorithms, ACIE and ACIE2, for online investment with dynamically adjustable cash inflows. Unlike traditional models that assume a fixed capital base, our framework allows investors to flexibly adjust capital injection levels over time, guided by return forecasting. ACIE optimizes portfolio weights and cash inflow proportion in a single-period setting, while ACIE2 extends this to a two-period lookahead optimization, offering improved stability and foresight. Both models are formulated as nonlinear constrained optimization problems, which can be solved by trust region interior point methods. Extensive experiments across four real-world datasets validate that our methods outperform a broad range of baseline strategies in terms of cumulative wealth, Sharpe ratio, and Calmar ratio. Additionally, we demonstrate that the dynamic cash inflow mechanism enhances risk control and adapts effectively to different market environments, making our approach practical and effective for real-world investment management.",

keywords = "Adjustable cash inflows, Nonlinear programming, Online portfolio selection, Transaction cost, Trust region method",

author = "Benmeng Lyu and Sini Guo and Gu, \{Jia Wen\} and Ching, \{Wai Ki\}",

note = "Publisher Copyright: {\textcopyright} 2025 Elsevier Ltd",

year = "2025",

month = jul,

day = "25",

doi = "10.1016/j.eswa.2025.127940",

language = "English",

volume = "284",

journal = "Expert Systems with Applications",

issn = "0957-4174",

publisher = "Elsevier Ltd.",

}

TY - JOUR

T1 - Adjustable cash inflows based online investment decision making

AU - Lyu, Benmeng

AU - Guo, Sini

AU - Gu, Jia Wen

AU - Ching, Wai Ki

PY - 2025/7/25

Y1 - 2025/7/25

N2 - Online portfolio selection tackles the sequential investment decision making and optimization issues with the market information updated constantly. In this work, we propose two novel online portfolio selection algorithms, ACIE and ACIE2, for online investment with dynamically adjustable cash inflows. Unlike traditional models that assume a fixed capital base, our framework allows investors to flexibly adjust capital injection levels over time, guided by return forecasting. ACIE optimizes portfolio weights and cash inflow proportion in a single-period setting, while ACIE2 extends this to a two-period lookahead optimization, offering improved stability and foresight. Both models are formulated as nonlinear constrained optimization problems, which can be solved by trust region interior point methods. Extensive experiments across four real-world datasets validate that our methods outperform a broad range of baseline strategies in terms of cumulative wealth, Sharpe ratio, and Calmar ratio. Additionally, we demonstrate that the dynamic cash inflow mechanism enhances risk control and adapts effectively to different market environments, making our approach practical and effective for real-world investment management.

AB - Online portfolio selection tackles the sequential investment decision making and optimization issues with the market information updated constantly. In this work, we propose two novel online portfolio selection algorithms, ACIE and ACIE2, for online investment with dynamically adjustable cash inflows. Unlike traditional models that assume a fixed capital base, our framework allows investors to flexibly adjust capital injection levels over time, guided by return forecasting. ACIE optimizes portfolio weights and cash inflow proportion in a single-period setting, while ACIE2 extends this to a two-period lookahead optimization, offering improved stability and foresight. Both models are formulated as nonlinear constrained optimization problems, which can be solved by trust region interior point methods. Extensive experiments across four real-world datasets validate that our methods outperform a broad range of baseline strategies in terms of cumulative wealth, Sharpe ratio, and Calmar ratio. Additionally, we demonstrate that the dynamic cash inflow mechanism enhances risk control and adapts effectively to different market environments, making our approach practical and effective for real-world investment management.

KW - Adjustable cash inflows

KW - Nonlinear programming

KW - Online portfolio selection

KW - Transaction cost

KW - Trust region method

UR - https://www.scopus.com/pages/publications/105004365416

U2 - 10.1016/j.eswa.2025.127940

DO - 10.1016/j.eswa.2025.127940

M3 - Article

AN - SCOPUS:105004365416

SN - 0957-4174

VL - 284

JO - Expert Systems with Applications

JF - Expert Systems with Applications

M1 - 127940

ER -

Adjustable cash inflows based online investment decision making

摘要

访问文件

其它文件与链接

学术指纹

引用此