A Trend-Shift Model for Global Factor Analysis of Investment Products
A Trend-Shift Model for Global Factor Analysis of Investment Products
复制标题
DOI：
10.1587/transinf.2018edp7420
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Makoto Kirihata;Qiang Ma
中科院分区：
文献类型：
--
作者：
Makoto Kirihata;Qiang Ma
最近，越来越多的人开始投资。了解ff选择fi金融产品的因素对于投资决策是很重要的。然而，对于新手来说，理解因素是一种狂热的崇拜，因为各种因素相互影响(ffiff)。人们已经研究了各种技术，但传统的因素分析方法侧重于揭示某一时期内因素的影响，预测资产净值并不容易。作为对净资产值预测的一种合理解决方案，本文通过在状态空间模型中引入趋势变化点作为移动干扰变量，提出了一种用于全局因素分析的趋势移动模型。此外，为了更准确地实现趋势转移模型，本文对基于趋势的分段方法进行了扩展，提出了一种有效的趋势检测方法TP-ffi(Two-ff)。与任务空间模型相比，TP-任务空间模型通过减少对参数的依赖，能够很好地检测fl的趋势。通过对11种投资信托产品的实验，验证了所提出的模型和方法的有效性和有效性。
SUMMARY Recently, more and more people start investing. Under- standing the factors a ff ecting financial products is important for making investment decisions. However, it is di ffi cult to understand factors for novices because various factors a ff ect each other. Various technique has been stud-ied, but conventional factor analysis methods focus on revealing the impact of factors over a certain period locally, and it is not easy to predict net asset values. As a reasonable solution for the prediction of net asset val- ues, in this paper, we propose a trend shift model for the global analysis of factors by introducing trend change points as shift interference variables into state space models. In addition, to realize the trend shift model e ffi ciently, we propose an e ff ective trend detection method, TP-TBSM (two- phase TBSM), by extending TBSM (trend-based segmentation method). Comparing with TBSM, TP-TBSM could detect trends flexibly by reduc- ing the dependence on parameters. We conduct experiments with eleven investment trust products and reveal the usefulness and e ff ectiveness of the proposed model and method.