An Intelligent Decision Support System for Investment Analysis

Abstract

We present an intelligent decision support system that combines decision analysis and traditional investment evaluation and analysis. The system brings to the ordinary user expertise in both decision analysis and investment evaluation techniques, as well as domain knowledge about the market. The system supports the entire decision analysis cycle and provides facilities and tools for decision modeling, probability assessment, model evaluation, and sensitivity analysis. An example based on the Shanghai Stock Market is presented. We demonstrate how an investment decision model for the stock market is constructed by the system and how the optimal decision is obtained. Sensitivity and value of information analysis were also carried out by the system.

Predicting business processes of the social insurance using recurrent neural network and Markov chain

“…Integrated PPMs (Pfeffer, 2005;Rozinat et al, 2009) with theoretical decision models (Natarajan et al, 2011;Vanderfeesten et al, 2011) have captured a lot of attention to create JM2 17,3 integrated decision support systems (Liu et al, 2010) A decision support system empowers ordinary users in both decision analysis and domain knowledge. It has, for example, combined decision analysis with investment valuation techniques and stock market knowledge (Poh, 2000). A detailed discussion of case-, rule-and combinatorial methods was provided in Liu et al (2010) to support the decision-maker.…”

Automatic Formulation of the Internal Control Report over Financial Reporting

“…KBS has been applied to an abundance of decision problems in financial and production domains, such as for supporting investments decisions (see Poh, 2000), for performance measurement (Ammar, Duncombe, Jump, & Wright, 2004;Khan & Wibisono, 2008;Wang, Huang, & Lai, 2008), for formulating budget planning -which is called Knowledge-based Intelligent Decision Support System or KIDSS system (Wen et al, 2005), for supporting business in small financial institutions (Chung & Pak, 2006), for supporting decision on credit granting -which is called Moody's KMV Risk Advisor™ or MRA (Kumra et al, 2006), for formulating the auditor"s opinion -which is called Auditor Report EXpert or AREX (Wahdan, 2006), for optimising portfolio management (Bao & Yang, 2008), for measuring logistic performance -which is called knowledge-based logistics performance measurement system or KLPMS (Choy et al, 2008), for financial knowledge management (Shiue et al, 2008;Cheng et al, 2009), for evaluating the credit worthiness of customers using balance scorecard strategic planning opinions -which is called BSC knowledge-based system or BSCKBS (Huang, 2009), for selecting supplier/customer with the consideration of benefits, opportunities, costs, and risks (Lee, 2009), for determining cost-volume-profit analysis (Yuan, 2009), for determining (pro)-performance appraisal (Chen & Chen, 2010), for obtaining customerbuying patterns (Jayanthi & Vishal, 2011) and for clarifying financial ratios (Gunawan, 2012), for assessing materiality level at the audit planning stage Materiality Expert (MEX) (Wahdan & Hassan, 2019). While organizations develop information systems, auditors must adapt their approaches to comply with the fast evolution of these systems.…”

Enhancing stock market prediction with extended coupled hidden Markov model over multi-sourced data

“…Most of previous studies utilize historical time-series prices to predict the future prices of instruments in financial market and make predictions with various models [37,42,41,6,23,8,9,18]. An intelligent decision support system combines influence digram generator, probability assessor, value function generator to help decision-makers make better investment decisions [39]. Recent works begin to explore other data sources to improve the predictive power.…”