Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/44426
Title: Investment portfolio balancing using adaptive neuro-fuzzy inference systems (ANFIS)
Authors: Techatewon, Phakhawet.
Keywords: DRNTU::Engineering::Computer science and engineering
Issue Date: 2011
Abstract: Investors have begun to apply financial tools to the technical analysis to maximize the returns. The efficient frontier is one of the widely used techniques in selecting the portfolio, and Adaptive Network‐based Fuzzy Inference System (ANFIS) is renowned for its effective prediction capability. Many researchers have applied ANFIS for the stock prediction; however, it has been done in an efficient market, and mostly used for just stock prediction. In this study, the efficient frontier and ANFIS has been combined to create the effective portfolio selection system for the investors in United Kingdom (UK) market and Thailand market. They are efficient market and emerging market respectively. The user interface which applied the trained data and modern portfolio theory’s formula is able to display the efficient frontier graph and its information. The system is also able to generate the portfolio as well as the weight for each stock to the investors according to the duration and desired rate of return. The result from the experiment shows that the system predicted stock value and the real stock value are more than 94% correlated. The normalized root mean square error for the prediction value is less than 7%. These correlation and error applied to both UK market and Thai market which can be inferred that the system is also effective in an emerging market like Thai stock market. The simulation also showed that the system is able to make profit for both markets in various durations of investment as well. Thus, the system is able to generate an effective portfolio for the investors.
URI: http://hdl.handle.net/10356/44426
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
SCE10-0290.pdf
  Restricted Access
1.18 MBAdobe PDFView/Open

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.