### Abstract

In 1950s, Markowitzs first proposed portfolio theory based on a mean-variance (MV) model to balance the risk and profit of decentralized investment. The two main inputs of MV are expected return rate and the variance of expected return rate. The expected return rate is an estimated value which is often decided by experts. Various uncertainty of stock price brings difficulties to predict return rate even for experts. MV model has its tendency to maximize the influence of errors in the input assumptions. Some scholars used fuzzy intervals to describe the return rate. However, there were still some variables decided by experts. This paper proposes a classification method to find the latent relationship between the interval return rate and the trading data of a stock and predict the interval of return rate without consulting any expert. Then this paper constructs the portfolio model based on minimax rule with interval numbers. The evaluation results show that the proposed method is reliable.

Original language | English |
---|---|

Title of host publication | IEEE International Conference on Fuzzy Systems |

Publisher | Institute of Electrical and Electronics Engineers Inc. |

Pages | 2047-2054 |

Number of pages | 8 |

ISBN (Print) | 9781479920723 |

DOIs | |

Publication status | Published - 2014 Sep 4 |

Event | 2014 IEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2014 - Beijing Duration: 2014 Jul 6 → 2014 Jul 11 |

### Other

Other | 2014 IEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2014 |
---|---|

City | Beijing |

Period | 14/7/6 → 14/7/11 |

### Fingerprint

### Keywords

- Classification
- Interval number
- Minimax
- Portfolio

### ASJC Scopus subject areas

- Software
- Artificial Intelligence
- Applied Mathematics
- Theoretical Computer Science

### Cite this

*IEEE International Conference on Fuzzy Systems*(pp. 2047-2054). [6891693] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/FUZZ-IEEE.2014.6891693

**A minimax model of portfolio optimization using data mining to predict interval return rate.** / Yuan, Meng; Watada, Junzo.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

*IEEE International Conference on Fuzzy Systems.*, 6891693, Institute of Electrical and Electronics Engineers Inc., pp. 2047-2054, 2014 IEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2014, Beijing, 14/7/6. https://doi.org/10.1109/FUZZ-IEEE.2014.6891693

}

TY - GEN

T1 - A minimax model of portfolio optimization using data mining to predict interval return rate

AU - Yuan, Meng

AU - Watada, Junzo

PY - 2014/9/4

Y1 - 2014/9/4

N2 - In 1950s, Markowitzs first proposed portfolio theory based on a mean-variance (MV) model to balance the risk and profit of decentralized investment. The two main inputs of MV are expected return rate and the variance of expected return rate. The expected return rate is an estimated value which is often decided by experts. Various uncertainty of stock price brings difficulties to predict return rate even for experts. MV model has its tendency to maximize the influence of errors in the input assumptions. Some scholars used fuzzy intervals to describe the return rate. However, there were still some variables decided by experts. This paper proposes a classification method to find the latent relationship between the interval return rate and the trading data of a stock and predict the interval of return rate without consulting any expert. Then this paper constructs the portfolio model based on minimax rule with interval numbers. The evaluation results show that the proposed method is reliable.

AB - In 1950s, Markowitzs first proposed portfolio theory based on a mean-variance (MV) model to balance the risk and profit of decentralized investment. The two main inputs of MV are expected return rate and the variance of expected return rate. The expected return rate is an estimated value which is often decided by experts. Various uncertainty of stock price brings difficulties to predict return rate even for experts. MV model has its tendency to maximize the influence of errors in the input assumptions. Some scholars used fuzzy intervals to describe the return rate. However, there were still some variables decided by experts. This paper proposes a classification method to find the latent relationship between the interval return rate and the trading data of a stock and predict the interval of return rate without consulting any expert. Then this paper constructs the portfolio model based on minimax rule with interval numbers. The evaluation results show that the proposed method is reliable.

KW - Classification

KW - Interval number

KW - Minimax

KW - Portfolio

UR - http://www.scopus.com/inward/record.url?scp=84912553307&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84912553307&partnerID=8YFLogxK

U2 - 10.1109/FUZZ-IEEE.2014.6891693

DO - 10.1109/FUZZ-IEEE.2014.6891693

M3 - Conference contribution

AN - SCOPUS:84912553307

SN - 9781479920723

SP - 2047

EP - 2054

BT - IEEE International Conference on Fuzzy Systems

PB - Institute of Electrical and Electronics Engineers Inc.

ER -