A Study on Forecasting Mutual Fund Net Asset Value in Thailand

Article Sidebar

PDF
Published: Jan 26, 2021
Keywords:
Forecasting K-nearest Neighbor Method Artificial Neural Networks Method

Main Article Content

Kunyanat Suraruengchai
Department of Statistics, Faculty of Science, Kasetsart University, Bangkok
Boonorm Chomtee
Department of Statistics, Faculty of Science, Kasetsart University, Bangkok
Prasit Payakkapong
Department of Statistics, Faculty of Science, Kasetsart University, Bangkok

Abstract

This study aims to compare the two forecasting methods: k-nearest neighbor method and artificial neural networks method in forecasting mutual fund net asset values in Thailand. There are 2 groups of the studied data. The first group contains 4-year and 5-month data from 30 September 2015 to 28 February 2020 of 991 sets of K-CHX and 1079 sets of SCBCE and TMBCOF. The accuracy of forecasting are shown as the Mean Absolute Percent Error (MAPE) and Mean Squared Error (MSE). The results indicated that for the 3 mutual funds, based on MAPE and MSE, artificial neural network method is better. The second group con-tains from 1 to 15 March 2020 which are used ahead of forecasts. It is found that artificial neural networks method is better for SCBCE and TMBCOF. However, k-nearest neighbor method is better for K-CHX.

Article Details

Issue
Vol. 31 No. 1 (2021): January-March, 2021
Section
Applied Science Research Articles

The articles published are the opinion of the author only. The author is responsible for any legal consequences. That may arise from that article.

References

[1] K. Alkhatib and H. Najadat, I. Hmeidi, and Mohammed K. Ali Shatnawi, “Stock price prediction using K-Nearest Neighbor (Knn) algorithm,” International Journal of Business, Humanities and Technology, vol. 3, no. 3, pp. 32–44, 2013.

[2] I. Vainionpaa and S. Davidsson, “Stock market prediction using the K Nearest Neighbours algorithm and a comparison with the moving average formula,” B.S. thesis, Department of Computer Science Education, KTH Royel Institute of Technology, Sweden, 2014.

[3] T. Prakobphon, “Artificial neural networks,” HCU Journal 73, vol. 12, no. 24, 2009 (in Thai).

[4] T. Sujjaviriyasup, “Artificial neural network model for forecasting monthly price of maize in Thailand,” Srinakharinwirot Science Journal, vol. 34, no. 1, pp. 91-107, 2018 (in Thai).

[5] SCB Bank. (2019). Fund Information. SCB Asset Management Co.,Ltd. Bangkok, Thailand. [Online]. Available: https://www.scbam.com/th/fund/default/fund-information/SCBCE.

[6] Kasikorn Asset Management (2019). Mutual Fund. Kasikorn Asset Management Co., Ltd. Bangkok, Thailand. [Online]. Available: https://www.kasikornasset.com/TH/mutualfund/nav/Pages/history.aspx?fund_code=K-CHX.

[7] TMB Bank. (2019). Past Investment Unit Value. TMB Asset Management Co., Ltd. Bangkok, Thailand. [Online]. Available: https://www.tmbbank.com/tmbadvisory/partner/previous.