TITLE:
Implementing Trade Strategy with HMM Model: A Practice on Some Telecommunication Companies
AUTHORS:
Chuanzhong Sun
KEYWORDS:
Hidden Markov Model, Stock Trend Status, Trade Strategy
JOURNAL NAME:
Open Journal of Social Sciences,
Vol.6 No.3,
March
13,
2018
ABSTRACT: Stock trend prediction has been a challenge task for many traders. For stock traders, promptly predicting the bearish or bullish market status is very helpful in reducing the losses and increasing returns. This paper presents a Hidden Markov Models (HMM) approach for determining stock trend status: “upper trend”, “low trend”, or “Medium”. And a simple trade strategy based on the estimated trend status is formulated. Then the strategy is applied to three telecommunication stocks: AT & T, Verizon, and China Mobile for trade performance evaluation. We use the real daily trading data of NYSE from October 25, 2016 to November 06, 2017 to test performance of the strategy. The results show that the strategy is actually very encouraging. For the generally bearish period of telecommunication sector, a 9.7% and 3.7% return rate can still be achieved for AT & T and Verizon. For China Mobile, although the return is negative, the final loss is still 2% less than if “Buy and Hold”.