Listen to the signals from an interactive agent‐based model

ABSTRACT

In this paper, we develop a trading strategy based on the estimated results of an interactive agent-based model. We examine our trading strategy in nine markets proxied by market indices. Our strategy is able to ride the rising trend and avoid declining periods. In addition, our strategy could outperform market index in some financial markets.

KEYWORDS:

• Trading strategy
• agent-based model
• noise traders
• fundamentalists
• speculative bubbles

JEL CLASSIFICATION:

• G7.001

Highlights

• We introduce a trading strategy based on the estimated results of an interactive agent-based model.

• Our strategy is able to capture the rising periods and avoid declining periods.

• Our strategy outperforms the market index in some financial markets.

Disclosure statement

No potential conflict of interest was reported by the author.

Notes

¹ See, for example, Hommes (2006).

² For stability of the coefficients of estimated parameters and so on, see Cheng and Kim (2017) section 6.3.

³ See Cheng and Kim (2017) section 5.2, the chosen parameters space were picked based on empirical simulation experiences.

⁴ The time period covered in different markets vary due to the availability of data from Bloomberg. For instance, the adjusted closing prices for the SSE index are available since 12/19/1990.

⁵ We move the window from January 1983 to September 2015 and estimate the coefficients of chosen key parameter for each window from January 1985 to September 2015.