An investigation of model selection criteria for technical analysis of moving average

Subject Areas : Mathematical Optimization

Milad Jasemi ¹ , Ali M Kimiagari ²

1 - Department of Industrial Engineering, Islamic Azad University, Masjed Soleyman Branch, Masjed Soleyman, 61649, Iran
2 - Department of Industrial Engineering, Amirkabir University of Technology, Tehran, 15914, Iran

Received: 2020-10-01 Accepted : 2020-10-01 Published : 2012-01-01

Keywords: moving average, Portfolio Selection, Investment decision, Technical Analysis, Trend forecasting,

Abstract :

Moving averages are one of the most popular and easy-to-use tools available to a technical analyst, and they also form the building blocks for many other technical indicators and overlays. Building a moving average (MA) model needs determining four factors of (1) approach of issuing signals, (2) technique of calculating MA, (3) length of MA, and (4) band. After a literature review of technical analysis (TA) from the perspective of MA and some discussions about MA as a TA, this paper is structured to highlight the effects that each of the first three factors has on performance of MA as a TA. The results that based on some experiments with real data support the fact that deciding about the first and second factors is not much critical, and more attention should be paid to other factors.