Forecast model for financial time series: An approach based on harmonic oscillators
Abstract
A financial asset price-forecasting model based on damped driven harmonic oscillator is presented. It is inspired on the idea that in the price fluctuations a restoring force to a supposed fair price, besides inertia and dissipation, could take place. The model is evaluated in an emerging market, which is of the Brazilian stock exchange BM&FBovespa (B3). The choice is due to the expectation that the model could perform better by exploiting deviations from the concept of efficient market. In such direction, the use of Hurst exponent to choose suitable assets to trade employing the model is discussed. A fairly common trading system endowed with the stop gain and stop loss limiting parameters was used to evaluate the model. To avoid excessive arbitrariness, those parameters were established after a study referred to the data itself in which a consistently defined relation return/risk is computed. The proposed model overcomes a full random model in four studied cases. In the aggregated result of 5 stocks, it was achieved a return of investment of 64:80% , disregarding operating costs. This is 72.19% higher than the respective result from random model.
- Publication:
-
Physica A Statistical Mechanics and its Applications
- Pub Date:
- July 2020
- DOI:
- 10.1016/j.physa.2020.124365
- Bibcode:
- 2020PhyA..54924365G
- Keywords:
-
- Econophysics;
- Forecasting model;
- Harmonic oscillator;
- Stock markets;
- Hurst exponent;
- Algorithmic trading;
- Quantitative finance