TY - JOUR
KW - Dynamic Strategy
KW - Evolutionary Computation
KW - Finance
KW - Grammatical Evolution
KW - Structural Change
KW - Trading
AU - Carlos Martín
AU - David Quintana
AU - Pedro Isasi
AB - The attainment of trading rules using Grammatical Evolution traditionally follows a static approach. A single rule is obtained and then used to generate investment recommendations over time. The main disadvantage of this approach is that it does not consider the need to adapt to the structural changes that are often associated with financial time series. We improve the canonical approach introducing an alternative that involves a dynamic selection mechanism that switches between an active rule and a candidate one optimized for the most recent market data available. The proposed solution seeks the flexibility required by structural changes while limiting the transaction costs commonly associated with constant model updates. The performance of the algorithm is compared with four alternatives: the standard static approach; a sliding window-based generation of trading rules that are used for a single time period, and two ensemble-based strategies. The experimental results, based on market data, show that the suggested approach beats the rest.
IS - Regular Issue
M1 - 6
N2 - The attainment of trading rules using Grammatical Evolution traditionally follows a static approach. A single rule is obtained and then used to generate investment recommendations over time. The main disadvantage of this approach is that it does not consider the need to adapt to the structural changes that are often associated with financial time series. We improve the canonical approach introducing an alternative that involves a dynamic selection mechanism that switches between an active rule and a candidate one optimized for the most recent market data available. The proposed solution seeks the flexibility required by structural changes while limiting the transaction costs commonly associated with constant model updates. The performance of the algorithm is compared with four alternatives: the standard static approach; a sliding window-based generation of trading rules that are used for a single time period, and two ensemble-based strategies. The experimental results, based on market data, show that the suggested approach beats the rest.
PY - 2021
SP - 104
EP - 111
T2 - International Journal of Interactive Multimedia and Artificial Intelligence
TI - Dynamic Generation of Investment Recommendations Using Grammatical Evolution
UR - https://www.ijimai.org/journal/sites/default/files/2021-05/ijimai_6_6_11.pdf
VL - 6
SN - 1989-1660
ER -