An Algorithmic Trading Strategy for the Colombian US Dollar Inter-bank Bulk Market SET-FX Based on an Evolutionary TPOT AutoML Predictive Model

In this paper, we introduce a competitive algorithmic trading strategy for the Colombian US dollar inter-bank bulk order-driven market, SET-FX. The strategy is underpinned by an evolutionary predictive model constructed with the Tree-based Pipeline Optimization Tool (TPOT). TPOT is a strongly-typed genetic programming-based automated machine learning tool that employs the Non-dominated Sorting Genetic Algorithm II (NSGA-II), a multi-objective evolutionary algorithm. It aims to discover machine learning models that balance maximum accuracy with minimum complexity.