Support Resistance Levels towards Profitability in Intelligent Algorithmic Trading Models

Past studies showed that more advanced model architectures and techniques are being developed for intelligent algorithm trading, but the input features of models across these very similar. This justifies increasing need new meaningful to better explain price movements. study shows inclusion Support Resistance engineered from proposed novel methodology increased machine learning model’s aggregate profitability performance by 65% eight currency pairs when compared an identical without features. Moreover, results also distribution is statistically significantly different between two with features, respectively. Therefore, objective this 3-fold: (1) propose a automate levels identification; (2) engineer Machine Learning Models improve algorithmic trading profitability; (3) provide empirical evidence towards significant incremental contribution (Psychological Price Levels) in models.