How Is a Machine Learning Algorithm Now-Casting Stock Returns? A Test for ASELSAN

Abstract

This paper focus on measuring the performance of algortimic trading in now-casting of stock returns using machine learning technics. For this task, (1) nine commonly used trend indicators to capture the behavior of the stock and a binary variable to signal positive/negative returs are used as predictors and target variable, respectively; (2) the standart machine learning process (splitting data, choosing the best performing algorithm among the alternatives, and testing this algorithm for new data) is applied to ASELSAN (a Turkish defense industry company) stock traded in BIST-100. The main findings are: (1) the decission tree algoritm performs better than K-nearest Neighbours, Logistic Regression, Bernoili Naïve Bayes alternatives; (2) the now-casting model allowed to realize an 18% of yield over the test period; (3) the model’s performance metrics (accuracy, precision, recall, f1 scores and the ROC-AUC curve) that are commonly used for classification models in machine learning takes values just in the acceptance boundary.