Narrow Results

We study the effects of considering different criteria simultaneously on portfolio optimization. Using a single-period optimization setting, we use various combinations of expected return, variance, liquidity and Conditional Value at Risk criteria. With stocks from Borsa Istanbul, we make computational studies to show the effects of these criteria on objective and decision spaces. We also consider cardinality and weight constraints and study their effects on the results. In general, we observe that considering alternative criteria results in enlarged regions in the efficient frontier that may be of interest to the decision maker. We discuss the results of our experiments and provide insights.

High liquidity is one of the most significant objectives in the banking industry. To ensure stable liquidity, client prediction is a common method adopted by bank managers. Although there has been some literature discussing the methods to make client predictions, it lacks quantitative comparison between algorithms. This study will focus on the prediction of bank clients and compare the effectiveness of different algorithms in machine learning (neural network, decision tree, logistic regression). It is designed to compare the five metrics (Type I sample f1-score, Type II sample f1-score, accuracy, Area Under Curve, Kolmogorov-Smirnov) to distinguish the feasibility of different algorithms. The higher index represents the better algorithm. As the results, the neural network has the highest AUC (0.85) and highest Type I sample f1-score (0.50), while the logistic regression has the highest accuracy (0.90), KS (0.64), and Type II sample f1-score (0.50). (0.94). According to reality, the neural network is suggested to be the optimal algorithm that needs to be adopted by bank managers for client prediction.