Detection of Trade-Based Manipulations in Borsa Istanbul with Artificial Neural Networks

This study investigates trade-based manipulations in Borsa Istanbul (BIST). An artificial neural network model to detect trade-based manipulation from the daily data of manipulated stocks was proposed. As a result of this study, artificial neural networks are proven to be successful in detecting trade-based manipulations in the stock market in terms of the measurement methods of accuracy, sensitivity, and fl score. The proposed model's performance was compared with some commonly used classification algorithms. Experimental results show that an fl score of 0.86, a sensitivity of 0.87 and an accuracy of 0.89 in market manipulation detection were achieved.