TORA’s new AI TCA product moves beyond traditional TCA by using AI techniques to accurately estimate price slippage for trades before they enter the market.

Asset managers are increasingly relying on analytics to build more sophisticated, quantitative best execution processes to meet MiFID II’s higher standards and to gain a competitive advantage. Trading desks are also embracing rapid advances in AI technology to automate and improve the efficiency of their operations. The addition of this pre-trade TCA product to the TORA OEMS enables traders to monitor costs across the lifecycle of a trade and take advantage of new insights to help improve investment decision making.

Utilizing an extensive library of historical global market data, the new pre-trade TCA solution examines the core attributes of orders such as spread, volatility and volume consumption and estimates the market impact of using any broker and algo combination to help traders determine the optimal place to send their orders.

“This TCA solution is built upon a convolutional neural network that is trained using real time and historical data. Machine learning algorithms are used to continuously capture new order data as it becomes available. Through this feedback mechanism the network weights are adapted to reflect the additional information and thus increase the estimation precision over time”, said Pascal Kuyten from the TORA quantitative research group.

Commenting on the development, David Tattan, Head of European Business Development at TORA said: “MiFID II raises the bar for traders to deliver and demonstrate best execution to investors and regulators. Automation and artificial intelligence will play an important part in helping them keep up with market complexity and a proliferation of information to process. We are very excited about the potential for this product to enhance our clients’ investment frameworks and it is an important addition to TORA’s MiFID II optimized solution.”