Automated trading
Automated trading systems seek to place orders on the financial markets so as to make capital grow while at the same time limiting the inherent risk. The prices of financial products are time series that vary according to many parameters that are not all observable. Within machine learning, time series are very specific data that require the use of specific methods
One of the characteristics of machine learning approaches to automated trading lies in the evaluation of performance. More often than not, the assessment is based solely on the accuracy of the market direction (up or down). However, on a series of predictions, a model with high accuracy can also result in a high loss since the amplitude is not taken into account.
As part of the Chair, we study:
- metrics with true exploitability beyond accuracy,
- the use of backtesting for the construction of more efficient models,
- reinforcement learning reinforcement for the construction of robust models.
Decision trees with complex conditions for trading
Decision trees with complex conditions for trading.
JDSE 2022
The Junior Conference on DataScience and Engeneering 2022 (JDSE) took place on september 15-16, on the Polytechnique campus (Palaiseau).
Hugo Thimonier has the opportunity to present “TracInAD: Measuring Influence for Anomaly Detection” to the audience.
Marc Velay won the best poster contest with his poster about “Robustness Analysis of Deep RL for Portfolio Selection”.
Temporal Point Processes
Machine learning applied to Hawkes processes.
Fraud and explainability
An investigation on explaining supervised machine learning models.