Adrian de Valois-Franklin
WALLACE is a genetic algorithm based on the concept of survival of the fittest. Constantly growing and developing, it is currently analysing about 10,000 securities across 42 dimension space features. As a self-learning system, the team at Castle Ridge offer it new features and data sources, and WALLACE decides what will add value from these, adopting and learning itself to build a highly liquid market neutral strategy.
- Survival of the fittest: An insight into the process and journey of creating WALLACE
- The burden of unsupervised learning: enabling the machine to decide what inputs are more or less useful
- Becoming social: How WALLACE explains its decisions and exposes its thought process to overcome interpretability issues