Bank of Montreal is working with Toronto-based startup Riskfuel Analytics to develop AI-based models for pricing and scenario analysis of structured derivatives transactions.
The partnership follows a pilot which saw quantitative researchers from both firms speed up valuation of autocallable notes which "previously presented significant runtime challenges".
BMO says that working with Riskfuel will reduce its reliance on slow and expensive financial models to calculate pricing and risks of structured products.
Graham Wells, head, equity quantitative modeling, global markets engineering, BMO, says: "Riskfuel has delivered a cutting-edge proof of concept that promises the most significant step forward in quantitative finance in a generation. Removing the runtime hurdle opens the door for significant advancements in accuracy and realism of structured notes pricing models."
Ryan Ferguson, CEO, Riskfuel, adds: "Structured notes are traditionally priced using slow numerical techniques that simulate an extremely large number of possible future states of the financial markets. Riskfuel uses Deep Learning to replace these slow simulators with very fast neural nets."