Machine learning gives Danske transformative quant boost
In 2006, a new mathematical technique was introduced to banking. The adjoint algorithmic differentiation (AAD) allowed quantitative analysts (or quants) to run modelling that produced accurate simulation results at high speeds. The development shook finance and soon derivatives markets were being commonly navigated by algorithmic calculations of credit value adjustments (CVAs).
Now, two Copenhagen-based quants, Brian Huge and Antoine Savine, have improved the technique by twinning it with machine learning that spots patterns in the datasets. Building their neural networks on top of the existing quant architecture, the pair think they can produce comparable results thousands of times faster.
“The pathwise differentials in themselves contain plenty of information and we suspected we could use it to train pricing approximations more effectively,” Huge told Risk . “It can also be used to generate dynamic risk reports, because we can quickly compute risks in a vast number of future scenarios.”
“Everything we can do with the differential machine learning can also be done already with nested Monte Carlo simulation,” says Savine. “With differential machine learning you just do it thousands of times faster and with similar accuracy.”
Giuseppe Benedetti, senior quantitative analyst at financial software vendor FIS, says: “Every time you increase speed, the quality of your risk management massively improves, because when calculations are slow, people have to cut corners.”
He adds: “We’re looking into this technique as a candidate to be implemented in our products. Using AAD pathwise derivatives to regularise the exposure estimation process is a very clever idea to reduce noise and make the methodology more reliable and applicable in production environments.”
Danske Bank is testing the combined model for market risk before implementing it on a wider scale. It is expected to be rolled out in 2021.
Google is using AI to design faster and improved processors
Engineers at Google are now using artificial intelligence (AI) to design faster and more efficient processors, and then using its chip designs to develop the next generation of specialised computers that run the same type of AI algorithms.
Google designs its own computer chips rather than buying commercial products, this allows the company to optimise the chips to run its own software, but the process is time-consuming and expensive, usually taking two to three years to develop.
Floorplanning, a stage of chip design, involves taking the finalised circuit diagram of a new chip and arranging the components into an efficient layout for manufacturing. Although the functional design of the chip is complete at this point, the layout can have a huge impact on speed and power consumption.
Previously floorplanning has been a highly manual and time-consuming task, says Anna Goldie at Google. Teams would split larger chips into blocks and work on parts in parallel, fiddling around to find small refinements, she says.
Fast chip design
They have created a convolutional neural network system that performs the macro block placement by itself within hours to achieve an optimal layout; the standard cells are automatically placed in the gaps by other software. This ML system should be able to produce an ideal floorplan far faster than humans at the controls. The neural network gradually improves its placement skills as it gains experience, according to the AI scientists.
In their paper, the Googlers said their neural network is "capable of generalising across chips — meaning that it can learn from experience to become both better and faster at placing new chips — allowing chip designers to be assisted by artificial agents with more experience than any human could ever gain."
Generating a floorplan can take less than a second using a pre-trained neural net, and with up to a few hours of fine-tuning the network, the software can match or beat a human at floorplan design, according to the paper, depending on which metric you use.
"Our method was used to design the next generation of Google’s artificial-intelligence accelerators, and has the potential to save thousands of hours of human effort for each new generation," the Googlers wrote. "Finally, we believe that more powerful AI-designed hardware will fuel advances in AI, creating a symbiotic relationship between the two fields.