DBS Bank is planning to expand its quant pricing engine (QPEs) with artificial intelligence (AI) and machine learning (ML) solutions.
The bank had earlier hinted on its QPE "acting as a central pricing engine for [the] DBS trading business, supporting the interest rate, equities, FX and XVA trading business" in 2022.
The bank is now in the process of effectively scaling QPEs on the cloud to meet customers’ pricing requests in near-real time.
Gengpu Liu, executive director of quant and tech modelling in DBS’ Treasury & Markets (T&M) business said the bank is now planning to incorporate "advanced analytics" into its QPE.
“We’re always looking for new ways to boost efficiency, improve performance, reduce costs, and explore opportunities,” Liu said.
Quantitative traders, or quants for short, use mathematical models and large data sets to automate trading - identify opportunities and buy and sell securities.
The QPE is a pricing tool to support trading customers identify profitable opportunities using in-house algorithms.
DBS hosted these engines on legacy on-premises infrastructures with traditional databases.
Liu said, “Previously, setting up an on-premises infrastructure was a painful task that involved tedious resource acquisition and lengthy provisioning activities."
It migrated the QPEs to Amazon Web Services (AWS) to offer "near real-time pricing with a dynamic workload" for its customers.
Expanding on the QPE since 2018, the bank has built nine subsystems for many trading activities in a "short period of three years".
Solutions
The AWS cloud has enabled DBS to provision capacity as needed by using Amazon Elastic Compute Cloud (Amazon EC2) and Amazon Elastic Container Service (Amazon ECS), a fully managed container orchestration service.
DBS uses an in-memory data store - Amazon ElastiCache for Redis as a near real-time cache to handle complicated job queues for its QPE.
We have "successfully" improved the pricing query response time from up to 1 minute to as fast as 0.5 seconds, he added.
The bank has achieved "infinite scalability", which it considers a key to success in attaining computing needs in its trading business.
DBS said it can widen its solution stack by accessing a variety of services and technologies on AWS.
For instance, the bank can set up ElastiCache clusters to partition data across multiple shards. It can process massive data on demand and generate responses from its pricing models at a fast speed.
DBS has also cut down its costs using Amazon EC2 Spot Instances, which runs fault-tolerant workloads.
The bank has now embarked on a road map to build on its QPE with analytics capabilities.