Cardinal Analytics, a fintech start-up specialising in US corporate bond risk analytics, has selected the Datactics FlowDesigner data quality and matching platform to ensure the data fed into its credit risk model is accurate, complete and timely.
The Belfast based company decided to work with Datactics and sign a three-year licence for FlowDesigner after a project using Python to match data from three Mergent data feeds with different naming conventions failed to achieve a near perfect matching rate. It engaged with Datactics about a month ago and within three weeks a solution was developed that consistently matches 99.5% of the corporate bond data required to power its credit risk model.
Mark Fletcher, CEO at Cardinal, says: “The Datactics solution is an order of magnitude better than Python code. It is quick and effective in producing high quality data for the credit risk model, we can see the audit trail all the time, and we can generate high predictive accuracy scores. Every 1% improvement in predictive accuracy creates an additional $1 billion of bond defaults that we can predict.”
For Datactics, the Cardinal contract marks the first time it has worked with Mergent data feeds and adds to its experience of instrument mapping and matching for clients using data from vendors such as Bloomberg and Thomson Reuters. It is also the first time it has developed a solution in a public cloud environment.
Stuart Harvey, CEO at Datactics, says: “Datactics is a good fit for Cardinal and other specialist analytics firms requiring a pre-analytics layer as we can swap out developer time and deliver fast and high volume data quality and matching using out-of-the-box logic and rules.”